WO2022150011A1

WO2022150011A1 - System and method for image processing

Info

Publication number: WO2022150011A1
Application number: PCT/SG2021/050019
Authority: WO
Inventors: Derrence CHONG
Original assignee: Endosiq Technology Pte. Ltd.
Priority date: 2021-01-11
Filing date: 2021-01-11
Publication date: 2022-07-14

Abstract

Disclosed is a method for processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the comparison step includes a step of obtaining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

Description

SYSTEM AND METHOD FOR IMAGE PROCESSING

TECHNICAL FIELD

[0001] The present disclosure relates to a system and method for processing images.

BACKGROUND

[0002] The following discussion of the background is intended to facilitate an understanding of the present disclosure only. It should be appreciated that the discussion is not an acknowledgement or admission that any of the material referred to was published, known or is part of the common general knowledge of the person skilled in the art in any jurisdiction as of the priority date of the invention.

[0003] Template matching in the context of image processing refers to the comparison of a captured/obtained image with a reference or template image and identifying one or more similarities or differences (as the case may be) between the captured or obtained image and the reference image in order to perform further processing steps. Template matching has been utilized particularly in medical imaging and diagnostics, wherein the reference image is representative of a desired view of at least one anatomical region of a subject.

[0004] Notwithstanding the above, there exists an ongoing need to improve the accuracy of template matching techniques in the field of medical imaging, especially for specific anatomical region(s) of a human being.

[0005] Accordingly, it is an object of the disclosure to provide an improved system and method to address the aforementioned need at least in part.

SUMMARY

[0006] The disclosure is motivated by the use of a feature detection algorithm, such as a ridge detection method to facilitate identification of a particular feature associated with an image (e.g. blood vessels of a human bladder image) so that the particular feature is properly identified. The disclosure seeks to provide a method of improved matching between a template image (reference image) and a current image, and to provide a relatively high degree of matching compared to prior art. It is contemplated that an improved matching will lead to a more accurate identification of anatomical features and/or conditions.

[0007] According to an aspect of the disclosure there is a method for processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the comparison step includes a step of obtaining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

[0008] In some embodiments, the comparison step further comprises the steps of: comparing the obtained degree of similarity with a first predetermined threshold, and determining whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold. If an intermediate match is determined, the step of determining the degree of similarity may further include the steps of: obtaining a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image, and applying a ridge detection filter to determine a final match.

[0009] The step of applying the ridge detection filter may include the steps of: comparing the degree of similarity between the sub-image of the associated greyscale of the image frame and the sub-image of the intermediate matched associated greyscale image, and determining whether there is a final match between the sub-image of the associated greyscale of the image frame and the corresponding sub-image of the intermediate matched associated greyscale image, based on a second predetermined threshold.

[0010] In some embodiments, the first predetermined threshold may be 0.75. In some embodiments, the second predetermined threshold may be 1.

[0011] In some embodiments, each of the plurality of image frames may have a resolution of at least 1280-pixel by 720-pixel resolution.

[0012] In some embodiments, the multimedia file comprises a video file associated with an anatomical region of the subject. The multimedia file may be a medical image of an anatomical region. The anatomical region may be a bladder of a human subject.

[0013] In some embodiments, the video file may be associated with blood vessels on/within the bladder. The blood vessels may comprise veins on the bladder.

[0014] According to another aspect of the disclosure there is a system for processing images comprising a storage medium for storing at least one multimedia file, the multimedia file comprising a plurality of image frames; a processor configured to: execute the at least one multimedia file and determine if at least one template image associated with a subject is present; wherein if at least one template image is present, (i.) convert each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) compare the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the processor is configured to obtain a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

[0015] In some embodiments, the processor is further configured to compare the obtained degree of similarity with a first predetermined threshold, and determine whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold. [0016] If an intermediate match is determined, the processor may be configured to obtain a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image, and apply a ridge detection filter to determine the final match.

[0017] In some embodiments where the ridge detection filter is applied, the processor is configured to compare the degree of similarity between the sub-image of the associated greyscale of the image frame and the sub-image of the intermediate matched associated greyscale image, and determine whether there is a final match between the sub-image of the associated greyscale of the image frame and the corresponding sub-image of the intermediate matched associated greyscale image, based on a second predetermined threshold.

[0018] In some embodiments, the first predetermined threshold is 0.75. In some embodiments, the second predetermined threshold is 1. In some embodiments, the first predetermined threshold may be above 0.5, and preferably in a range of 0.6 to 0.8.

[0019] In some embodiments, the plurality of image frames may have a resolution of 1280-pixel by 720-pixel resolution.

[0020] In some embodiments, the multimedia file is a video file associated with an anatomical region of the subject. The multimedia file may be a medical image of an anatomical region. The anatomical region may be a bladder of a human subject. In some embodiments, the video file may be associated with blood vessels on/within the bladder. The blood vessels may be veins on the bladder.

[0021] In some embodiments, the system is arranged in data or signal communication with a cystoscopy system. The cystoscopy system may comprise at least one cystoscope equipped with an imaging sensor to obtain real time images of a bladder of the subject.

[0022] According to another aspect of the disclosure there is a non-transitory computer readable medium having stored thereon software instructions that, when executed by a processor or a dedicated circuit, cause the processor to or dedicated circuit to perform a method of processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one match; wherein the comparison step includes a step of determining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

[0023] Other aspects and features of the present invention will become apparent to those of ordinary skill in the art upon review of the following description of specific embodiments of the invention in conjunction with the accompanying figures.

BRIEF DESCRIPTION OF DRAWINGS

[0024] In the figures, which illustrate, by way of example only, embodiments of the present invention,

[0025] Figure 1a and 1b show general flow charts depicting a method for image processing;

[0026] Figure 2 shows a flow chart depicting a method for image processing specific for the application of bladder localization; and

[0027] Figure 3 shows results demonstrating the efficacy of the method depicted in the identification of veins on a bladder.

DESCRIPTION OF EMBODIMENTS

[0028] As used herein, the term ‘subject’ can be any animals, including mammalian animals and human beings. [0029] As used herein, the term “associate”, “associated”, “associate”, and “associating” indicate a defined relationship (or cross-reference) between at least two items. For instance, a coloured image may undergo image processing to obtain a derived image, such as a greyscale image and/or a sub-image. Such a derived image or sub-image is an associated image of the coloured image.

[0030] As used herein, the term ‘sub-image’ broadly includes a resized image and/or a cropped image.

[0031] As used herein, the term ‘network’ can be any means of providing communication between one or more devices and/or content stored elsewhere. As used herein, network can be a personal area network, local area network, a storage area network, a system area network, a wide area network, a virtual private network, and an enterprise private network. The network can include one or more gateways or no gateways. The network communication can be conducted via published standard protocols or proprietary protocols.

[0032] As used herein, communication of data through any network can be: (i) encoded or unencoded; (ii) encrypted or unencrypted; (iii) delivered via a wired network, a wireless network, or a combination of wired and wireless. Wireless communication can be accomplished in any practical manner including a Wi-Fi 802.11 network, a Bluetooth™ network, or mobile phone network (such as 3G, 4G, LTE, and 5G). The terms “connected”, “connected”, and “connecting” as used herein refer to a communication link between at least two devices and can be accomplished as discussed in this paragraph.

[0033] As used herein, the term “computing device” may be a single stand alone computer such as a desktop computer or a laptop computer, a thin client, a tablet computer, or a mobile phone. The computing device may run a local operating system and store computer files on a local storage drive. The computing device may access files and application through a gateway to one or more content repositories, the content repository can host files and/or run virtual applications and generate a virtual desktop for the computing device.

[0034] As used herein, the term “server” may include a single stand-alone computer, a single dedicated server, multiple dedicated servers, and/or a virtual server running on a larger network of servers and/or cloud-based service.

[0035] As used herein, the term “database” may include one or more data repositories to store data and access data from a single stand-alone computer, a data server, multiple dedicated data servers, a cloud-based service, and/or a virtual server running on a larger network of servers.

[0036] As used herein, the term “module” may include hardware, software, or combinations thereof to achieve a desired function. For example, a data module may include the necessary hardware and software to communicate with one or more sensors to send and receive data from the sensors.

[0037] As used herein, the term “real time” is used in the context of a computer processing term in relation to at least one of a hardware system and software system that are subject to a deadline or constraint and must guarantee response within specified time.

[0038] According to an aspect of the disclosure there is a method of processing images, in particular medical images. The method is suited especially for the identification of specific locations on/in a human bladder, and may include template matching. Broadly, the method obtains at least one, preferably a plurality of template images captured from a bladder scan procedure and uses such template images as reference images for comparison with subsequent scanned images to identify the location(s) within the bladder.

[0039] Referring to Figure 1a, the method 100 may include the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present (step S102); wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images (step S104); and (ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match (step S106). The comparison step (step S106) may include a step of obtaining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image (step S108).

[0040] The determination of whether at least one template image is present may be based on a step of checking a database. If no template image is present, the method 100 may be diverted to a non-template matching procedure/process.

[0041] Referring to Figure 1b, the comparison step (step S106) may further comprise the steps of: comparing the obtained degree of similarity with a first predetermined threshold (step S122), and determining whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold (step S124).

[0042] If an intermediate match is determined, the step of determining the degree of similarity further includes the steps of: obtaining a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image (step S126), and applying a ridge detection filter to determine a final match (step S128).

[0043] Referring to Figure 2, which is a specific embodiment of the method 100 in relation to a bladder localization method 200 of a human subject, the multimedia file may be a video file obtained real-time or offline. The video file may be at least one of various file formats such as mp4, 3gp, ogg, wmv, webm, flv, avi, etc. The video file may contain multimedia content including images and sound of the bladder of the human subject.

[0044] The bladder localization method 200 may be run on a general purpose computer or may be run on dedicated machines, integrated circuit (IC) chips for image processing of medical images. In some embodiments the bladder localization method 200 may be installed as a software application on a mobile computer device. The mobile computer device may include smart phones, tablet PC or the like. In some embodiments, the bladder localization method 200 may be installed on an application specific integrated circuit (ASIC).

[0045] The bladder localization method 200 may be compiled as an executable file which provides an interface for a user to select a multimedia file such as a video file. Once the video file is selected, the method 200 performs a step of loading a selected video for execution (step S202a). As an alternative embodiment, a user may select the method 200 to be executed while he/she activates a video recording device. The video file may therefore be obtained real time (step S202b). It is contemplated that the video file may be a video of a bladder (or a part thereof) of the human subject.

[0046] As the video is executed or obtained (either in real-time or otherwise), the method 200 detects if at least one template image is available (step S204). The at least one template image may be stored on a depository (e.g. a database) on the general purpose computer, dedicated machines, or mobile computer device, as the case may be. The at least one template images may be of a predetermined format, such as a jpeg format or a bitmap format. The at least one template images is suitable for image processing.

[0047] If no template image is detected, the method 200 is terminated (step S206).

[0048] If at least one template image is available, the method 200 loads the template image for analysis (step S208). Each template image may be previously obtained from the human subject and stored in a database. Each template image may also be obtained based on known conditions (normal or otherwise) of the human subject.

[0049] A check on whether a plurality of templates associated with the same human subject is performed (step S210). If a plurality of templates are present, each of the plurality of templates is converted to greyscale. If only one template is present, the single template is converted to greyscale (step S212).

[0050] The conversion of the one or more template images to greyscale may be achieved by various methods as known to a skilled person.

[0051] The method 200 next performs a scan of the video file (on a frame by frame basis) to locate or determine one or more matches between each frame and the one or more template images (step S214). For the purpose of determination, each image frame of the video file associated with the human subject is also converted to grey scale.

[0052] Each converted grey scale image frame of the video is compared with each of the converted grey scale template image to identify any match(es). The comparison may include obtaining a degree of similarity between the greyscale image of the image frame and the greyscale image of the at least one template image. If the degree of similarity is more than or equal to a first predetermined threshold, a match may be concluded. In some embodiments, the first predetermined threshold is 0.75 or 75% (Step S216). The degree of similarity between each image frame and the template image may be determined based on known methods of measurement/calculation of Euclidean distance, Mahalanobis distance, Chord distance, Pearson’s correlation coefficient, etc. If no match is found between a particular image frame with all the template images, the method 200 moves to the next image frame for matching (step S218). In general, the first predetermined threshold may be above 0.5, and preferably in a range of 0.6 to 0.8.

[0053] If a matched is detected between the particular image frame with at least one of the template images based on the first predetermined threshold, the particular image frame is regarded as an intermediate matched frame. The intermediate matched frame is resized so that the matched features are in focus or centered. The resizing may be by way of an image crop (step S220). In some embodiments, the intermediate matched feature(s) may be a specific pattern of blood vessel(s) formed on a surface of the bladder. Non-limiting examples of patterns include criss-crossed, overlaps etc.

[0054] A final match based on an application of a feature detection algorithm is performed on the resized intermediate matched frame (step S222). For identification of blood vessel patterns on the human subject’s bladder, a feature detection algorithm, such as a ridge detection algorithm or filter, may be suitable. The ridge algorithm is suited to identify ‘ridges or peaks’ on a portion of the bladder. Other feature detection algorithms suitable for identifying ‘valleys’ or ‘peaks’ on an image may also be contemplated.

[0055] To obtain a final match, the feature detection algorithm (i.e. the ridge detection algorithm) may be applied on the intermediate matched image of the converted greyscale image frame and greyscale template image to isolate the blood vessels. Once the blood vessels have been isolated, the ridge detection algorithm will search each image frame of the video to locate the isolated blood vessel(s) (step S224). This corresponds to a step of locating matching points in the intermediate matched image frame of the video.

[0056] The final match may include the use of a second predetermined threshold value for determining a level of similarity between the template image and the intermediate matched image frame (step S226). In some embodiments, the second predetermined threshold value is 1.0, indicating a complete or identical match (step S226). If the complete or perfect match is identified, the match is indicated as perfect (step S228) and a final match is located (step S230). If the threshold value is less than the predetermined threshold, then the algorithm continues to search for data points to determine a match (step S232).

[0057] Figures 3a to 3d show the efficacy of the method 200 in identifying a particular vein pattern on a human bladder. Figure 3a shows a matched result being highlighted in a box which is matched to the template image (Figure 3b).

[0058] Figure 3c shows the results of 3a being cropped out with a ridge detection filter applied and compared with the template image (Figure 3d) to ensure a higher level of detect accuracy.

[0059] It is contemplated that the ridge detection filter is configured to receive image data from the intermediate matched image (which may be resized). Data of the intermediate matched image may be expressed in the form of a mathematical matrix, preferably a square matrix, and more preferably a Hessian matrix. The ridge filter may then be executed to identify one or more ‘ridges’ in the image. This may correspond to blood vessels, such as veins, in a medical image of a bladder.

[0060] In some embodiments, in addition to the image data, the ridge filter may be further configured to receive a predetermined ridge scale s. The ridge scale may be the scale of Gaussian derivatives in the Hessian matrix. By default, a value of s :::1 is used.

[0061] According to another aspect of the disclosure there is a system for processing images comprising a storage medium for storing at least one multimedia file, the multimedia file comprising a plurality of image frames; a processor configured to: execute the at least one multimedia file and determine if at least one template image associated with a subject is present; wherein if at least one template image is present, (i.) convert each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) compare the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the processor is configured to obtain a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

[0062] In some embodiments, the processor is further configured to compare the obtained degree of similarity with a first predetermined threshold, and determine whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold.

[0063] In some embodiments, if an intermediate match is determined, the processor is configured to obtain a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image, and apply a feature detection algorithm, such as a ridge detection filter, to determine the final match. In the application of the ridge detection filter, the processor is configured to compare the degree of similarity between the sub-image of the associated greyscale of the image frame and the sub-image of the intermediate matched associated greyscale image, and determine whether there is a final match between the sub-image of the associated greyscale of the image frame and the corresponding sub-image of the intermediate matched associated greyscale image, based on a second predetermined threshold.

[0064] In some embodiments, the plurality of image frames has a resolution of 1280-pixel by 720-pixel resolution.

[0065] The multimedia file may be a video file associated with an anatomical region of a subject. The multimedia file may be a medical image of an anatomical region. In some embodiments, the anatomical region may be a bladder of a human subject. In some embodiments, the video file may be associated with blood vessels on/within the bladder. In some embodiments, the blood vessels may be veins on the bladder.

[0066] The system for processing images may be arranged in data communication with a cystoscopy system having at least one cystoscope equipped with an imaging sensor (such as a lens) to obtain real time images of a bladder of a subject. In some embodiments, the system may include other sensors such as temperature sensors, pressure sensors, etc.

[0067] In some embodiments, the system may be integrated with or form part of the cystoscopy system. Specifically a processor may be arranged in data or signal communication of the image capturing device of the cystoscopy system to capture images/videos of a human bladder for analysis.

[0068] According to another aspect of the disclosure there is a non-transitory computer readable medium having stored thereon software instructions that, when executed by a processor or a dedicated circuit, cause the processor to or dedicated circuit to perform a method of processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and (ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one match; wherein the comparison step includes a step of determining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

[0069] The non-transitory computer readable medium may be a data storage medium having read-only memory (ROM), random access memory (RAM). In some embodiments, the non-transitory computer readable medium may form part of a mobile computer device.

[0070] It should be further appreciated by the person skilled in the art that variations and combinations of features described above, not being alternatives or substitutes, may be combined to form yet further embodiments falling within the intended scope of the invention.

Claims

1. A method for processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present,

(i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and

(ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the comparison step includes a step of obtaining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

2. The method of claim 1 , wherein the comparison step further comprises the steps of: comparing the obtained degree of similarity with a first predetermined threshold, and determining whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold.

3. The method of claim 2, wherein if an intermediate match is determined, the step of determining the degree of similarity further includes the steps of: obtaining a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image, and applying a ridge detection filter to determine a final match.

4. The method of claim 3, wherein the step of applying the ridge detection filter includes the steps of: comparing the degree of similarity between the sub-image of the associated greyscale of the image frame and the sub-image of the intermediate matched associated greyscale image, and determining whether there is a final match between the sub-image of the associated greyscale of the image frame and the corresponding sub-image of the intermediate matched associated greyscale image, based on a second predetermined threshold.

5. The method of any one of claims 2 to 4, wherein the first predetermined threshold is 0.75.

6. The method of any one of claims 2 to 5, wherein the second predetermined threshold is 1.

7. The method of any one of the preceding claims, wherein each of the plurality of image frames has a resolution of at least 1280-pixel by 720-pixel resolution.

8. The method of any one of the preceding claims, wherein the multimedia file comprises a video file associated with an anatomical region of the subject.

9. The method of claim 8, wherein the multimedia file is a medical image of an anatomical region.

10. The method of claim 9, wherein the anatomical region is a bladder of a human subject.

11. The method of claim 10, wherein the video file is associated with blood vessels on/within the bladder.

12. The method of claim 11 , wherein the blood vessels comprise veins on the bladder.

13. A system for processing images comprising a storage medium for storing at least one multimedia file, the at least one multimedia file comprising a plurality of image frames; a processor configured to: execute the at least one multimedia file and determine if at least one template image associated with a subject is present; wherein if at least one template image is present,

(i.) convert each of the plurality of image frames and the at least one template image to associated grey scale images; and

(ii.) compare the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one final match; wherein the processor is configured to obtain a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

14. The system of claim 13, wherein the processor is further configured to compare the obtained degree of similarity with a first predetermined threshold, and determine whether there is an intermediate match between the associated greyscale of the image frame and the associated greyscale image of the at least one template image based on the first predetermined threshold.

15. The system of claim 14, wherein if an intermediate match is determined, the processor is configured to obtain a sub-image of the associated greyscale of the image frame and a corresponding sub-image of the intermediate matched associated greyscale image, and apply a ridge detection filter to determine the final match.

16. The system of claim 15, wherein in the application of the ridge detection filter, the processor is configured to compare the degree of similarity between the sub-image of the associated greyscale of the image frame and the sub-image of the intermediate matched associated greyscale image, and determine whether there is a final match between the sub-image of the associated greyscale of the image frame and the corresponding sub-image of the intermediate matched associated greyscale image, based on a second predetermined threshold.

17. The system of any one of claims 14 to 16, wherein the first predetermined threshold is 0.75.

18. The system of any one of claims 14 to 17, wherein the second predetermined threshold is 1.

19. The system of any one of claims 13 to 18, wherein the plurality of image frames has a resolution of 1280-pixel by 720-pixel resolution.

20. The system of any one of claims 13 to 19, wherein the multimedia file is a video file associated with an anatomical region of the subject.

21 . The system of claim 20, wherein the multimedia file is a medical image of an anatomical region.

22. The system of claim 21 , wherein the anatomical region is a bladder of a human subject.

23. The system of claim 22, wherein the video file is associated with blood vessels on/within the bladder.

24. The system of claim 23, wherein the blood vessels are veins on the bladder.

25. The system of any one of claims 13 to 24, wherein the system is arranged in data or signal communication with a cystoscopy system.

26. The system of claim 25, wherein the cystoscopy system comprises at least one cystoscope equipped with an imaging sensor to obtain real time images of a bladder of the subject.

27. A non-transitory computer readable medium having stored thereon software instructions that, when executed by a processor or a dedicated circuit, cause the processor to or dedicated circuit to perform a method of processing images comprising the steps of: obtaining or executing a multimedia file comprising a plurality of image frames associated with a subject and determining if at least one template image associated with the subject is present; wherein if at least one template image is present, (i.) converting each of the plurality of image frames and the at least one template image to associated grey scale images; and

(ii.) comparing the associated greyscale image of each image frame with each associated greyscale image of the at least one template image to identify at least one match; wherein the comparison step includes a step of determining a degree of similarity between the associated greyscale image of the image frame and the associated greyscale image of the at least one template image.

28. A device for processing images comprising an input module configured to receive or store at least one multimedia file, the at least one multimedia file comprising a plurality of image frames; a processor configured to: execute the at least one multimedia file and determine if at least one template image associated with a subject is present; wherein if at least one template image is present,

29. The device of claim 28, wherein the input module comprises a user interface and is configured to stream the at least one multimedia tile for execution by the processor.

30. The device of claim 28 or 29, wherein the processor is an application specific integrated circuit (ASIC).

31 . The device of any one of claims 28 to 30, wherein the device is integrated with a cystoscopy system.