CN111598880A - Fluorescence in situ hybridization sample pathological detection system - Google Patents
Fluorescence in situ hybridization sample pathological detection system Download PDFInfo
- Publication number
- CN111598880A CN111598880A CN202010422279.8A CN202010422279A CN111598880A CN 111598880 A CN111598880 A CN 111598880A CN 202010422279 A CN202010422279 A CN 202010422279A CN 111598880 A CN111598880 A CN 111598880A
- Authority
- CN
- China
- Prior art keywords
- image
- instruction
- image acquisition
- image processing
- fluorescence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 111
- 238000007901 in situ hybridization Methods 0.000 title claims abstract description 57
- 230000001575 pathological effect Effects 0.000 title claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 119
- 102100030086 Receptor tyrosine-protein kinase erbB-2 Human genes 0.000 claims abstract description 60
- 101001012157 Homo sapiens Receptor tyrosine-protein kinase erbB-2 Proteins 0.000 claims abstract description 59
- 210000004881 tumor cell Anatomy 0.000 claims abstract description 41
- 230000007170 pathology Effects 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000002509 fluorescent in situ hybridization Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 51
- 230000011218 segmentation Effects 0.000 claims description 19
- 238000013135 deep learning Methods 0.000 claims description 18
- 230000009471 action Effects 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 206010006187 Breast cancer Diseases 0.000 abstract description 9
- 208000026310 Breast neoplasm Diseases 0.000 abstract description 9
- 230000001960 triggered effect Effects 0.000 abstract description 4
- 239000000523 sample Substances 0.000 description 34
- 238000010586 diagram Methods 0.000 description 12
- 210000004027 cell Anatomy 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 8
- 238000002073 fluorescence micrograph Methods 0.000 description 7
- 210000000349 chromosome Anatomy 0.000 description 4
- 230000003321 amplification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 101150054472 HER2 gene Proteins 0.000 description 2
- 238000011460 HER2-targeted therapy Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 108700020302 erbB-2 Genes Proteins 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010186 staining Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 101100314454 Caenorhabditis elegans tra-1 gene Proteins 0.000 description 1
- 208000005443 Circulating Neoplastic Cells Diseases 0.000 description 1
- 102000001301 EGF receptor Human genes 0.000 description 1
- 108060006698 EGF receptor Proteins 0.000 description 1
- 101150029707 ERBB2 gene Proteins 0.000 description 1
- 101710100968 Receptor tyrosine-protein kinase erbB-2 Proteins 0.000 description 1
- 208000005718 Stomach Neoplasms Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004791 biological behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000033077 cellular process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000799 fluorescence microscopy Methods 0.000 description 1
- 238000002546 full scan Methods 0.000 description 1
- 206010017758 gastric cancer Diseases 0.000 description 1
- 208000030776 invasive breast carcinoma Diseases 0.000 description 1
- 230000031864 metaphase Effects 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 210000004940 nucleus Anatomy 0.000 description 1
- 238000010827 pathological analysis Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 201000011549 stomach cancer Diseases 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B30/00—ICT specially adapted for sequence analysis involving nucleotides or amino acids
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30068—Mammography; Breast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Epidemiology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biotechnology (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention provides a fluorescence in situ hybridization sample pathology detection system, comprising: the image acquisition device is configured to carry out microscopic acquisition on the fluorescence in-situ hybridization sample so as to acquire a pathological image; an image processing device configured to perform image processing on the pathological image; the trigger control device is respectively connected with the image acquisition device and the image processing device and is configured to output a control instruction to the image acquisition device and the image processing device; the control instruction comprises an image acquisition instruction or an image processing instruction, wherein when the control device is triggered to output the image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction; when the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the processing instruction to acquire a pathological detection result. The invention can rapidly complete the image acquisition of the FISH section of the breast cancer tumor cell and the HER2 detection.
Description
Technical Field
The invention belongs to the technical field of medical image processing, relates to a pathological detection system, and particularly relates to a fluorescent in-situ hybridization sample pathological detection system.
Background
Breast cancer is the highest incidence of malignant tumors in women, and is rapidly increasing at a rate of 3% to 4% per year, and has become the first killer of women. Clinically, about 20-35% of invasive breast cancers have amplification of the HER2 gene and high expression of protein. The HER2 gene (also known as HER2/neu, c-erbB-2) is located in chromosome 17, region q12 (17q12), one of the epidermal growth factor receptor (HER) family members, which plays an important regulatory role in cellular physiological processes. HER2 is an important breast cancer prognosis judgment factor, HER2 positive (over-expressed or amplified) breast cancer has special clinical characteristics and biological behaviors, and the treatment mode is also greatly different from other types of breast cancer.
With the development of microscopic and pathological diagnosis techniques, Fluorescence In Situ Hybridization (FISH) diagnosis is an effective method for diagnosing HER2 amplification, which counts signals of stained cell samples by fluorescence microscopy and then detects the signals according to the count and ratio of the signals.
On image acquisition, the physician uses multi-channel full-scan counting of the fluorescence, or manually selects the field of view for image acquisition. A selected area is selected at the judgment of HER2 and counted for red and green signals.
However, the conventional HER2 analysis system has the following problems in image acquisition and analysis:
first, there are a division of image acquisition into fluorescence full-slice scanning and manual acquisition. Fluorescence whole-slice scanning takes a long time to scan a whole-slice multi-channel fluorescence image because the field of view is not differentiated. Typically one patient takes one to two hours and is inefficient. In manual acquisition, although the visual field can be selected, the doctor needs to switch back and forth between the visual field observed by the eyepiece and the multi-channel fluorescence image acquired by the computer, which is very inconvenient. In addition, current software on computer analysis can only count out red signals and green signals according to a selected range area, but cannot distinguish tumor cells. In addition, the existing diagnosis system can only recognize red signals and green signals, can not automatically obtain the result of negative or positive HER2 detection according to the detected signals, and still relies on the experience of doctors to diagnose.
The fluorescent in situ hybridization sample pathological detection is applied to the detection of HER2 amplification of breast cancer or gastric cancer, metaphase chromosome karyotype analysis, CTC circulating tumor cell analysis and other pathological detection analysis, and has similar problems. Therefore, how to provide a fluorescence in situ hybridization sample pathological detection system to solve the problems that in the prior art, manual acquisition needs a doctor to switch back and forth between an ocular observation field and a computer acquisition multichannel fluorescence image, and the use is inconvenient; moreover, computer analysis software can only count out red signals and green signals according to the selected range region, and cannot judge defects such as tumor cells, and the like, so that the technical problem to be solved by the technical personnel in the field is really solved.
Disclosure of Invention
In view of the above disadvantages of the prior art, the present invention aims to provide a fluorescence in situ hybridization sample pathology detection system, which is used for solving the problems that in the prior art, manual acquisition requires a doctor to switch back and forth between an ocular observation field and a computer-acquired multi-channel fluorescence image, and the use is inconvenient; and the computer analysis software can only count out red signals and green signals according to the selected range area, so that the problem of tumor cells cannot be judged.
To achieve the above and other related objects, the present invention provides a fluorescence in situ hybridization sample pathology detection system, comprising: the image acquisition device is configured to perform microscopic shooting on the fluorescence in-situ hybridization sample to obtain a pathological image; an image processing device configured to perform image processing on the pathological image; the trigger control device is respectively connected with the image acquisition device and the image processing device and is configured to output a control instruction to the image acquisition device and the image processing device; the control instruction comprises an image acquisition instruction or an image processing instruction; when the trigger control device outputs an image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction; when the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the processing instruction so as to obtain a pathological detection result.
In an embodiment of the present invention, the trigger control device is provided with at least two control keys, and the control keys are used for sensing a trigger action of a user to trigger the output of the image acquisition instruction or the image processing instruction.
In an embodiment of the invention, the pathological image includes a red channel image, a blue channel image or a green channel image; each channel image was obtained by taking a fluorescent in situ hybridization sample under filtering through a monochromatic filter.
In an embodiment of the present invention, the image acquisition instruction includes at least one of a monochrome channel image acquisition instruction, a three-color channel image acquisition instruction, and an area scanning instruction; the monochrome channel image acquisition instruction comprises a blue channel image acquisition instruction, a green channel image acquisition instruction and a red channel image acquisition instruction which are respectively configured to instruct the image acquisition device to acquire a blue channel image, a green channel image and a red channel image; the three-color channel image acquisition instruction is configured to instruct the image acquisition device to sequentially acquire three-color channel images; the area scanning instruction comprises a scanning area first end point determining instruction, a scanning area second end point determining instruction and a scanning instruction, wherein the scanning area first end point determining instruction and the scanning area second end point determining instruction are respectively configured to instruct the image acquisition device to determine a first end point and a second end point of a scanning area, and the first end point and the second end point are used for determining a rectangular area for scanning a sample; and the scanning instruction is configured to instruct the image acquisition device to perform area scanning according to the rectangular area determined by the first end point and the second end point.
In an embodiment of the present invention, the control key includes a monochrome channel image capture key and an image processing key; sequentially outputting the blue channel image acquisition instruction, the green channel image acquisition instruction and the red channel image acquisition instruction by continuously triggering the monochromatic channel image acquisition key; and outputting the image processing instruction by triggering the image processing key.
In an embodiment of the present invention, the control key includes a three-color channel image acquisition key and an image processing key; outputting a three-color channel image acquisition instruction by triggering a three-color channel image acquisition key; and outputting the image processing instruction by triggering the image processing key.
In an embodiment of the present invention, the control key includes a region endpoint key, a scan key, and an image processing key; sequentially outputting a first end point determining instruction of the scanning area and a second end point determining instruction of the scanning area by triggering the area end point key; outputting the scanning instruction by triggering the scanning key; and outputting the image processing instruction by triggering an image processing key.
In an embodiment of the invention, when the image processing apparatus receives the image processing instruction, the blue channel image, the green channel image and the red channel image are synthesized into the fluorescence in-situ hybridization image.
In an embodiment of the invention, when the image processing apparatus receives the image processing command, the image processing apparatus further: segmenting the fluorescence in-situ hybridization image by utilizing a tumor cell segmentation model to obtain a tumor cell region; performing target detection on the tumor cell region by using a HER2 signal detection model to obtain the HER2 signal quantity; performing target detection on the tumor cell region by using a CEP17 signal detection model to obtain the CEP17 signal quantity; and acquiring a pathological detection result according to the CEP17 signal quantity and the HER2 signal quantity.
In an embodiment of the present invention, the tumor cell segmentation model is obtained by training according to a deep learning image segmentation model, and the training method includes the following steps: obtaining tumor cell segmentation training data, wherein the tumor cell segmentation training data comprise fluorescence in-situ hybridization images marked with tumor cell region information; and inputting the tumor cell segmentation training data into the deep learning image segmentation model for training to obtain the tumor cell segmentation model.
In an embodiment of the present invention, the HER2 signal detection model is obtained by training according to a deep learning target detection model, and the training method includes the following steps: acquiring HER2 signal detection training data, wherein the HER2 signal detection training data comprise fluorescence in situ hybridization images marked with HER2 signal position information; and inputting the HER2 signal detection training data into the deep learning target detection model for training to obtain a HER2 signal detection model.
In an embodiment of the present invention, the CEP17 signal detection model is obtained by training a deep learning target detection model, and the training method includes the following steps: obtaining CEP17 signal detection training data, wherein the CEP17 signal detection training data comprise fluorescence in situ hybridization images marked with CEP17 signal position information; inputting the CEP17 signal detection training data into the deep learning target detection model for training to obtain a CEP17 signal detection model
As mentioned above, the fluorescence in situ hybridization sample pathology detection system of the invention has the following beneficial effects:
the fluorescence in situ hybridization sample pathological detection system can rapidly complete the image acquisition of the FISH section and the HER2 detection of the breast cancer tumor cells without switching back and forth between the observation field of the eyepiece and the acquisition of a multichannel fluorescence image by a computer by a doctor.
Drawings
FIG. 1 is a schematic structural diagram of a fluorescence in situ hybridization sample pathology detection system according to an embodiment of the present invention.
Fig. 2A is a schematic diagram illustrating a control key of the touch control device according to an embodiment of the invention.
Fig. 2B is a schematic diagram illustrating another embodiment of a control key of the touch control device according to the present invention.
Fig. 2C is a schematic diagram illustrating another embodiment of a control button on the touch control device according to the present invention.
FIG. 3A is a sample exemplary diagram of the present invention.
Fig. 3B is a sample diagram after the scan area is determined according to the present invention.
Description of the element reference numerals
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Example one
The embodiment provides a fluorescence in situ hybridization sample pathology detection system, which comprises:
the image acquisition device is configured to perform microscopic shooting on the fluorescence in-situ hybridization sample to obtain a pathological image;
an image processing device configured to perform image processing on the pathological image;
the trigger control device is respectively connected with the image acquisition device and the image processing device and is configured to output a control instruction to the image acquisition device and the image processing device; the control instruction comprises an image acquisition instruction or an image processing instruction;
when the trigger control device outputs an image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction; when the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the processing instruction so as to obtain a pathological detection result.
The fluorescence in situ hybridization sample pathology detection system provided in the present embodiment will be described in detail with reference to the drawings. Please refer to fig. 1, which is a schematic structural diagram of a fluorescence in situ hybridization sample pathology detection system in an embodiment. As shown in fig. 1, the fluorescence in situ hybridization sample pathology detection system 1 includes an image acquisition device 11, an image processing device 12, and a trigger control device 13 connected to the image acquisition device 11 and the image processing device 12.
The image acquisition device 11 is configured to take a microscopic photograph of the fluorescence in situ hybridization sample to obtain a pathological image. In practical applications, the image capturing device 11 includes a manual microscope and/or an automatic microscope.
In this embodiment, the pathology image includes a red channel image, a blue channel image, or a green channel image, and the red/blue/green channel image is obtained by capturing a fluorescence in situ hybridization sample under filtering by a monochromatic filter.
The image processing device 12 is configured to perform image processing on the pathological image.
The trigger control device 13, which is respectively connected to the image capturing device 11 and the image processing device 12, is configured to sense a trigger action through different control keys to output a control instruction to the image capturing device 11 and the image processing device 12. The control instruction comprises an image acquisition instruction or an image processing instruction. In this embodiment, the efficiency of acquiring FISH images is improved by the trigger control device 13.
In this embodiment, when the trigger control device 13 outputs an image capturing instruction 11 to the image capturing device, the image capturing device 11 captures a corresponding pathological image according to the image capturing instruction. When the trigger control device 13 outputs an image processing instruction to the image processing device 12, the image processing device 12 processes the pathological image according to the image processing instruction to obtain a pathological detection result.
Two control keys are arranged on the trigger control device 13, and the control keys are used for sensing the trigger action of a user to trigger the output of the image acquisition instruction or the image processing instruction.
In this embodiment, the image capture instruction is a monochrome channel image capture instruction.
The monochrome channel image acquisition instruction comprises a blue channel image acquisition instruction, a green channel image acquisition instruction and a red channel image acquisition instruction. The blue channel image acquisition instruction is configured to instruct the image acquisition device to acquire a blue channel image, the green channel image acquisition instruction is configured to instruct the image acquisition device to acquire a green channel image, and the red channel image acquisition instruction is configured to instruct the image acquisition device to acquire a red channel image.
Please refer to fig. 2A, which is a schematic diagram illustrating an embodiment of a control button on a trigger control device. As shown in fig. 2A, the control key 2 includes a monochrome channel image capture key 21 and an image processing key 22.
In this embodiment, the monochrome channel image capture key 21 is triggered three times, and the blue channel image capture instruction, the green channel image capture instruction, and the red channel image capture instruction are sequentially output to the image capture device 11, and the image capture device 11 captures a blue channel image, a green channel image, and a red channel image, respectively.
In another embodiment, the monochrome channel image capture keys 21 may be respectively set as three keys of a red channel image capture key, a green channel image capture key, and a blue channel image capture key.
The monochrome channel image processing key 22 is triggered to output the image processing instruction to the image processing device 12, the image processing device 12 synthesizes the blue channel image, the green channel image and the red channel image into a fluorescence in situ hybridization image, and a tumor cell segmentation model is used for segmenting the fluorescence in situ hybridization image to obtain a tumor cell region; performing target detection on the tumor cell region by using a HER2 signal detection model to obtain the HER2 signal quantity; performing target detection on the tumor cell region by using a CEP17 signal detection model to obtain the CEP17 signal quantity; and acquiring a pathological detection result according to the CEP17 signal quantity and the HER2 signal quantity. The pathological detection result comprises the ratio of the HER2 signal quantity to the CEP signal quantity, and a negative or positive detection result judged according to the ratio and the average HER2 copy number/cell.
In one embodiment, the judgment criteria of the detection result includes the following 5 cases:
no. 1, the ratio of HER2/CEP17 is more than or equal to 2.0, and the average HER2 copy number/cell is more than or equal to 4.0: this case was judged to be FISH positive. If a plurality of HER2 signals are connected into a cluster, the FISH positive can be directly judged.
Species 3, HER2/CEP17 ratio <2.0, average HER2 copy number/cell > 6.0: it is recommended to increase the count of cells for this case and to determine FISH positive if the results remain unchanged. Studies have shown that if CEP17 is replaced with another probe on chromosome 17, a significant portion of the results in this group of cases translate to a ratio of HER 2/chromosome 17 replacement probe >2.0, with an average HER2 copy number/cell > 6.0. This group of people should have more accumulation according to the syndrome medical basis.
In the 4 th category, the ratio of HER2/CEP17 is less than 2.0, the average HER2 copy number/cell is more than or equal to 4.0 and less than 6.0, and the existing evidence-based medical evidence shows that if the IHC result of HER2 is not 3+, whether the patients with the FISH result can benefit from the anti-HER 2 targeted therapy is uncertain at present, and a more sufficient evidence-based medical evidence needs to be waited. This case suggests recounting the signals in at least 20 nuclei and, if the results change, performing a comprehensive judgment analysis of the two results. If this is still the case, it is necessary to note in the FISH report: the HER2 status of the patients needs to be judged by combining with IHC results, and if the IHC results are 3+, the HER2 status is judged to be positive. HER2 status should be judged negative if IHC results are 0, 1+ or 2 +.
Species 5, HER2/CEP17 ratio <2.0, average HER2 copy number/cell < 4.0: this was judged to be FISH negative.
In this embodiment, the tumor cell segmentation model is obtained by training according to a deep learning image segmentation model, and the training method includes the following steps:
obtaining tumor cell segmentation training data, wherein the tumor cell segmentation training data comprise fluorescence in-situ hybridization images marked with tumor cell region information;
and inputting the tumor cell segmentation training data into the deep learning image segmentation model for training to obtain the tumor cell segmentation model.
The HER2 signal detection model is obtained by training according to a deep learning target detection model, and the training method comprises the following steps:
acquiring HER2 signal detection training data, wherein the HER2 signal detection training data comprise fluorescence in situ hybridization images marked with HER2 signal position information; and inputting the HER2 signal detection training data into the deep learning target detection model for training to obtain a HER2 signal detection model.
The CEP17 signal detection model is obtained by training according to a deep learning target detection model, and the training method comprises the following steps:
obtaining CEP17 signal detection training data, wherein the CEP17 signal detection training data comprise fluorescence in situ hybridization images marked with CEP17 signal position information; and inputting the CEP17 signal detection training data into the deep learning target detection model for training to obtain a CEP17 signal detection model.
By using the fluorescence in situ hybridization sample pathology detection system, the image acquisition of the FISH section and the HER2 detection of the breast cancer tumor cell can be quickly completed without switching back and forth between the observation field of an eyepiece and the acquisition of a multichannel fluorescence image by a computer by a doctor.
Example two
The fluorescence in situ hybridization sample pathology detection system comprises an image acquisition device, an image processing device and a trigger control device connected with the image acquisition device and the image processing device.
The image acquisition device is configured to perform microscopic shooting on the fluorescence in-situ hybridization sample to obtain a pathological image. In this embodiment, the pathology image includes a red channel image, a blue channel image, or a green channel image, and the red/blue/green channel image is obtained by capturing a fluorescence in situ hybridization sample under filtering by a monochromatic filter.
The image processing device is configured to perform image processing on the pathological image.
The trigger control device respectively connected with the image acquisition device and the image processing device is configured to sense trigger actions through different control keys so as to output control instructions to the image acquisition device and the image processing device. The control instruction comprises an image acquisition instruction or an image processing instruction. In this embodiment, the efficiency of acquiring FISH images is improved by the trigger control device.
In this embodiment, when the trigger control device outputs an image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction. When the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the image processing instruction so as to obtain a pathological detection result.
Two control keys 2 are arranged on the trigger control device, and the control keys 2 are used for sensing the trigger action of a user to trigger the output of the image acquisition instruction or the image processing instruction.
In this embodiment, the image capture command is a three-color channel image capture command. The three-color channel image acquisition instruction is configured to instruct the image acquisition device to sequentially acquire three-color channel images, namely, to sequentially acquire a blue channel image, a green channel image and a red channel image.
Please refer to fig. 2B, which is a schematic diagram illustrating another embodiment of a control button on a trigger control device. As shown in fig. 2B, the control key 2 includes a three-color-channel image capture key 23 and an image processing key 22.
In this embodiment, by triggering the three-color channel image acquisition button 23, the three-color channel image acquisition instruction is output to the image acquisition device, and the image acquisition device sequentially acquires a blue channel image, a green channel image, and a red channel image.
The image processing instruction is output to the image processing device by triggering the image processing key 22, the image processing device synthesizes the blue channel image, the green channel image and the red channel image into a fluorescence in-situ hybridization image, and the fluorescence in-situ hybridization image is segmented by utilizing a tumor cell segmentation model to obtain a tumor cell region; performing target detection on the tumor cell region by using a HER2 signal detection model to obtain the HER2 signal quantity; performing target detection on the tumor cell region by using a CEP17 signal detection model to obtain the CEP17 signal quantity; and acquiring a pathological detection result according to the CEP17 signal quantity and the HER2 signal quantity.
EXAMPLE III
The fluorescence in situ hybridization sample pathology detection system comprises an image acquisition device, an image processing device and a trigger control device connected with the image acquisition device and the image processing device.
The image acquisition device is configured to perform microscopic shooting on the fluorescence in-situ hybridization sample to obtain a pathological image. In this embodiment, the pathology image includes a red channel image, a blue channel image, or a green channel image, and the red/blue/green channel image is obtained by capturing a fluorescence in situ hybridization sample under filtering by a monochromatic filter.
The image processing device is configured to perform image synthesis and analysis on the pathological image.
The trigger control device respectively connected with the image acquisition device and the image processing device is configured to sense trigger actions through different control keys so as to output control instructions to the image acquisition device and the image processing device. The control instruction comprises an image acquisition instruction or an image processing instruction. In this embodiment, the efficiency of acquiring FISH images is improved by the trigger control device.
In this embodiment, when the trigger control device outputs an image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction. When the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the image processing instruction so as to obtain a pathological detection result.
The trigger control device is provided with three control keys, and the control keys are used for sensing the trigger action of a user to trigger the output of the image acquisition instruction or the image processing instruction.
In this embodiment, the image capturing command is a region scanning command. The area scanning instruction comprises a scanning area first end point determining instruction, a scanning area second end point determining instruction and a scanning instruction, wherein the scanning area first end point determining instruction and the scanning area second end point determining instruction are respectively configured to instruct the image acquisition device to determine a first end point and a second end point of a scanning area, and the first end point and the second end point are used as two vertexes of a rectangular opposite angle to determine a rectangular area for scanning a sample. The scanning instruction is configured to instruct the image acquisition device to perform area scanning according to the rectangular area determined by the first end point and the second end point.
Please refer to fig. 2C, which is a schematic diagram illustrating another embodiment of the control key on the control key. As shown in fig. 2C, the control key 2 includes an area end point key 24, a scan key 25, and an image processing key 22.
Specifically, the area endpoint key 24 is triggered twice, and a first endpoint determination instruction and a second endpoint determination instruction of the scanning area are sequentially output to the image acquisition device, so that the image acquisition device is instructed to determine a first endpoint and a second endpoint of the scanning area, and the first endpoint and the second endpoint are used as two vertexes of a diagonal of a rectangle to determine the rectangular area to be scanned. And outputting the scanning instruction to the image acquisition device by triggering the scanning key 25, and carrying out area scanning by the image acquisition device according to the scanning areas determined by the first end point and the second end point.
Referring to fig. 3A and 3B, the distribution is shown as a sample example diagram and a sample example diagram after the scan area is determined. As shown in fig. 3A and 3B, the slide used to carry the pathological specimen is typically of a 76mm by 26mm format, with the remainder of the staining being the specimen, the stained area of the specimen typically being tissue only 15-20mm in size. The doctor looks under the eyepiece of the microscope to find a staining area, determines a rectangular area, namely a box area shown in fig. 3B, by determining two end points (as two vertexes on the diagonal line of the rectangle), and only scans to obtain a pathological microscopic image of the rectangular area.
Specifically, by activating the image processing button 22, the image processing instruction is output to the image processing apparatus so that the image processing apparatus processes the pathological microscopic image. The processing procedure of the pathological micrographs by the image processing device is similar to that of the first embodiment and the second embodiment, and is not repeated here. In conclusion, the fluorescence in situ hybridization sample pathology detection system can rapidly complete image acquisition of a FISH section and HER2 detection of breast cancer tumor cells without switching back and forth between an eyepiece observation field and a computer acquired multichannel fluorescence image by a doctor. The invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (12)
1. A fluorescence in situ hybridization sample pathology detection system, comprising:
the image acquisition device is configured to perform microscopic shooting on the fluorescence in-situ hybridization sample to obtain a pathological image;
an image processing device configured to perform image processing on the pathological image;
the trigger control device is respectively connected with the image acquisition device and the image processing device and is configured to output a control instruction to the image acquisition device and the image processing device; the control instruction comprises an image acquisition instruction or an image processing instruction;
when the trigger control device outputs an image acquisition instruction to the image acquisition device, the image acquisition device acquires a corresponding pathological image according to the image acquisition instruction; when the trigger control device outputs an image processing instruction to the image processing device, the image processing device processes the pathological image according to the processing instruction so as to obtain a pathological detection result.
2. The fluorescence in situ hybridization sample pathology detection system of claim 1, characterized in that: the trigger control device is provided with at least two control keys, and the control keys are used for sensing the trigger action of a user to trigger the output of the image acquisition instruction or the image processing instruction.
3. The fluorescence in situ hybridization sample pathology detection system of claim 2, characterized in that: the pathology image comprises a red channel image, a blue channel image or a green channel image; each channel image was obtained by taking a fluorescent in situ hybridization sample under filtering through a monochromatic filter.
4. The fluorescence in situ hybridization sample pathology detection system of claim 3, characterized in that:
the image acquisition instruction comprises at least one of a monochromatic channel image acquisition instruction, a three-color channel image acquisition instruction and an area scanning instruction; the monochrome channel image acquisition instruction comprises a blue channel image acquisition instruction, a green channel image acquisition instruction and a red channel image acquisition instruction which are respectively configured to instruct the image acquisition device to acquire a blue channel image, a green channel image and a red channel image; the three-color channel image acquisition instruction is configured to instruct the image acquisition device to sequentially acquire three-color channel images; the area scanning instruction comprises a scanning area first end point determining instruction, a scanning area second end point determining instruction and a scanning instruction, wherein the scanning area first end point determining instruction and the scanning area second end point determining instruction are respectively configured to instruct the image acquisition device to determine a first end point and a second end point of a scanning area, and the first end point and the second end point are used for determining a rectangular area for scanning a sample; and the scanning instruction is configured to instruct the image acquisition device to perform area scanning according to the rectangular area determined by the first end point and the second end point.
5. The fluorescence in situ hybridization sample pathology detection system of claim 3, characterized in that: the control keys comprise a monochromatic channel image acquisition key and an image processing key;
sequentially outputting the blue channel image acquisition instruction, the green channel image acquisition instruction and the red channel image acquisition instruction by continuously triggering the monochromatic channel image acquisition key;
and outputting the image processing instruction by triggering the image processing key.
6. The fluorescence in situ hybridization sample pathology detection system of claim 4, characterized in that: the control keys comprise a three-color channel image acquisition key and an image processing key;
outputting a three-color channel image acquisition instruction by triggering a three-color channel image acquisition key;
and outputting the image processing instruction by triggering the image processing key.
7. The fluorescence in situ hybridization sample pathology detection system of claim 3, characterized in that: the control keys comprise an area endpoint key, a scanning key and an image processing key;
sequentially outputting a first end point determining instruction of the scanning area and a second end point determining instruction of the scanning area by triggering the area end point key;
outputting the scanning instruction by triggering the scanning key;
and outputting the image processing instruction by triggering an image processing key.
8. The fluorescence in situ hybridization sample pathology detection system of claim 3, characterized in that: and when the image processing device receives the image processing instruction, synthesizing the blue channel image, the green channel image and the red channel image into a fluorescence in-situ hybridization image.
9. The fluorescence in situ hybridization sample pathology detection system of claim 8, wherein when said image processing device receives said image processing instructions, said image processing device further:
segmenting the fluorescence in-situ hybridization image by utilizing a tumor cell segmentation model to obtain a tumor cell region;
performing target detection on the tumor cell region by using a HER2 signal detection model to obtain the HER2 signal quantity;
performing target detection on the tumor cell region by using a CEP17 signal detection model to obtain the CEP17 signal quantity;
and acquiring a pathological detection result according to the CEP17 signal quantity and the HER2 signal quantity.
10. The fluorescence in situ hybridization sample pathology detection system of claim 9, said tumor cell segmentation model being trained from a deep learning image segmentation model, the training method comprising the steps of:
obtaining tumor cell segmentation training data, wherein the tumor cell segmentation training data comprise fluorescence in-situ hybridization images marked with tumor cell region information;
and inputting the tumor cell segmentation training data into the deep learning image segmentation model for training to obtain the tumor cell segmentation model.
11. The fluorescence in situ hybridization sample pathology detection system of claim 9, said HER2 signal detection model being trained from a deep learning objective detection model, the training method comprising the steps of:
acquiring HER2 signal detection training data, wherein the HER2 signal detection training data comprise fluorescence in situ hybridization images marked with HER2 signal position information;
and inputting the HER2 signal detection training data into the deep learning target detection model for training to obtain a HER2 signal detection model.
12. The fluorescence in situ hybridization sample pathology detection system of claim 9, said CEP17 signal detection model being trained from a deep learning objective detection model, the training method comprising the steps of:
obtaining CEP17 signal detection training data, wherein the CEP17 signal detection training data comprise fluorescence in situ hybridization images marked with CEP17 signal position information;
and inputting the CEP17 signal detection training data into the deep learning target detection model for training to obtain a CEP17 signal detection model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010422279.8A CN111598880A (en) | 2020-05-19 | 2020-05-19 | Fluorescence in situ hybridization sample pathological detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010422279.8A CN111598880A (en) | 2020-05-19 | 2020-05-19 | Fluorescence in situ hybridization sample pathological detection system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111598880A true CN111598880A (en) | 2020-08-28 |
Family
ID=72192351
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010422279.8A Pending CN111598880A (en) | 2020-05-19 | 2020-05-19 | Fluorescence in situ hybridization sample pathological detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111598880A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115063796A (en) * | 2022-08-18 | 2022-09-16 | 珠海横琴圣澳云智科技有限公司 | Cell classification method and device based on signal point content constraint |
CN116188463A (en) * | 2023-04-24 | 2023-05-30 | 中国科学院长春光学精密机械与物理研究所 | Automatic detection and analysis method, device, equipment and medium for FISH image signal |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101184171A (en) * | 2007-11-28 | 2008-05-21 | 华中科技大学 | Digitization system of video film |
CN105993163A (en) * | 2015-07-02 | 2016-10-05 | 深圳市大疆创新科技有限公司 | Image processing system, image data processing method, apparatus and related equipment |
CN107172327A (en) * | 2017-03-27 | 2017-09-15 | 联想(北京)有限公司 | A kind of image-pickup method and electronic equipment |
CN109222865A (en) * | 2018-10-17 | 2019-01-18 | 卓外(上海)医疗电子科技有限公司 | A kind of multi-modality imaging endoscopic system |
CN109636801A (en) * | 2019-01-29 | 2019-04-16 | 上海杏脉信息科技有限公司 | Automatic method, equipment and the medium for obtaining HER2 fluorescence in situ hybridization result |
-
2020
- 2020-05-19 CN CN202010422279.8A patent/CN111598880A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101184171A (en) * | 2007-11-28 | 2008-05-21 | 华中科技大学 | Digitization system of video film |
CN105993163A (en) * | 2015-07-02 | 2016-10-05 | 深圳市大疆创新科技有限公司 | Image processing system, image data processing method, apparatus and related equipment |
CN107172327A (en) * | 2017-03-27 | 2017-09-15 | 联想(北京)有限公司 | A kind of image-pickup method and electronic equipment |
CN109222865A (en) * | 2018-10-17 | 2019-01-18 | 卓外(上海)医疗电子科技有限公司 | A kind of multi-modality imaging endoscopic system |
CN109636801A (en) * | 2019-01-29 | 2019-04-16 | 上海杏脉信息科技有限公司 | Automatic method, equipment and the medium for obtaining HER2 fluorescence in situ hybridization result |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115063796A (en) * | 2022-08-18 | 2022-09-16 | 珠海横琴圣澳云智科技有限公司 | Cell classification method and device based on signal point content constraint |
CN116188463A (en) * | 2023-04-24 | 2023-05-30 | 中国科学院长春光学精密机械与物理研究所 | Automatic detection and analysis method, device, equipment and medium for FISH image signal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9567651B2 (en) | System and method for the detection of abnormalities in a biological sample | |
US7760927B2 (en) | Method and system for digital image based tissue independent simultaneous nucleus cytoplasm and membrane quantitation | |
US7587078B2 (en) | Automated image analysis | |
DK2973397T3 (en) | Tissue-object-based machine learning system for automated assessment of digital whole-slide glass | |
ES2292973T3 (en) | METHOD FOR VIDEO-MICROSCOPY AND ASSOCIATED SYSTEM, AND PRODUCT OF COMPUTER LOGICAL SUPPORT PROGRAM. | |
JP2022534157A (en) | Computer-assisted review of tumors on histological images and postoperative tumor margin assessment | |
WO2010087112A1 (en) | Image analysis apparatus, image analysis method, image analysis program and recording medium | |
US20050136549A1 (en) | Method and system for automatically determining diagnostic saliency of digital images | |
US20060127880A1 (en) | Computerized image capture of structures of interest within a tissue sample | |
US9436992B2 (en) | Method of reconstituting cellular spectra useful for detecting cellular disorders | |
CN106462767B (en) | Inspection device for processing and analyzing images | |
EP1534114A2 (en) | Computerized image capture of structures of interest within a tissue sample | |
EP1680757A1 (en) | Automated microspcope slide tissue sample mapping and image acquisition | |
CN111986150A (en) | Interactive marking refinement method for digital pathological image | |
WO2007024264A2 (en) | Method and system for digital image based tissue independent simultaneous nucleus, cytoplasm and membrane quantitation | |
WO2012041333A1 (en) | Automated imaging, detection and grading of objects in cytological samples | |
JP2010540931A (en) | Method and system using multiple wavelengths for processing biological specimens | |
CN111598880A (en) | Fluorescence in situ hybridization sample pathological detection system | |
JP2007516428A (en) | A system for determining the staining quality of slides using a scatter plot distribution | |
US20240169534A1 (en) | Medical image analysis device, medical image analysis method, and medical image analysis system | |
CN115861212B (en) | System and apparatus for distinguishing related disorders based on gastric mucosa biopsy samples | |
Sheikhzadeh | Improving cervical neoplasia diagnosis via novel in vivo imaging technologies and deep learning algorithms | |
WO2022259648A1 (en) | Information processing program, information processing device, information processing method, and microscope system | |
Pietka et al. | Searching for Malignancy in Automated Urological Cytology | |
DEMO | Pathologist Advice on Prostate Cancer Microscopy Analysis Techniques 25 May, 2022| Blog posts, IKOSA AI |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |