Systems and methods for processing electronic medical images to determine enhanced electronic medical images

Abstract

A system and method for processing electronic images from a medical device includes: receiving a first image frame and a second image frame from the medical device; and determining a region of interest (ROI) by subtracting the first image frame from the second image frame, the ROI corresponding to a visual obstacle in the first and / or second image frames. Image processing can be applied to the first and / or second image frames based on a comparison between a first region in the first image frame corresponding to the ROI and a second region in the second image frame corresponding to the ROI, and the first and / or second image frames can be provided for display to a user.

Description

[0001] Cross-reference to related applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 890,399, filed August 22, 2019, the entire contents of which are incorporated herein by reference. Technical Field

[0003] Various aspects of this disclosure generally relate to systems and methods that can be used to plan and / or perform medical procedures. Background Technology

[0004] Substantial progress has been made toward improving the effectiveness of medical care while reducing trauma and risks to patients. Many surgeries that once required open surgery can now be performed using minimally invasive techniques, thus providing patients with shorter recovery times and lower risks of infection. Certain surgeries requiring biopsies, electrical stimulation, tissue ablation, or removal of congenital or foreign objects can be performed via minimally invasive procedures.

[0005] In the field of urology, kidney stones, or kidney stones, accumulate in the urinary tract and become lodged in the kidneys. Kidney stones are deposits of substances from urine, typically minerals and acid salts. While smaller stones can pass through the body naturally, larger stones require surgical intervention for removal. Although open surgery was once the standard treatment for stone removal, other minimally invasive techniques, such as ureteroscopy and percutaneous nephrolithotomy / nephrolithotomy (PCNL), have become safer and more effective alternatives. Furthermore, advances in imaging technology have improved the ability of medical professionals to identify and locate stones before and during surgery. However, medical professionals must still analyze images to determine the location of stones and whether any are present. In addition, images are often obstructed, blurry, and / or difficult to evaluate, making the task of identifying the presence of any stones challenging for medical professionals.

[0006] The systems, apparatus, and methods disclosed herein can correct some of the aforementioned disadvantages and / or solve other problems in the prior art. Summary of the Invention

[0007] Furthermore, the various examples disclosed herein relate to medical systems and methods. Each example disclosed herein may include one or more features described in conjunction with any of the other disclosed examples.

[0008] In one example, this disclosure includes a method for processing electronic images from a medical device. The method includes receiving a first image frame and a second image frame from the medical device, and determining a region of interest (ROI) by subtracting the first image frame from the second image frame. The ROI corresponds to a visual obstacle in the first and / or second image frames. Based on a comparison between a first region in the first image frame corresponding to the ROI and a second region in the second image frame corresponding to the ROI, image processing can be applied to the first and / or second image frames, and the first and / or second image frames can be provided for display to a user.

[0009] In another example, this disclosure includes a system for processing electronic images from a medical device, the system including a data storage device (which stores instructions for processing the electronic images) and a processor (configured to execute the instructions to implement a method for processing the electronic images). The method may include receiving a first image frame and a second image frame from the medical device; and determining a region of interest (ROI) by subtracting the first image frame from the second image frame, the ROI corresponding to a visual obstacle in the first and / or second image frames. Based on a comparison between a first region in the first image frame corresponding to the ROI and a second region in the second image frame corresponding to the ROI, image processing may be applied to the first and / or second image frames, and the first and / or second image frames may be provided for display to a user.

[0010] In another instance, this disclosure includes a non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform a method of processing electronic images from a medical device. The method may include receiving a first image frame and a second image frame from the medical device, and determining a region of interest (ROI) by subtracting the first image frame from the second image frame, the ROI corresponding to a visual obstacle in the first and / or second image frames. Based on a comparison between a first region in the first image frame corresponding to the ROI and a second region in the second image frame corresponding to the ROI, image processing may be applied to the first and / or second image frames, and the first and / or second image frames may be provided for display to a user. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate various exemplary embodiments and, together with the description, serve to explain the principles of this disclosure.

[0012] Figure 1 A medical system according to various aspects of this disclosure is shown.

[0013] Figure 2This is a flowchart of an exemplary method for processing medical images according to various aspects of this disclosure.

[0014] Figure 3 This is a flowchart of an exemplary method for determining a region of interest in a medical image according to various aspects of this disclosure.

[0015] Figure 4 This is a flowchart of an exemplary method for determining a template for object tracking in a medical image, according to various aspects of this disclosure.

[0016] Figure 5 This is a flowchart of an exemplary method for determining medical image enhancement according to various aspects of this disclosure.

[0017] Figure 6 This disclosure shows the aspects that can be followed according to this disclosure. Figures 1-5 An exemplary system used in accordance with the technology described herein. Detailed Implementation

[0018] Examples of this disclosure include systems and methods that facilitate and improve the efficiency and safety of minimally invasive procedures. For example, aspects of this disclosure can provide users (e.g., physicians, medical technicians, or other healthcare providers) with the ability to more easily identify and thus remove kidney stones or other substances from a patient's kidneys or other organs. In some embodiments, this disclosure can be used, for example, to plan and / or perform flexible ureteroscopy with or without laser lithotripsy. The techniques discussed herein are also applicable to other medical techniques, such as any medical technique that utilizes endoscopy.

[0019] Reference will now be made in detail to the examples of this disclosure described above and illustrated in the accompanying drawings. Wherever possible, the same reference numerals will be used throughout the drawings to refer to the same or similar parts.

[0020] The terms “proximal” and “distal” are used herein to refer to the relative positions of the components of the exemplary medical device or insertion device. When used herein, “proximal” means a position relatively closer to the exterior of the body or closer to the operator using the medical device or insertion device. Conversely, “distal” means a position relatively further away from the operator using the medical device or insertion device or closer to the interior of the body.

[0021] The foregoing overview and the following detailed description are both exemplary and illustrative only, and not intended to limit the features claimed. The word “comprising” or other variations used herein are intended to cover non-exclusive inclusion, and thus a process, method, article, or apparatus that comprises a list of elements includes not only those elements but may also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Furthermore, the word “exemplary” used herein is used in the sense of “example” rather than “ideal.” The words “about,” “approximately,” and “about” used herein refer to a range of values ​​within + / - 5% of the stated values.

[0022] Figure 1 A medical system 100 is illustrated, comprising a medical device (such as an endoscope) or other medical imaging device / medical device 105, a network 110, a user device 115 (which may include a display 120 viewable by a user / physician / doctor / patient 125), and a server 130 (which may include a frame processor 135 and / or a template matcher 140). The endoscope 105, user device 115, and / or server 130 may be wired (as shown), wirelessly connected, or communicatively coupled. Alternatively, the functions of server 130 may be performed on the endoscope 105, user device 115, etc. Server 130, endoscope 105, and / or user device 115 may also include a single electronic component.

[0023] like Figure 1 As shown, endoscope 105 can be an insertion device, such as a ureteroscope (e.g., Boston Scientific's LithoVue). TM Digital flexible ureteroscope.

[0024] By positioning the endoscope 105 inside the patient (e.g., through the patient's urethra to the patient's kidney), a retrieval device (not shown) can be inserted to remove and eliminate material (e.g., kidney stones) with or without laser lithotripsy. The endoscope 105, when inserted into the patient, can record and / or transmit image and / or video data, and may have a light source or other imaging source that can display images inside the patient's blood vessels, organs, etc. The endoscope 105 may be further equipped with a laser for performing laser lithotripsy, which can be used to remove, break up, or destroy one or more organ obstructions (such as kidney stones).

[0025] Display 120 may be a single display or at least dual displays, having multiple screens or multiple displays on one screen. In one example, one of these displays may display one or more images currently or previously acquired by endoscope 105. Other displays may display images or videos acquired from one or more other imaging devices 145, such as by X-ray, magnetic resonance imaging, computed tomography, rotational angiography, ultrasound, or another suitable internal imaging device. Alternatively, one display of display 120 may display an image modified using one or more image enhancement techniques described herein, while another display may display an unenhanced image. Alternatively, one display of display 120 may display an image modified using one or more enhancement techniques described herein, while another display 120 may display an image modified using one or more different enhancement techniques described herein.

[0026] Software or application software can manipulate, process, and interpret images received from imaging device 145 to confirm the presence, location, and characteristics of kidney stones or other substances. As will be further described herein, frame processor 135 and / or template matching application software 140 can process and enhance images received from endoscope 105.

[0027] When performing a medical procedure (such as lithotripsy) to remove kidney stones, a physician may insert an endoscope 105 into the patient. For example, when illuminated by a light source on the endoscope 105, the monitor 120 may become partially or completely obscured by fragments of kidney stones or other floating particles. Additionally, flashes of light from a laser or other light source emanating from the endoscope 105 can cause the surgeon or technician to lose track of the kidney stones or other objects involved in the medical procedure. Difficulty tracking kidney stones or surgical objects can increase the time required to perform the procedure, increase the error rate, and increase the cognitive load associated with maintaining visual tracking of objects.

[0028] Figure 2 This is a flowchart of an exemplary method for processing medical images according to various aspects of this disclosure. A source of video or image frames 205 (which may be any medical device, such as endoscope 105 or imaging device 145) may provide frames to signal input 210. These frames may be provided to a frame processor 215 capable of storing multiple frames. One or more frames 220 may be provided to a frame processor 135, which may generate one or more processed frames 230. The processed frames 230 may be provided to a signal output 235, which may be displayed on a display 120.

[0029] Signal input 210 may be a software processor capable of transmitting newly received frames. Frame processor 215 may send frames directly to display 120 via signal output 235, or it may send one or more frames to frame processor 135. As described elsewhere herein, frame processor 135 may implement interference reduction and / or template matching techniques. Frame processor 215 may also send the original frame to display 120 and a copy of the frame to frame processor 135. Processed frame 230 may be received and transmitted to display 120. This allows the original frame to be displayed on display 120 along with processed frame 230. Alternatively, frame processor 215 may send source frame 220 to frame processor 135, and frame processor 215 may return processed frame 230, which includes a dual display of the original frame and the enhanced frame. Therefore, processed frame 230 may be larger than the source frame. Frame processor 135 may further add buttons or other user interface elements to processed frame 230.

[0030] Although the techniques described herein are described as occurring in frame processor 135 (which may be depicted as residing on a single device), any functionality of the frame processor may be distributed to any number of devices, such as any device depicted in system 100. Furthermore, one or more of signal input 210, frame processor 215, and / or signal output 235 may be housed in one or more servers 130, or any other device depicted on system 100.

[0031] Figure 3 This is a flowchart of an exemplary method for interference deduction according to various aspects of this disclosure. Multiple frames can be received from a frame source 305. This frame source may include an endoscope 105 or other medical imaging device 145. One or more frames can be accumulated in a color frame buffer 310 and / or a grayscale frame buffer 315. Multiple frames can be accumulated for comparison. By comparing the multiple frames with each other, a background can be identified and distinguished from a visual obstacle. This visual obstacle can be a reflection, glare, light source, clumps of dust, debris, particles, kidney or gallstones, or clumps of other stones, etc. The visual obstacle may also have a relevant brightness or intensity exceeding a threshold. Using the techniques described herein, the visual obstacle can be considered as a region of interest and can be processed to remove or alleviate the degree or severity of the obstruction.

[0032] When a new frame is received from frame source 305, a copy can be stored in color frame buffer 310 and / or grayscale frame buffer 315. The frame in color frame buffer 310 may have multiple channels for various colors, such as three channels for red, green, and blue. A copy of the frame is stored in grayscale frame buffer 315. Grayscale frame buffer 315 and / or color frame buffer 310 can be used to determine one or more regions of interest in a frame that may include one or more visual obstacles.

[0033] The received color frame can be converted to grayscale for storage in grayscale frame buffer 315. The conversion may include merging two or more color channels to form a grayscale frame. This can be done at least partially because different color channels in a color frame may be inconsistent in the presence of visual obstacles (e.g., light intensity exceeding a threshold, blocks of fragments exceeding a size threshold, etc.). The merged channel frame may not have this inconsistency because only one channel exists, but information from multiple channels can still be present in the merged channel frame.

[0034] Alternatively, regions of interest can be identified even with uncertain grayscale frames. According to the techniques described herein, any color channel reporting a visual impairment can be used to determine the region of interest, even if there are inconsistencies with other color channels regarding the presence of any region of interest.

[0035] Region of Interest (ROI) mask generator 320 can receive frames from grayscale frame buffer 315 and / or color frame buffer 310. The ROI mask generator 320 can determine regions with intensity variations that can be removed from the display frames (ROIs). Multiple received frames (which can be consecutive frames) can be compared, and common features can be subtracted. For example, if the current frame 322 is being processed to determine the ROI, the current frame can be compared with the preceding frame 321 and the following / following frame 323. Common features of the frames or features determined to be similar within a predetermined threshold can be subtracted from each other. Two processed frames can be generated: the first is the subtraction of the previous frame 321 with the current frame 322, and the second is the subtraction of the subsequent frame 323 with the current frame 322. These two processed frames can then be added together. Any remaining objects can be designated as the ROI 324.

[0036] The common feature can be the background, and therefore, after subtraction, only objects that move faster than the background (such as chunks of debris and other visual obstacles) remain. One or more of these visual obstacles can be designated as regions of interest and region-of-interest masks can be applied.

[0037] Visual obstacles can also be objects with light intensity exceeding a threshold. For example, reflections of light or laser exceeding a brightness / intensity threshold may not originate from a specific or other object moving near the endoscope, but may originate from light emitted from the kidney stone itself, the wall of a blood vessel / tissue / organ, or some other object that may not be subtracted from nearby frames. Therefore, the region of interest can also, or alternatively, be designated as any region with light intensity / brightness exceeding a predetermined threshold. This type of visual obstacle can be identified before and / or after frame reception processing by comparing nearby frames. For example, the current frame 322 can be frame reception processing. The current frame 322 can be compared with a earlier frame 321 that does not have a strong light visual obstacle. These two frames can be subtracted to determine a first subtracted frame. Then, the current frame 323 can be compared with a later frame 323 that does not have a strong light visual obstacle. These two frames can be subtracted to determine a second subtracted frame. The two subtracted frames are then added to determine the mask region of interest. This process can be repeated for more frames for which subtraction is performed. Alternatively, the region of interest can be determined by simply comparing the frame to be processed with another frame.

[0038] One or more frames with identified regions of interest 324 can be provided to the region of interest comparator 325. Once the region of interest is determined, it can be analyzed relative to one or more color channels of the corresponding color version of that frame. At the first color channel (e.g., red), two or more frames can be analyzed. For example, the frame 322 being processed can be compared with the previous frame 321 and the subsequent frame 323. Image features of the determined regions of interest 324 can be compared across multiple respective frames. For example, the image features of the region of interest 324 in the current frame 322 can be compared with the corresponding region of interest 332 in the previous frame 321. The region of interest 332 may cover the same area in the frame as the region of interest 324. The image features of the region of interest 324 in the current frame 322 can be further compared with the region of interest 342 in the subsequent frame 323. For example, the image features being compared can be brightness, intensity, the amount of intensity variation relative to other frames, deviation from average brightness across a predetermined number of frames, motion patterns, texture, intensity histogram, entropy, etc.

[0039] In one implementation, the intensities of color channels across multiple frames can be compared, and a minimum, median, or average intensity can be determined. For example, in the red channel, pixels in region of interest 332 may have an average intensity of 5, while region of interest 324 may have an intensity of 95, and region of interest 342 may have an intensity of 25. The multiple frames may have very dark or very bright visual obstacles. Therefore, the median intensity across the multiple frames can be selected. Pixels in the region of interest with the median value can be used to replace pixels in the region of interest of the current frame 322. This determination can be made for other color channels (e.g., green and blue). Regions of interest in some color channels will be replaced by regions of interest in another frame, although regions of interest in other color channels will remain uncorrected. If necessary, these color channels can be processed in this way until all channels have processed regions of interest. Figure 3 In the example, the region of interest 342 of the subsequent frame 323 can replace the region of interest 324 of the current frame 322 (e.g. Figure 3 (As shown in the diagram) is designated as region of interest 345. In this way, bright flashes or dark obstacles in the current frame can be replaced to reduce or eliminate visual obstructions.

[0040] A possible side effect of substituting the region of interest (as described above) is that hard or artificial edges (halos) may appear around the substituted area. This can distort the observer's perception of the true shape of the object receiving the image correction and may give the observer the impression of edges that do not actually exist in the patient's body.

[0041] To mitigate or eliminate this problem, after determining the region of interest (ROI), an edge 352 of the ROI can be determined at 350. This edge 352 may have a predetermined thickness or may be based on the size of the ROI. For example, when the ROI becomes larger, the edge 352 may be automatically determined to be thicker. Morphological operations (e.g., dilation and erosion operations) can be used to determine these edges. The ROI edge can be placed above the current frame 355 with the replaced ROI 357. The edge of the replaced ROI 357 can be removed. The ROI edge can be drawn or may have an applied color gradient from the inner edge to the outer edge, such that the “halo” of the processed current frame is removed / smoothed, and any rough edges that may cause visual interference are removed. The color gradient may not only be a first-order gradient but also a second-order derivative gradient to help smooth the color transition from the inner to the outer edge 352. After applying these techniques, a processed frame 360 ​​with corrected edges 362 can be provided to the user for display.

[0042] Figure 4This is a flowchart of an exemplary method for determining a template for target tracking in medical images according to various aspects of this disclosure. As mentioned above, endoscopic operators may find it difficult to track target objects or tissues (such as kidney stones). In addition to visual obstructions, the movement of the endoscope and other influences can increase the tracking difficulty for the endoscopic operator and thus increase cognitive load. While processing the frame to reduce or remove visual obstructions can make the process easier, it can also help to automatically highlight or otherwise display the target tissue or object on the display. For example, a box or outline can be placed around the target object (such as a kidney stone). Figure 4 Techniques for template matching 142 are revealed, which can be implemented alone or as a supplement to the interference reduction techniques discussed elsewhere in this paper.

[0043] At frame 0 (405), the frame can be provided to a trained template system 410. This trained template system 410 can be trained with images of the target object (e.g., images of kidney stones). The trained template system can return a portion of frame 0 corresponding to the target object, for example, a portion of frame 0 containing the image of kidney stones (represented as template 415). Template 415 can be used to quickly and automatically identify the same target object in subsequent frame 1 (420). For a given template and target frame, various image features (intensity, gradient, etc.) can be determined for both, which can be used to determine if a match exists. The target object in frame 1 can be slightly different, as it may have a rotated, changing shape (fragmented), moved closer to or further from the camera, etc. That is, if template 415 matches any region of frame 1 within a predetermined tolerance / confidence threshold, it can be assumed that the matching region is the target object in a subsequent frame. Thus, using templates obtained from previous frames, objects can be tracked across multiple frames. As described above, bounding boxes, circles, indicators, or any other indicators can be placed around the target object to make it easier for users to track the object. Additionally, indicators that match confidence levels can also be identified and / or displayed.

[0044] A portion of frame 1 can be used to generate template 425. This template 425 can be used to locate the target object in subsequent frame 2 (430). A portion of frame 2 containing the target object can be used to generate template 435. Using a template is faster and less computationally intensive than providing each frame to a trained template system 410 for tracking the target object. Therefore, templates may be preferred unless the target object cannot be tracked within a predetermined confidence level. Template 435 can be used to identify the target object in frame 3 (440).

[0045] These templates can be quickly compared with different parts of the frame to determine if a match exists within a predetermined threshold or confidence level. However, a match may not exist within the predetermined threshold or confidence level. For example, kidney stones can break apart, and the shape in one frame may be significantly different from the shape in the next frame. If, for example, using a template from a previous frame, the target object cannot be identified within the tolerance range, the frame (such as frame 3) can be provided again to the trained template system 410. The trained template system 410 can return a template 445, which can be used to identify the target object (450) in frame 4, etc.

[0046] Additionally, a buffer can be used to store templates from previous frames. If an object obscures the endoscope 105 or other medical imaging device, tracking of the target object may fail rapidly if only the template from the previous frame is used to track the target object. If the target object is not identified within a predetermined confidence level, other previous templates can be analyzed to search for a match.

[0047] Figure 5 This is a flowchart of an exemplary method for determining medical image enhancement according to various aspects of this disclosure. In step 505, a first image frame and a second image frame may be received from a medical imaging device. In step 510, a region of interest (ROI) corresponding to a visual obstacle in the first and / or second image frames may be determined by subtracting the first image frame from the second image frame. In step 515, image processing may be applied to the first and / or second image frames based on a comparison between a first region in the first image frame corresponding to the ROI and a second region in the second image frame corresponding to the ROI. In step 520, the first and / or second image frames may be provided for display to a user.

[0048] Figure 6 This disclosure shows the aspects that can be followed according to this disclosure. Figures 1-5 An exemplary system used in accordance with the technology described herein. Figure 6This is a simplified functional block diagram of a computer that can be configured as a server 130, endoscope 105, imaging device 145, and / or user device 115 according to the various exemplary embodiments disclosed herein. Specifically, in one embodiment, any user device, server, etc. discussed herein may be a component of hardware 600, including, for example, a data communication interface 620 for packet data communication. The platform may also include a central processing unit (“CPU”) 602, which takes the form of one or more processors for executing program instructions. The platform may include an internal communication bus 608 and storage units 606 (such as read-only memory (ROM), hard disk drive (HDD), solid-state drive (SDD), etc.) that can store data in a computer-readable medium 622, although system 600 may receive programs and data via network communication. System 600 may also have a memory 604 (such as RAM) that stores instructions 624 for performing the techniques given herein, although instructions 624 may be temporarily or permanently stored in other modules of system 600 (e.g., processor 602 and / or computer-readable medium 622). The system 600 may also include input and output ports 612 and / or a display 610 for connection to input and output devices such as a keyboard, mouse, touchscreen, monitor, display, etc. Various system functions can be executed in a distributed manner on several similar platforms to distribute the processing load. Alternatively, these systems can be executed by an appropriate program on a single computer hardware platform.

[0049] The disclosed technology can help enable efficient and effective surgery to break down and / or remove material from a patient's organs. In particular, the user can easily view the processed frames to aid, for example, in removing kidney stones inside a patient's kidney. The images are clearer with fewer visual obstructions, and the target kidney stone can be more easily tracked due to indicators that follow its location. Therefore, in the case of kidney stones, the user can more efficiently remove kidney stones from a specific location inside the patient's kidney.

[0050] Furthermore, while the examples described in this disclosure generally relate to ureteroscopic removal of kidney stones with or without lithotripsy, it is also conceivable that the systems and procedures described herein are equally applicable to the removal of other substances. For example, the systems and methods described above can be used during percutaneous nephrolithotomy / nephrolithotomy (PCNJL) for planning and intermediate procedures to locate any missed kidney stones. The systems and methods described above can also be used to plan or perform procedures to remove ureteral stones, gallstones, bile duct stones, etc.

[0051] While the principles of this disclosure have been described herein with reference to illustrative examples used for a particular purpose, it should be understood that this disclosure is not limited to these examples. Those skilled in the art and who have access to the teachings provided herein will recognize that other modifications, uses, embodiments, and equivalents fall within the scope of the features described herein. Therefore, the claimed features are not to be considered limited by the foregoing description.

Claims

1. A system for processing electronic images from a medical device, comprising: A data storage device for storing instructions for processing electronic images; as well as A processor configured to execute the instructions to implement a method for processing an electronic image, the method comprising: Receive the first and second image frames from the medical device; A region of interest is determined by subtracting the first image frame from the second image frame. The region of interest corresponds to a visual obstacle in the first image frame and / or the second image frame, wherein the visual obstacle includes reflections, glare, debris, and / or stones. Image processing is applied to the first image frame and / or the second image frame based on a comparison between a first region of the first image frame corresponding to the region of interest and a second region of the second image frame corresponding to the region of interest. Determine the boundary of a predetermined thickness around the region of interest; Apply a color gradient to the boundary of the predetermined thickness around the region of interest; and Provide the first image frame and / or the second image frame to display to the user.

2. The system of claim 1, wherein subtracting the first image frame from the second image frame comprises: If the similar regions of both the first image frame and the second image frame exceed a predetermined threshold, then that region is removed from consideration of the region of interest.

3. The system of claim 1, wherein the method performed by the system further comprises: Generate a grayscale first image frame based on the first image frame; Generate a grayscale second image frame based on the second image frame; as well as The region of interest is determined based on the first grayscale image frame and the second grayscale image frame.

4. The system of claim 1, wherein determining the region of interest further includes: Receive a third image frame from the medical device; and The region of interest is determined in the following manner: Subtract the first image frame from the second image frame to form the first subtracted image frame; The second image frame is subtracted from the third image frame to form the second subtracted image frame; as well as Add the first subtracted frame image frame to the second subtracted frame image frame.

5. The system of claim 1, wherein the method performed by the system further comprises: Receive a third image frame from the medical device; Determine the first pixel value associated with the first region of the first image frame corresponding to the region of interest; Determine the second pixel value associated with the second region of the second image frame corresponding to the region of interest; Determine the third pixel value associated with the third region of the third image frame; as well as Based on a comparison of the first pixel value, the second pixel value, and the third pixel value, image processing is applied to the second region of the second image frame corresponding to the region of interest.

6. The system of claim 5, wherein applying image processing to the second region of the second image frame further includes determining an intermediate pixel by comparing the first pixel value, the second pixel value, and the third pixel value; When it is determined that the first pixel value is the intermediate pixel, the second region of the second image frame corresponding to the region of interest is replaced with the first region of the first image frame corresponding to the region of interest; and When the third pixel value is determined to be the intermediate pixel, the second region of the second image frame corresponding to the region of interest is replaced with the third region of the third image frame corresponding to the region of interest.

7. The system of claim 6, wherein the step of determining the intermediate pixel and replacing the second region of the second image frame is performed in one time in one color channel.

8. The system of claim 1, wherein the method performed by the system further comprises: A first template is determined that is associated with an object of interest in the first image frame, the first template comprising a portion of the first image frame depicting the object of interest; as well as The position of the object of interest in the second image frame is determined based on the first template.

9. The system of claim 8, wherein determining the position of the object of interest in the second image frame further comprises: The first template and multiple regions of the second image frame are compared. as well as When a region of the second image frame that matches the first template is located within a predetermined tolerance range, that region of the second image frame is associated with the object of interest.

10. The system of claim 8, wherein the method performed by the system further comprises: An indication of the region of interest in the second image frame is provided to be displayed to the user.

11. The system of claim 10, wherein the indication includes a contour line around the object of interest to be displayed to the user.

12. The system of any one of claims 1-11, wherein the medical device comprises an endoscope.

13. The system of any one of claims 1-11, wherein the region of interest corresponds to at least one kidney stone.

Images