CN117224231A - Vascular exposure analysis device for hepatectomy dissection - Google Patents
Vascular exposure analysis device for hepatectomy dissection Download PDFInfo
- Publication number
- CN117224231A CN117224231A CN202311526647.3A CN202311526647A CN117224231A CN 117224231 A CN117224231 A CN 117224231A CN 202311526647 A CN202311526647 A CN 202311526647A CN 117224231 A CN117224231 A CN 117224231A
- Authority
- CN
- China
- Prior art keywords
- module
- layer
- branch
- input
- blood vessel
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 39
- 238000002224 dissection Methods 0.000 title claims abstract description 16
- 230000002792 vascular Effects 0.000 title claims abstract description 16
- 238000012752 Hepatectomy Methods 0.000 title claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 230000002440 hepatic effect Effects 0.000 claims abstract description 26
- 210000004185 liver Anatomy 0.000 claims abstract description 15
- 210000003240 portal vein Anatomy 0.000 claims abstract description 9
- 210000004204 blood vessel Anatomy 0.000 claims description 57
- 238000000605 extraction Methods 0.000 claims description 24
- 210000000232 gallbladder Anatomy 0.000 claims description 8
- 210000001367 artery Anatomy 0.000 claims description 6
- 210000001659 round ligament Anatomy 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 239000003708 ampul Substances 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 claims description 2
- 239000000945 filler Substances 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 7
- 210000002767 hepatic artery Anatomy 0.000 abstract description 3
- 201000007270 liver cancer Diseases 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 208000014018 liver neoplasm Diseases 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 210000003484 anatomy Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000002357 laparoscopic surgery Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a vascular exposure analysis device for hepatectomy dissection, which relates to the technical field of medical appliances and comprises an input module, a three-dimensional modeling module, an acquisition module, a semantic segmentation module, a first analysis module, a second analysis module, an instance segmentation module, a vascular branch identification module, a third analysis module, an appliance detection module, a first judgment module and a display module; the three-dimensional reconstruction is carried out on the liver region of the patient before the operation by the device, and the three-dimensional reconstruction comprises important vascular structures such as hepatic artery, hepatic portal vein and the like, so that information is provided for the operation, and a doctor is helped to plan the operation process better.
Description
Technical Field
The invention relates to the technical field of medical appliances, in particular to a vascular exposure analysis device for hepatectomy dissection.
Background
Primary liver cancer is a serious disease seriously affecting life health, surgical treatment is a preferred treatment method for early liver cancer patients, and is an important treatment means for enabling liver cancer patients to survive for a long time or even be cured. However, even if there is a chance of obtaining early liver cancer with radical excision, the recurrence rate after 5 years of operation is still up to 70%, which severely restricts the curative effect of liver cancer operation treatment, resulting in poor long-term prognosis effect for patients.
The appearance of the 3D laparoscope provides a new opportunity for accurate minimally invasive navigation. The surgeon wears 3D glasses to watch the images fused by the left and right cameras of the laparoscope, so that three-dimensional depth information can be perceived. However, such depth information cannot be quantified, and it is still necessary to perform binocular vision stereo matching for depth estimation, and to obtain surface information of a laparoscopic surgery scene by using a triangulation method, which is highly demanded by surgeons. To sum up, the problems of the prior art still exist:
1. no quantitative method is used for estimating the three-dimensional depth information, and different doctors can make different judgments under the influence of subjective consciousness of the doctors;
2. the use of 3D laparoscopes requires a high degree of experience for the physician, who has a long learning curve, and may not be able to accurately judge.
In summary, analyzing relevant information in a laparoscopic image by using computer technology, assisting a surgeon in judging and analyzing is an urgent problem to be solved at present.
Disclosure of Invention
The present invention has been made in order to solve the above-mentioned problems, and an object of the present invention is to provide a vascular exposure analysis device for hepatectomy dissection.
The invention realizes the above purpose through the following technical scheme:
vascular exposure analysis device for use in hepatectomy dissection; comprising the following steps:
an input module; the input module is used for inputting the operation plan of the patient;
a three-dimensional modeling module; the three-dimensional modeling module performs three-dimensional modeling on the blood vessel information of the liver region of the patient to obtain a three-dimensional model of the patient, wherein the blood vessel information of the liver region comprises left branch of hepatic intrinsic artery, right branch of hepatic intrinsic artery, left branch of hepatic portal vein, right branch of hepatic portal vein, blood vessel and focus information;
an acquisition module; the acquisition module is used for acquiring an operation picture in real time;
a semantic segmentation module; the semantic segmentation module acquires a segmentation area of a liver, a gall bladder and a hepatic round ligament in the three-dimensional model by utilizing the semantic segmentation model;
a first analysis module; the first analysis module judges the position of the first hepatic portal according to the correlation relationship of the segmentation areas;
a second analysis module; the second analysis module distinguishes target blood vessels to be exposed according to the operation plan;
an instance segmentation module; the example segmentation module acquires the region range of each target blood vessel in the picture by using an example segmentation model, wherein each region range is used as a branch individual of one target blood vessel;
a blood vessel branch identification module; the blood vessel branch identification module is used for identifying branch categories of branch individuals by utilizing the blood vessel branch identification model;
a third analysis module; the third analysis module is used for distinguishing blood vessels in a core area and blood vessels in a non-core area according to the operation plan, wherein the core area is an area which is required to be dissected currently, and other areas except the core area are the non-core areas;
an instrument detection module; the instrument detection module is used for identifying the surgical instrument by using the instrument detection model;
a first judgment module; the first judging module analyzes and judges the exposure condition of each target blood vessel in the core area according to the instrument detection result and the blood vessel identification result in the core area;
a display module; the display module is used for displaying the operation picture and distinguishing and displaying the exposure condition of the blood vessel and each target blood vessel in the operation plan.
The invention has the beneficial effects that: the three-dimensional reconstruction is carried out on the liver region of the patient before the operation by the device, and the three-dimensional reconstruction comprises important vascular structures such as hepatic artery, hepatic portal vein and the like, thereby providing priori guidance for the operation and helping doctors to plan the operation process better. In the operation process, the technology such as an example segmentation model and a blood vessel branch recognition model is used for recognizing the blood vessel region in real time, classifying and rendering the blood vessel according to a preset operation plan, and providing the blood vessel exposure condition of the anatomical region. Thus, doctors can more accurately perform operation according to the information provided by the device, and misoperation is reduced.
Drawings
FIG. 1 is a schematic view of a vascular exposure analysis device for use in hepatectomy dissection according to the present invention;
FIG. 2 is a schematic diagram of the structure of the semantic segmentation model of the present invention;
FIG. 3 is a schematic diagram of an example segmentation model of the present invention;
FIG. 4 is a schematic diagram of the structure of the vessel branch recognition model of the present invention;
FIG. 5 is a schematic diagram of the structure of the instrument detection model of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be understood that the directions or positional relationships indicated by the terms "upper", "lower", "inner", "outer", "left", "right", etc. are based on the directions or positional relationships shown in the drawings, or the directions or positional relationships conventionally put in place when the inventive product is used, or the directions or positional relationships conventionally understood by those skilled in the art are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific direction, be configured and operated in a specific direction, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, terms such as "disposed," "connected," and the like are to be construed broadly, and for example, "connected" may be either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The following describes specific embodiments of the present invention in detail with reference to the drawings.
As shown in fig. 1, a vascular exposure analysis device for use in hepatectomy dissection; comprising the following steps:
an input module; the input module is used for inputting an operation plan of a patient, and the operation plan is formulated by a doctor according to the illness state of the patient and an operation target;
a three-dimensional modeling module; the three-dimensional modeling module performs three-dimensional modeling on the blood vessel information of the liver region of the patient to obtain a three-dimensional model of the patient, wherein the blood vessel information of the liver region comprises left branch of hepatic intrinsic artery, right branch of hepatic intrinsic artery, left branch of hepatic portal vein, right branch of hepatic portal vein, blood vessel and focus information;
an acquisition module; the acquisition module is used for acquiring an operation picture in real time;
a semantic segmentation module; the semantic segmentation module acquires a segmentation area of a liver, a gall bladder and a hepatic round ligament in the three-dimensional model by utilizing the semantic segmentation model;
the semantic segmentation model is based on a UNet algorithm, the UNet algorithm is based on a convolutional neural network architecture design, and consists of a downsampling part, an upsampling part and a pixel-level classification part, wherein the calculation of UNet is used in the downsampling process, but a filling technology is used in the calculation, so that image edge information is not lost in the calculation; in the up-sampling process, linear interpolation is used for replacing deconvolution calculation, and the calculated amount of the model is reduced under the condition of maintaining the model effect; finally, the liver, gall bladder, hepatic round ligament and others appearing in the image are classified by a pixel-class classification section.
The concrete structure is as follows:
as shown in fig. 2, the semantic segmentation model includes an N-layer downsampling layer, an N-layer upsampling layer and a first classification head, the N-layer downsampling layer is sequentially connected from input to output, the output of the N-layer downsampling layer and the output of the N-N upsampling layer are used as the input of the N-n+1-layer upsampling layer, the output of the N-layer upsampling layer is used as the input of the first classification head, the upsampling layer upsamples by using linear interpolation, the downsampling layer includes a filling layer and a convolution layer, and the filling layer is used for performing boundary filling on an input image of the downsampling layer, wherein N is a positive integer less than or equal to N;
a first analysis module; the first analysis module judges the position of the first hepatic portal according to the correlation relationship of the segmentation areas; the method comprises the following steps: the first analysis module is used for providing the region which is positioned on the liver and is the position of the first hepatic portal to a doctor of a main knife according to the segmentation region and the position information of the patient, wherein the lower right part of the gallbladder is the ampulla end of the gallbladder, and the nearest connecting line of the ampulla and the hepatic round ligament is combined to guide the doctor to dissect the appointed position;
a second analysis module; the second analysis module distinguishes target blood vessels to be exposed according to the operation plan;
an instance segmentation module; the example segmentation module acquires the region range of each target blood vessel in the operation picture by using an example segmentation model, wherein each region range is used as a branch individual of one target blood vessel;
the example segmentation module acquires the region range of each blood vessel to be exposed in the picture by using an example segmentation model; firstly, extracting the minimum circumscribed frame of the corresponding region in the original image according to the mask result, and then discarding other region information which does not belong to the current target pipeline according to the mask result content.
The instance segmentation model is developed based on a meist algorithm, which includes a feature extraction backbone, feature pyramids, target detection heads, mask regression branches for instance segmentation, see fig. 3. Because the targets in the images are larger or smaller, a combination of a feature extraction trunk and a feature pyramid is adopted to extract a multi-scale feature map, and then the multi-scale feature map is respectively sent into a detection and segmentation head network. The mask regression branch predicts the mask vector of the target while detecting the target, and reconstructs the mask vector to generate a target mask, the reconstruction being denoted v=tu;wherein T is the engineering matrix, u is compressed into v, W is the reconstruction matrix, u is reconstructed into the target mask, v is the compressed vector, and u is a planarized vector; />Is the target mask.
The concrete structure is as follows:
as shown in fig. 3, the example segmentation model includes M-layer first feature extraction layers, a feature pyramid, 2M-1 second classification heads and a mask regression branch, the feature pyramid includes 2M-1 layer second feature extraction layers, the M-layer first feature extraction layers are sequentially connected from input to output, the output of the M-layer first feature extraction layer is used as the input of the M-layer second feature extraction layer, the output of the m+1 layer second feature extraction layer is also used as the input of the M-layer second feature extraction layer, the output of the m+1 layer second feature extraction layer is used as the input of the m+m+1 layer second feature extraction layer, M is a positive integer smaller than M, the output of one layer second feature extraction layer is used as the input of one classification head, and the outputs of the 2M-1 second classification heads are all used as the input of the mask regression branch.
A blood vessel branch identification module; the blood vessel branch identification module is used for identifying branch categories of branch individuals by utilizing the blood vessel branch identification model;
the vascular branch recognition model adopts an algorithm architecture based on a transducer, and in order to accord with the rule based on the transducer algorithm structure, the image is divided into patches with fixed sizes; to preserve the location information of the image block, adding a location insert to the patch to preserve the location information, using standard learnable one-dimensional location inserts; the resulting vector sequence is then fed into a standard transform encoder that uses an alternating combination of multi-headed self-attention, full join, and layer normalization, and uses residual join to ensure that the information flow is smooth. Finally, the identification is performed by using a standard method, namely, an additional learnable classification token is added to the sequence, and finally, classification is performed on the classification token, see fig. 4.
The concrete structure is as follows:
as shown in fig. 4, the vessel branch identification model sequentially includes, from input to output, a segmentation layer for segmenting the region range of the vessel to be exposed into patches of a fixed size, a linear mapping layer for adding position embeddings into the patches and feeding the resulting vector sequence to the transducer encoder, a transducer encoder, and a third classification head for adding an additional learnable classification token to the sequence and classifying the classification token to obtain individual and branch categories of the vessel branch.
A third analysis module; the third analysis module is used for distinguishing blood vessels in a core area and blood vessels in a non-core area according to the operation plan, wherein the core area is an area which is required to be dissected currently, and other areas except the core area are the non-core areas; the method comprises the following steps: the third analysis module is combined with a preoperative operation plan to determine the current blood vessel branches which should be exposed, and the current region which should be dissected is determined to be a green core region which should be dissected by cross comparison with the blood vessel branches mentioned by the operation plan through the individuals and branch categories of the blood vessel branches in the operation picture, and other blood vessels are rendered to be red to represent a non-core region, namely a pipeline region which temporarily avoids dissection;
an instrument detection module; the instrument detection module is used for identifying a surgical instrument by using an instrument detection model, wherein the surgical instrument is used for lacing blood vessels in a core area;
the specific structure of the instrument detection model is as follows:
as shown in fig. 5, the apparatus detection model selects the DETR algorithm, the apparatus detection model sequentially includes, from input to output, a convolutional neural network, a transducer-based codec, and a detection head, the convolutional neural network downsamples 32 the original image data by adding channel dimension information, the codec encoder is generated by stacking a plurality of encoding layers, each encoding layer includes a multi-headed self-attention module and a feed-forward network, the codec encoder is used to reduce the channel dimension of the advanced feature map and generate a new feature map to calculate image features, the codec decoder uses a multi-headed self-attention mechanism to calculate image features, and the detection head is used to independently decode frame coordinates and class labels to obtain the detection result of the surgical apparatus. Using self-attention and encoder-decoder attention, the entire image can be used as context.
A first judgment module; the first judging module analyzes and judges the exposure condition of each target blood vessel in the core area according to the instrument detection result and the blood vessel identification result of the core area, wherein the exposure condition is whether each target blood vessel completes lacing or not;
a display module; the display module is used for displaying the operation picture and distinguishing and displaying the exposure condition of the blood vessel and each target blood vessel in the operation plan.
The device is based on 3D laparoscope technology and image analysis, and aims to improve the effect of liver cancer operation treatment, so that the survival rate of patients is improved. Three-dimensional reconstruction is carried out on the liver region of a patient before operation, and the three-dimensional reconstruction comprises important vascular structures such as hepatic artery, hepatic portal vein and the like, so that information is provided for operation, and doctors are helped to plan an operation process better. In the operation process, the system uses the technologies of example segmentation, vessel branch recognition model and the like to recognize the vessel region in real time, classifies and renders the vessel according to a preset operation plan, provides the information of the vessel in the anatomical region, and displays the information in the display module. Thus, doctors can more accurately perform operation according to the information provided by the display module of the device, and misoperation is reduced. The device covers a plurality of models, such as a semantic segmentation model, a blood vessel branch identification model, an instrument detection model and the like, and the models work cooperatively at different stages, so that more comprehensive information is provided, and a doctor is helped to make more accurate decisions.
The technical scheme of the invention is not limited to the specific embodiment, and all technical modifications made according to the technical scheme of the invention fall within the protection scope of the invention.
Claims (7)
1. Vascular exposure analysis device for use in hepatectomy dissection; characterized by comprising the following steps:
an input module; the input module is used for inputting the operation plan of the patient;
a three-dimensional modeling module; the three-dimensional modeling module performs three-dimensional modeling on the blood vessel information of the liver region of the patient to obtain a three-dimensional model of the patient, wherein the blood vessel information of the liver region comprises left branch of hepatic intrinsic artery, right branch of hepatic intrinsic artery, left branch of hepatic portal vein, right branch of hepatic portal vein, blood vessel and focus information;
an acquisition module; the acquisition module is used for acquiring an operation picture in real time;
a semantic segmentation module; the semantic segmentation module acquires a segmentation area of a liver, a gall bladder and a hepatic round ligament in the three-dimensional model by utilizing the semantic segmentation model;
a first analysis module; the first analysis module judges the position of the first hepatic portal according to the correlation relationship of the segmentation areas;
a second analysis module; the second analysis module distinguishes target blood vessels to be exposed according to the operation plan;
an instance segmentation module; the example segmentation module acquires the region range of each target blood vessel in the operation picture by using an example segmentation model, wherein each region range is used as a branch individual of one target blood vessel;
a blood vessel branch identification module; the blood vessel branch identification module is used for identifying branch categories of branch individuals by utilizing the blood vessel branch identification model;
a third analysis module; the third analysis module is used for distinguishing blood vessels in a core area and blood vessels in a non-core area according to the operation plan, wherein the core area is an area which is required to be dissected currently, and other areas except the core area are the non-core areas;
an instrument detection module; the instrument detection module is used for identifying the surgical instrument by using the instrument detection model;
a first judgment module; the first judging module analyzes and judges the exposure condition of each target blood vessel in the core area according to the instrument detection result and the blood vessel identification result in the core area;
a display module; the display module is used for displaying the operation picture and distinguishing and displaying the exposure condition of the blood vessel and each target blood vessel in the operation plan.
2. The vascular exposure analysis device for hepatectomy dissection according to claim 1, wherein the semantic segmentation model includes N-layer downsampling layers, N-layer upsampling layers and a first classification head, the N-layer downsampling layers being sequentially connected from input to output, the output of the N-layer downsampling layers and the output of the N-N upsampling layers being input of the N-n+1-th upsampling layers, the output of the N-th upsampling layers being input of the first classification head, the upsampling layers upsampling using linear interpolation, the downsampling layers including a filler layer for boundary filling the input image of the downsampling layers, wherein N is a positive integer of N or less.
3. The vascular exposure analysis device for hepatectomy dissection according to claim 1, wherein the first analysis module is configured to determine, based on the segmentation area and the patient position information, that the lower right portion of the gallbladder is the ampulla end of the gallbladder, that the nearest line connecting the ampulla and the hepatic round ligament is located on the liver at the position of the first hepatic portal.
4. The vessel exposure analysis device for hepatectomy dissection according to claim 1, wherein the example segmentation model includes M-layer first feature extraction layers, a feature pyramid, 2M-1 second classification heads, and a mask regression branch, the feature pyramid includes 2M-1 layer second feature extraction layers, the M-layer first feature extraction layers are sequentially connected from input to output, the output of the M-layer first feature extraction layer serves as the input of the M-layer second feature extraction layer, the output of the m+1 layer second feature extraction layer also serves as the input of the M-layer second feature extraction layer, the output of the M-layer second feature extraction layer serves as the input of the m+1 layer second feature extraction layer, the output of the m+m-layer second feature extraction layer serves as the input of the m+m+1 layer second feature extraction layer, M is a positive integer smaller than M, the output of the one layer second feature extraction layer serves as the input of one classification head, and the outputs of the 2M-1 second heads all serve as the input of the mask regression branch.
5. The vessel exposure analysis device for hepatectomy dissection according to claim 4, wherein the mask regression branch predicts a mask vector of the target while detecting the target, and reconstructs the mask vector to generate a target mask, the reconstruction being expressed as v=tu;wherein T is the engineering matrix, u is compressed into v, W is the reconstruction matrix, u is reconstructed into the target mask, v is the compressed vector, and u is a planarized vector; />Is the target mask.
6. The vessel exposure analysis apparatus for hepatectomy dissection according to claim 1, wherein the vessel branch identification model includes, in order from input to output, a segmentation layer for segmenting a pixel-level region range of a vessel to be dissected into patches of a fixed size, a linear mapping layer for adding position embedding into the patches and feeding the resulting vector sequence to the transducer encoder, a transducer encoder, and a third classification head for adding an additional learnable classification token to the sequence and classifying the classification token, resulting in individual and branch categories of the vessel branch.
7. The vessel exposure analysis device for hepatectomy dissection according to claim 1, wherein the instrument detection model sequentially comprises, from input to output, a convolutional neural network, a transducer-based codec, and a detection head, the convolutional neural network downsampling 32 the raw image data by adding channel dimension information, the codec encoder being generated by stacking a plurality of encoding layers, each encoding layer comprising a multi-headed self-attention module and a feed-forward network, the codec encoder being configured to reduce the channel dimension of the advanced feature map and generate a new feature map to calculate image features, the codec decoder using the multi-headed self-attention mechanism to calculate image features, the detection head being configured to independently decode frame coordinates and class labels to obtain the detection result of the surgical instrument.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311526647.3A CN117224231B (en) | 2023-11-16 | 2023-11-16 | Vascular exposure analysis device for hepatectomy dissection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311526647.3A CN117224231B (en) | 2023-11-16 | 2023-11-16 | Vascular exposure analysis device for hepatectomy dissection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117224231A true CN117224231A (en) | 2023-12-15 |
CN117224231B CN117224231B (en) | 2024-02-13 |
Family
ID=89086629
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311526647.3A Active CN117224231B (en) | 2023-11-16 | 2023-11-16 | Vascular exposure analysis device for hepatectomy dissection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117224231B (en) |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030043572A (en) * | 2001-11-23 | 2003-06-02 | 주식회사 인피니트테크놀로지 | Medical image segmentation apparatus and method thereof |
CN101425186A (en) * | 2008-11-17 | 2009-05-06 | 华中科技大学 | Liver subsection method based on CT image and system thereof |
US20100246909A1 (en) * | 2009-03-26 | 2010-09-30 | Thomas Blum | Medical imaging device and method to evaluate a test bolus image series |
AU2010323639A1 (en) * | 2009-11-24 | 2012-06-14 | Lexi Co., Ltd. | Preoperative planning program for artificial hip joint replacement surgery and surgery support jig |
CN107049475A (en) * | 2017-04-19 | 2017-08-18 | 纪建松 | Liver cancer local ablation method and system |
CN109215079A (en) * | 2018-07-17 | 2019-01-15 | 艾瑞迈迪医疗科技(北京)有限公司 | Image processing method, operation navigation device, electronic equipment, storage medium |
CN111145206A (en) * | 2019-12-27 | 2020-05-12 | 联想(北京)有限公司 | Liver image segmentation quality evaluation method and device and computer equipment |
CN112489051A (en) * | 2020-11-13 | 2021-03-12 | 深圳市旭东数字医学影像技术有限公司 | Liver cutting method and system based on blood vessels and lesion areas |
CN112932663A (en) * | 2021-03-02 | 2021-06-11 | 成都与睿创新科技有限公司 | Intelligent auxiliary method and system for improving safety of laparoscopic cholecystectomy |
CN113436140A (en) * | 2021-05-14 | 2021-09-24 | 南昌大学第一附属医院 | Quantitative analysis method, system, terminal and medium for identifying blood stasis syndrome subtype |
CN114299072A (en) * | 2022-03-11 | 2022-04-08 | 四川大学华西医院 | Artificial intelligence-based anatomy variation identification prompting method and system |
CN114668497A (en) * | 2022-03-29 | 2022-06-28 | 四川大学华西医院 | Computer-aided liver surgery planning three-dimensional modeling system |
KR20220148513A (en) * | 2021-04-29 | 2022-11-07 | 주식회사 삼육오엠씨네트웍스 | 3D body Scanning Device For Liposuction |
CN115862849A (en) * | 2023-02-17 | 2023-03-28 | 四川大学华西医院 | Noninvasive detection method, system and storage medium for hepatic cirrhosis portal hypertension |
CN116313028A (en) * | 2022-09-06 | 2023-06-23 | 上海联影智能医疗科技有限公司 | Medical assistance device, method, and computer-readable storage medium |
US20230230231A1 (en) * | 2020-06-24 | 2023-07-20 | Shanghai Pulse Medical Technology, Inc. | Training method and apparatus for angiography image processing, and automatic processing method and apparatus |
US20230252632A1 (en) * | 2022-02-10 | 2023-08-10 | Cathworks Ltd. | System and method for machine-learning based sensor analysis and vascular tree segmentation |
WO2023161193A2 (en) * | 2022-02-22 | 2023-08-31 | Karl Storz Se & Co. Kg | Medical imaging device, medical system, method for operating a medical imaging device, and method of medical imaging |
CN116761569A (en) * | 2020-11-12 | 2023-09-15 | 马佐尔机器人有限公司 | Surgical path planning using artificial intelligence for feature detection |
-
2023
- 2023-11-16 CN CN202311526647.3A patent/CN117224231B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20030043572A (en) * | 2001-11-23 | 2003-06-02 | 주식회사 인피니트테크놀로지 | Medical image segmentation apparatus and method thereof |
CN101425186A (en) * | 2008-11-17 | 2009-05-06 | 华中科技大学 | Liver subsection method based on CT image and system thereof |
US20100246909A1 (en) * | 2009-03-26 | 2010-09-30 | Thomas Blum | Medical imaging device and method to evaluate a test bolus image series |
AU2010323639A1 (en) * | 2009-11-24 | 2012-06-14 | Lexi Co., Ltd. | Preoperative planning program for artificial hip joint replacement surgery and surgery support jig |
CN107049475A (en) * | 2017-04-19 | 2017-08-18 | 纪建松 | Liver cancer local ablation method and system |
CN109215079A (en) * | 2018-07-17 | 2019-01-15 | 艾瑞迈迪医疗科技(北京)有限公司 | Image processing method, operation navigation device, electronic equipment, storage medium |
CN111145206A (en) * | 2019-12-27 | 2020-05-12 | 联想(北京)有限公司 | Liver image segmentation quality evaluation method and device and computer equipment |
US20230230231A1 (en) * | 2020-06-24 | 2023-07-20 | Shanghai Pulse Medical Technology, Inc. | Training method and apparatus for angiography image processing, and automatic processing method and apparatus |
CN116761569A (en) * | 2020-11-12 | 2023-09-15 | 马佐尔机器人有限公司 | Surgical path planning using artificial intelligence for feature detection |
CN112489051A (en) * | 2020-11-13 | 2021-03-12 | 深圳市旭东数字医学影像技术有限公司 | Liver cutting method and system based on blood vessels and lesion areas |
CN112932663A (en) * | 2021-03-02 | 2021-06-11 | 成都与睿创新科技有限公司 | Intelligent auxiliary method and system for improving safety of laparoscopic cholecystectomy |
KR20220148513A (en) * | 2021-04-29 | 2022-11-07 | 주식회사 삼육오엠씨네트웍스 | 3D body Scanning Device For Liposuction |
CN113436140A (en) * | 2021-05-14 | 2021-09-24 | 南昌大学第一附属医院 | Quantitative analysis method, system, terminal and medium for identifying blood stasis syndrome subtype |
US20230252632A1 (en) * | 2022-02-10 | 2023-08-10 | Cathworks Ltd. | System and method for machine-learning based sensor analysis and vascular tree segmentation |
WO2023161193A2 (en) * | 2022-02-22 | 2023-08-31 | Karl Storz Se & Co. Kg | Medical imaging device, medical system, method for operating a medical imaging device, and method of medical imaging |
CN114299072A (en) * | 2022-03-11 | 2022-04-08 | 四川大学华西医院 | Artificial intelligence-based anatomy variation identification prompting method and system |
CN114668497A (en) * | 2022-03-29 | 2022-06-28 | 四川大学华西医院 | Computer-aided liver surgery planning three-dimensional modeling system |
CN116313028A (en) * | 2022-09-06 | 2023-06-23 | 上海联影智能医疗科技有限公司 | Medical assistance device, method, and computer-readable storage medium |
CN115862849A (en) * | 2023-02-17 | 2023-03-28 | 四川大学华西医院 | Noninvasive detection method, system and storage medium for hepatic cirrhosis portal hypertension |
Non-Patent Citations (2)
Title |
---|
吴泓,谢坤林等: "《腹镜超声联合荧光显像在腹腔镜肝切除术中的应用》", 《中国普外基础与临床杂志》, vol. 27, no. 06, 25 May 2020 (2020-05-25), pages 662 - 665 * |
吴泓,谢坤林等: "《腹镜超声联合荧光显像在腹腔镜肝切除术中的应用》", 《中国普外基础与临床杂志》, vol. 27, no. 06, pages 662 - 665 * |
Also Published As
Publication number | Publication date |
---|---|
CN117224231B (en) | 2024-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113506334B (en) | Multi-mode medical image fusion method and system based on deep learning | |
WO2022257344A1 (en) | Image registration fusion method and apparatus, model training method, and electronic device | |
US9646423B1 (en) | Systems and methods for providing augmented reality in minimally invasive surgery | |
JP7174710B2 (en) | Systems and Methods for Targeted Object Augmentation to Generate Synthetic Breast Tissue Images | |
EP3814984B1 (en) | Systems and methods for automated detection of visual objects in medical images | |
CN113066026B (en) | Endoscope image smoke purification method based on deep neural network | |
CN110796670B (en) | Dissection method and device for dissecting interbed artery | |
CN110621231A (en) | System and method for hierarchical multi-level feature image synthesis and representation | |
CN111815766B (en) | Processing method and system for reconstructing three-dimensional model of blood vessel based on 2D-DSA image | |
CN114299072B (en) | Artificial intelligence-based anatomy variation identification prompting method and system | |
CN106157282A (en) | Image processing system and method | |
CN109801268B (en) | CT radiography image renal artery segmentation method based on three-dimensional convolution neural network | |
Debarba et al. | Efficient liver surgery planning in 3D based on functional segment classification and volumetric information | |
CN109771052B (en) | Three-dimensional image establishing method and system based on multi-view imaging and multi-polarization state imaging | |
Yamamoto et al. | An automated fracture detection from pelvic CT images with 3-D convolutional neural networks | |
CN116452618A (en) | Three-input spine CT image segmentation method | |
Shi et al. | Attention gate based dual-pathway network for vertebra segmentation of X-ray spine images | |
Xu et al. | RUnT: A network combining residual U-Net and transformer for vertebral edge feature fusion constrained spine CT image segmentation | |
CN117224231B (en) | Vascular exposure analysis device for hepatectomy dissection | |
Kohlmann et al. | Contextual picking of volumetric structures | |
CN113348485A (en) | Abnormality detection method, abnormality detection program, abnormality detection device, server device, and information processing method | |
Wang et al. | MLN-net: A multi-source medical image segmentation method for clustered microcalcifications using multiple layer normalization | |
Dickson et al. | A Dual Channel Multiscale Convolution U-Net Methodfor Liver Tumor Segmentation from Abdomen CT Images | |
CN113379691B (en) | Breast lesion deep learning segmentation method based on prior guidance | |
CN113850816B (en) | Cervical cancer MRI image segmentation device and method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |