Lung resection area determination method and device, electronic equipment, storage medium and computer program product

Abstract

The embodiment of the invention discloses a lung resection area determination method and device, electronic equipment, a storage medium and a computer program product. The method comprises the steps of obtaining a lung segmentation result of a lung image of a target lung, a to-be-resected segmentation result of a to-be-resected target in the lung image, and a vessel segmentation result of a vessel in the lung image; according to the vessel segmentation result, determining a vessel center line of the vessel, and determining a drainage basin range corresponding to each vessel point on the vessel center line in the lung segmentation result; and according to the to-be-resected segmentation result and the drainage basin range corresponding to each vessel point, determining a target resection area of the target lung for the to-be-resected target. According to the technical scheme, the target resection area in the lung can be accurately determined.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of medical data processing, and in particular, to a method, device, electronic device, storage medium and computer program product for determining a lung resection area. Background Art

[0002] The basic principle of surgery is to preserve the normal function of the organ to the maximum extent while ensuring the removal of the resection area. In pursuit of this goal, surgery has continuously evolved resection techniques, and through more minimally invasive and anatomical resection and organ tissue conservation surgical methods, more normal organs can be preserved, which is conducive to improving the efficacy. Therefore, it is crucial to determine the target resection area that needs to be resected during surgery.

[0003] However, due to the complex anatomy of the lungs and the large number of vascular variations, it is difficult to accurately determine the target resection area in the lungs, which urgently needs to be solved. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, electronic device, storage medium and computer program product for determining a lung resection area, so as to accurately determine a target resection area in the lung.

[0005] According to one aspect of the present invention, a method for determining a lung resection area is provided, which may include: obtaining a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vascular segmentation result of a vascular in the lung image; determining a vascular centerline of the vascular according to the vascular segmentation result, and determining a watershed range corresponding to each vascular point on the vascular centerline in the lung segmentation result; determining a target resection area for the target to be resected in the target lung according to the segmentation result to be resected and the watershed range corresponding to each vascular point.

[0006] According to another aspect of the present invention, a device for determining a lung resection area is provided, which may include: a vascular segmentation result acquisition module, used to acquire the lung segmentation result of the lung image of the target lung, the segmentation result of the target to be resected in the lung image, and the vascular segmentation result of the vessel in the lung image; a watershed range determination module, used to determine the vascular centerline of the vessel according to the vascular segmentation result, and determine the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result; a target resection area determination module, used to determine the target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to each vascular point.

[0007] According to another aspect of the present invention, an electronic device is provided, which may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that when the at least one processor executes, the method for determining the lung resection area provided in any embodiment of the present invention is implemented.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are used to enable a processor to implement the method for determining a lung resection area provided by any embodiment of the present invention when executed.

[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the method for determining a lung resection region provided by any embodiment of the present invention.

[0010] The technical solution of the embodiment of the present invention obtains the lung segmentation result of the lung image of the target lung, the segmentation result of the target to be resected in the lung image, and the vascular segmentation result of the vascular in the lung image, so as to determine a more accurate target resection area according to the lung segmentation result, the segmentation result to be resected and the vascular segmentation result; according to the vascular segmentation result, the vascular centerline of the vascular is determined, and the watershed range corresponding to each vascular point on the vascular centerline in the lung segmentation result is determined, so as to clarify the lung area related to the vascular point by determining the watershed range corresponding to each vascular point; according to the segmentation result to be resected and the watershed range corresponding to each vascular point, the target resection area for the target to be resected of the target lung is determined, and the target resection area with higher accuracy can be determined according to the watershed range corresponding to each vascular point. The above technical solution determines the target resection area by the watershed range corresponding to each vascular point, and accurately determines the target resection area in the lung, so that when performing surgical resection according to the target resection area, the target to be resected can be ensured to be cleanly resected while retaining the residual volume of the lung to a greater extent.

[0011] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 is a flow chart of a method for determining a lung resection area provided according to Embodiment 1 of the present invention;

[0014] Figure 2 is an example diagram of a target to be resected and a vessel in a method for determining a lung resection area provided according to an embodiment of the present invention;

[0015] Figure 3 is an example diagram of a target resection area in a method for determining a lung resection area provided according to an embodiment of the present invention;

[0016] Figure 4 is an example diagram of another target resection area in a method for determining a lung resection area provided according to an embodiment of the present invention;

[0017] Figure 5 is an example diagram of a segmentation result in a method for determining a lung resection area provided according to an embodiment of the present invention;

[0018] Figure 6 is an example diagram of a liver segmentation result, a segmentation result to be resected, and a vascular segmentation result in a method for determining a lung resection area provided according to an embodiment of the present invention;

[0019] Figure 7 This is an example diagram of the expansion of the segmentation result to be resected in a method for determining a lung resection area provided in an embodiment of the present invention;

[0020] Figure 8 is a flow chart of another method for determining a lung resection area provided according to an embodiment of the present invention;

[0021] Fig. 9 is a flow chart of another method for determining a lung resection area provided according to an embodiment of the present invention;

[0022] Fig.10 is an example diagram of mapping vascular levels of anatomical definitions of eighteen lung segments in another method for determining a lung resection area provided in an embodiment of the present invention;

[0023] Fig.11 is an example diagram of a vascular hierarchy system in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0024] Fig.12 is an example diagram of a liver segment in another method for determining a lung resection region provided according to an embodiment of the present invention;

[0025] Fig.13is an example diagram of a lung segment having an overlapping area with a segmentation result to be resected in another method for determining a lung resection area provided by an embodiment of the present invention;

[0026] Fig.14 is an example diagram of a target resection area in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0027] Fig.15 is an example diagram of a vascular clamp position in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0028] Fig.16 is an example diagram of another vascular clamp position in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0029] Fig.17 is an example diagram of another vascular clamp position in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0030] Fig.18 is an example diagram of another vascular clamp position in another method for determining a lung resection area provided according to an embodiment of the present invention;

[0031] Fig.19 is a flowchart of an optional example of another method for determining a lung resection area provided according to an embodiment of the present invention;

[0032] Fig. 20 is a structural block diagram of a device for determining a lung resection area provided according to an embodiment of the present invention;

[0033] Fig.21 It is a schematic diagram of the structure of an electronic device for implementing the method for determining a lung resection area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Figure 1 1 is a flow chart of a method for determining a lung resection area provided in an embodiment of the present invention. This embodiment is applicable to the case of determining a lung resection area. The method can be executed by a lung resection area determination device provided in an embodiment of the present invention, the device can be implemented in software and / or hardware, the device can be integrated in an electronic device, and the electronic device can be various user terminals or servers.

[0037] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0038] S110, obtaining a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vascular segmentation result of a vascular in the lung image.

[0039] The target lung is the lung that needs to be determined to be resected. The lung image can be an image obtained by acquiring the target lung; the lung image can be, for example, a medical image such as computed tomography (CT) or magnetic resonance imaging (MRI) in the Digital Imaging and Communications in Medicine (DICOM) format; the lung image can be, for example, two-dimensional or three-dimensional. The lung segmentation result is the result obtained by segmenting the target lung; the lung segmentation result can be, for example, the result obtained by segmenting the lung surface or lung contour of the target lung. The target to be resected is the target that needs to be resected in the target lung, for example, the target to be resected can be Figure 2The yellow target in the image. The segmentation result to be resected is the result obtained by segmenting the target to be resected. The vessel is a tubular structure in the target lung; the vessel may include, for example, blood vessels, trachea, bronchus and / or lymphatic vessels in the target lung, and the vessel may include arteries and / or veins. For example, the vessel may be Figure 2 The white bronchus in the target lung is shown in FIG. 1 . The vascular segmentation result is the result obtained by segmenting the vascular segmentation. It should be noted that the scheme in the embodiment of the present invention can be applied not only to the determination of the lung resection area, but also to the determination of the resection area of ​​other organs or tissues. When applied to the determination of the resection area of ​​other organs or tissues, the "lung" mentioned in the embodiment of the present invention can be replaced with the corresponding organ or tissue. Accordingly, the vascular segmentation result can be the vascular segment of other organs or tissues, for example, it can also include the hepatic vein, hepatic artery, bile duct and / or hepatic duct, etc.

[0040] It should be noted that the number of the target to be resected may be one or more. In the case where the number of the target to be resected is multiple, the technical solution of the embodiment of the present invention may be implemented for the multiple targets to be resected as a whole, or the technical solution of the embodiment of the present invention may be implemented for each target to be resected. Figure 3 , when the number of the target to be removed is one, the technical solution of the embodiment of the present invention can be performed on the target to be removed C1 to obtain the target removal area T1 of the target to be removed; see Figure 4 In the case where there are multiple targets to be resected, the technical solution of the embodiment of the present invention can be executed for each target to be resected to obtain target resection areas T1, T2 and T3 corresponding to the multiple targets to be resected.

[0041] In the embodiment of the present invention, the lung segmentation result, the segmentation result to be resected, and the vascular segmentation result may be three independent segmentation results; at least one of the lung segmentation result, the segmentation result to be resected, and the vascular segmentation result may also be located in the same segmentation result, for example, see Figure 5 , the dark yellow segmentation result to be resected, the red artery segmentation result in the vascular segmentation result, the blue vein segmentation result, and the white trachea and bronchus segmentation results can be located in the same segmentation result.

[0042] In the embodiment of the present invention, the lung segmentation result, the segmentation result of the resected object and the vascular segmentation result can be automatically obtained by using the deep learning segmentation algorithm model. Figure 6 When the technical solution of the embodiment of the present invention is applied to the target liver, for example, a deep learning segmentation algorithm model can be used to perform three-dimensional segmentation of the liver surface, the target to be resected, the portal vein and the hepatic vein of the target liver in the liver image, and automatically obtain the liver segmentation result, the target to be resected segmentation result and the vascular segmentation result.

[0043] S120 . Determine the vascular centerline of the vascular according to the vascular segmentation result, and determine the flow domain ranges corresponding to the vascular points on the vascular centerline in the lung segmentation result.

[0044] The vessel centerline is an imaginary line at the center of the vessel, which can be used to represent the shape, diameter and / or torsion of the vessel. The vessel point is a point on the vessel centerline; the vessel point can be, for example, a two-dimensional pixel point or a three-dimensional voxel point.

[0045] In the embodiment of the present invention, the vascular centerline of the vascular can be extracted from the vascular segmentation result. In the embodiment of the present invention, the method of determining the vascular centerline of the vascular according to the vascular segmentation result is not specifically limited.

[0046] It can be understood that the flow domain range is a range related to the vascular point. For example, when the vascular includes blood vessels, since the blood vessels can supply blood to the specific area corresponding to the vascular point, in this case, the flow domain range is the area supplied by the blood vessels corresponding to the vascular point. For another example, when the vascular includes a trachea, since the trachea can interact with the specific area corresponding to the vascular point, the flow domain range is the area corresponding to the vascular point that has an interactive relationship with the trachea.

[0047] In the embodiment of the present invention, for example, the flow domain ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result can be determined according to the direction of the vascular centerline; for another example, the flow domain ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result can be determined according to the nearest point corresponding to each pixel point or voxel point on the vascular centerline in the lung segmentation result; etc. In the embodiment of the present invention, the method for determining the flow domain ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result is not specifically limited.

[0048] In an embodiment of the present invention, different types of vessels may have different ways of determining the range of watersheds, that is, when there is at least one type of vessel, the vascular centerline of the vessel may be determined for each type of vessel, and the range of watersheds corresponding to each vascular point on the vascular centerline in the lung segmentation result may be determined according to the range determination rule corresponding to the vessel. For example, when the vessel includes blood vessels and trachea, the vascular centerline of the trachea and the vascular centerline of the blood vessels are determined, and the range of watersheds corresponding to each vascular point on the vascular centerline in the lung segmentation result may be determined according to the direction of the vascular centerline of the trachea, and the range of watersheds corresponding to each vascular point on the vascular centerline in the lung segmentation result may be determined according to the nearest point on the vascular centerline of the blood vessel corresponding to each pixel point or voxel point in the lung segmentation result.

[0049] S130 , determining a target resection region of the target lung for the target to be resected according to the segmentation result of the target to be resected and the watershed ranges corresponding to each vascular point.

[0050] The target resection area is the resection area of ​​the target lung that is actually required to be resected and is finally determined.

[0051] In the embodiment of the present invention, for example, the watershed ranges corresponding to the vascular points related to the segmentation result to be resected can be determined, and the area formed by the watershed ranges corresponding to the vascular points can be used as the target resection area. In the embodiment of the present invention, the method of determining the target resection area for the target lung to be resected according to the segmentation result to be resected and the watershed ranges corresponding to the vascular points is not specifically limited.

[0052] The technical solution of the embodiment of the present invention obtains the lung segmentation result of the lung image of the target lung, the segmentation result of the target to be resected in the lung image, and the vascular segmentation result of the vascular in the lung image, so as to determine a more accurate target resection area according to the lung segmentation result, the segmentation result to be resected and the vascular segmentation result; according to the vascular segmentation result, the vascular centerline of the vascular is determined, and the watershed range corresponding to each vascular point on the vascular centerline in the lung segmentation result is determined, so as to clarify the lung area related to the vascular point by determining the watershed range corresponding to each vascular point; according to the segmentation result to be resected and the watershed range corresponding to each vascular point, the target resection area for the target to be resected of the target lung is determined, and the target resection area with higher accuracy can be determined according to the watershed range corresponding to each vascular point. The above technical solution determines the target resection area by the watershed range corresponding to each vascular point, and accurately determines the target resection area in the lung, so that when performing surgical resection according to the target resection area, the target to be resected can be ensured to be cleanly resected while retaining the residual volume of the lung to a greater extent.

[0053] An optional technical solution determines the target resection area of ​​the target lung for the target to be resected based on the segmentation results to be resected and the watershed ranges corresponding to each vascular point, including: for each point to be resected in the segmentation results to be resected, determining the nearest point to be resected that is closest to the point to be resected on the center line of the vessel; determining the target resection area of ​​the target lung for the target to be resected based on the nearest point to be resected corresponding to each point to be resected and the watershed ranges corresponding to each vascular point.

[0054] The point to be removed is a pixel point or voxel point in the segmentation result to be removed, that is, a pixel point or voxel point of the target to be removed in the segmentation result to be removed. The nearest point to be removed is a vessel point on the vessel centerline that is closest to the point to be removed.

[0055] In the embodiment of the present invention, for example, the segmentation result to be resected and the center line of the vessel can be placed in the same space, and for each point to be resected in the segmentation result to be resected, the Euler distances corresponding to the point to be resected and each vessel point are determined to be equal distances, and the vessel point with the smallest Euler distance among the vessel points is used as the nearest point to be resected of the point to be resected, and the Euler distance is determined by Euler distance field transform (EDT). In the embodiment of the present invention, the method of determining the nearest point to be resected that is closest to the point to be resected from the center line of the vessel is not specifically limited.

[0056] In the embodiment of the present invention, there is no specific limitation on the method of determining the target resection area of ​​the target lung for the target to be resected according to the nearest point to be resected corresponding to each point to be resected and the watershed range corresponding to each vascular point.

[0057] In an embodiment of the present invention, the target resection area can be determined by determining the nearest point to be resected corresponding to each point to be resected, so that the determined target resection area can be more closely matched with the target to be resected, thereby more accurately determining the target resection area in the lungs.

[0058] Based on the above scheme, another optional technical scheme is to determine the target resection area of ​​the target lung for the target to be resected according to the nearest point to be resected corresponding to each point to be resected and the watershed range corresponding to each vascular point, including: for each nearest point to be resected obtained, determine the target point corresponding to the nearest point to be resected in each vascular point; determine the target resection area of ​​the target lung for the target to be resected according to the watershed range corresponding to each target point obtained.

[0059] The target point is the vessel point corresponding to the nearest point to be resected.

[0060] In the embodiment of the present invention, for example, for each nearest point to be resected, a target point that is the same point as the nearest point to be resected among the vascular points can be determined, and the obtained target points can represent all vascular clipped branches that can occlude the target to be resected, forming a responsible vascular set. In the embodiment of the present invention, the method of determining the target point corresponding to the nearest point to be resected among the vascular points is not specifically limited.

[0061] In the embodiment of the present invention, for example, the region formed by the watershed ranges corresponding to the obtained target points can be used as the target resection region for the target to be resected in the target lung. In this case, the segmentation result of the target to be resected can be regarded as a subset of the target resection region. In the embodiment of the present invention, the method of determining the target resection region for the target to be resected in the target lung according to the watershed ranges corresponding to the obtained target points is not specifically limited.

[0062] In an embodiment of the present invention, the target point can be determined, and the target resection area of ​​the target lung for the target to be resected can be determined according to the watershed range corresponding to each target point. The determined target resection area can be further made to better match the target to be resected, so that the target resection area in the lung can be determined more accurately.

[0063] Another optional technical solution is that before determining the target resection area of ​​the target lung for the target to be resected based on the segmentation result to be resected and the watershed range corresponding to each vascular point, the method for determining the lung resection area also includes: expanding the edge of the segmentation result to be resected by a preset size, and updating the segmentation result to be resected based on the obtained expansion result.

[0064] The preset size is the size of the edge of the segmentation result to be resected, that is, the size of the safety boundary of the segmentation result to be resected determined according to the cutting edge requirement; the preset size can be, for example, 5-20 mm; the preset size can be determined according to the cutting edge level requirement. The expansion result is the result obtained by expanding the edge of the segmentation result to be resected by the preset size.

[0065] In the embodiments of the present invention, see Figure 7 For example, the edges of the segmentation result C1 to be removed in each direction may be expanded outward by a preset size at equal distances, and the segmentation result to be removed may be updated according to the obtained expansion result; see Figure 5 For another example, the edges of the dark yellow segmentation result to be removed in each direction can be equally expanded by a preset size, and the segmentation result to be removed can be updated according to the obtained light yellow expansion result; etc. The above scheme can make the edge of the updated segmentation result to be removed safer, and can further ensure that the target to be removed is removed cleanly when performing surgical resection according to the target resection area.

[0066] Figure 8It is a flow chart of another method for determining the lung resection area provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result are determined, including: for each lung voxel point in the lung segmentation result, determining the closest lung voxel point on the vascular centerline that is closest to the lung voxel point; according to the closest lung voxel point corresponding to each lung voxel point, determining the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0067] See also Figure 8 The method of this embodiment may specifically include the following steps:

[0068] S210, obtaining a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vascular segmentation result of a vascular in the lung image.

[0069] S220 . Determine the vascular centerline of the vessel according to the vascular segmentation result.

[0070] S230 . For each lung voxel point in the lung segmentation result, determine the lung voxel closest point that is closest to the lung voxel point on the vessel centerline.

[0071] The closest point of the lung voxel is the vessel point on the vessel centerline that is closest to the lung voxel point.

[0072] It should be noted that the lung voxel point is the voxel point in the lung segmentation result when the lung segmentation result is a three-dimensional segmentation result, that is, the voxel point in the area corresponding to the target lung in the lung segmentation result; when the lung segmentation result is a two-dimensional segmentation result, the lung voxel point can be replaced by a lung pixel point.

[0073] In the embodiment of the present invention, for example, the lung segmentation result and the vascular centerline can be placed in the same space, and for each lung voxel point in the lung segmentation result, the Euler distances corresponding to the lung voxel point and each vascular point are determined to be equal distances, and the vascular point with the smallest Euler distance among the vascular points is used as the lung voxel closest point closest to the lung voxel point. In the embodiment of the present invention, the method of determining the lung voxel closest point closest to the lung voxel point from the vascular centerline is not specifically limited.

[0074] For example, the distance field of the image processing operator, such as the definition of the distance field distance transform (DistanceTransform, DT), can be used to calculate the distance q of each lung voxel point p from the vascular centerline, and the q point is the responsible vascular point of this p. The distance q of each lung voxel point p from the vascular centerline can be calculated by, for example, using the formula Df =min q∈G (d(pq)+f(q)) is determined. Among them, D f is the distance between the nearest lung voxel point and the nearest lung voxel point; d(pq) is the distance calculation formula between p and q, for example, the Euler distance can be taken; f(q) is the weight between the lung voxel point and the vascular point; G is the background grid point, that is, G can be a three-dimensional grid function, that is, after the action, discrete vascular points on the vascular centerline can be extracted.

[0075] S240 , determining the flow domain ranges corresponding to the respective vascular points on the vascular centerline in the lung segmentation result according to the nearest lung voxel points corresponding to each lung voxel point.

[0076] In the embodiment of the present invention, for example, the lung voxel nearest points corresponding to each lung voxel point can be integrated, and the area formed by the lung voxel points whose lung voxel nearest points are the same lung voxel nearest points is used as the watershed range of the vascular point corresponding to the lung voxel nearest point in the lung segmentation result, so that each vascular point on the vascular centerline will correspond to the part of the substantial area under the jurisdiction of the target lung. In the embodiment of the present invention, the method of determining the watershed range corresponding to each vascular point on the vascular centerline in the lung segmentation result according to the lung voxel nearest points corresponding to each lung voxel point is not specifically limited.

[0077] S250 , determining a target resection region of the target lung for the target to be resected according to the segmentation result of the target to be resected and the watershed ranges corresponding to the vascular points.

[0078] The technical solution of the embodiment of the present invention is to determine the closest lung voxel point to each lung voxel point in the lung segmentation result from the vascular centerline, so as to determine the vascular point responsible for the area corresponding to the lung voxel point by determining the closest lung voxel point; according to the closest lung voxel point corresponding to each lung voxel point, the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result are determined to determine a watershed range with higher accuracy. The above technical solution can improve the accuracy of the determined watershed range by determining the closest lung voxel point to the lung voxel point, and then determining the watershed ranges corresponding to each vascular point in the lung segmentation result.

[0079] An optional technical solution, according to the nearest lung voxel point corresponding to each lung voxel point, determines the watershed range corresponding to each vascular point on the vascular centerline in the lung segmentation result, including: for each vascular point on the vascular centerline, determining the watershed point of the vascular point, wherein the watershed point is located on the watershed branch on the vascular centerline, the watershed branch starts from the vascular point and ends at the terminal point of the vascular branch where the vascular point is located; for each of all the watershed points obtained, determining the target voxel point among all the lung voxel points that takes the watershed point as the nearest lung voxel; according to the target voxel points corresponding to all the watershed points, determining the watershed range of the vascular point in the lung segmentation result.

[0080] The vascular branch is the branch where the vascular point is located in the vascular centerline. The terminal point is the point at the terminal of the vascular branch. The target voxel point is the lung voxel point that takes the watershed point as the closest point to the lung voxel.

[0081] In the embodiment of the present invention, for example, all vascular points on the flow branch located on the vascular centerline can be used as flow points of the vascular point. In the embodiment of the present invention, the method of determining the flow point of the vascular point is not specifically limited.

[0082] In the embodiment of the present invention, for example, the closest lung voxel points corresponding to each lung voxel point can be integrated to determine the target voxel point that uses the watershed point as the closest lung voxel point among all lung voxel points. In the embodiment of the present invention, the method for determining the target voxel point that uses the watershed point as the closest lung voxel point among all lung voxel points is not specifically limited.

[0083] In the embodiment of the present invention, for example, the area formed by the target voxel points corresponding to all the flow points can be directly used as the flow range of the vascular point in the lung segmentation result, so that the collection of the flow areas of the downstream vessels of the vascular point and its own flow areas form the flow range governed by the flow branch from the vascular point as the starting point (vascular clamping point) to the end of the vascular branch, which is used as the flow range blocked after the message branch is clamped. In the embodiment of the present invention, the method of determining the flow range of the vascular point in the lung segmentation result according to the target voxel points corresponding to all the flow points is not specifically limited.

[0084] In an embodiment of the present invention, the watershed range of the vascular point in the lung segmentation result can be determined by determining the target voxel points corresponding to all the watershed points, so that the determined watershed range is not only the range related to the vascular point itself, but also includes the range related to all the watershed points, thereby determining the target resection area based on the watershed range, so that when performing surgical resection based on the target resection area, it can further ensure that the target to be resected is cleanly resected.

[0085] Fig. 9It is a flow chart of another method for determining a lung resection area provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, the method for determining a lung resection area also includes: constructing a vascular hierarchy system of vascular centerlines using a preset vascular stratification rule; dividing the lung segmentation result according to the vascular hierarchy system and the watershed ranges corresponding to each vascular point to obtain at least one lung segment; determining the target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to each vascular point, including: determining the target resection area of ​​the target lung for the target to be resected according to at least one lung segment, the segmentation result to be resected and the watershed ranges corresponding to each vascular point. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0086] See also Fig. 9 The method of this embodiment may specifically include the following steps:

[0087] S310, obtaining a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vascular segmentation result of a vascular in the lung image.

[0088] S320 . Determine the vascular centerline of the vascular according to the vascular segmentation result, and determine the flow domain ranges corresponding to the vascular points on the vascular centerline in the lung segmentation result.

[0089] S330. Use a preset vascular stratification rule to construct a vascular hierarchy system of vascular centerlines.

[0090] The vascular stratification rule is a rule for stratifying the vascular centerline; the vascular stratification rule can be, for example, the vascular hierarchy mapped by the anatomical definition of the eighteen lung segments, see Fig.10 , the 18-segment anatomical definition of the lung maps the vascular hierarchy to 8 segments of the left lung and 10 segments of the right lung; when the scheme for determining the resection area of ​​the embodiment of the present invention is applied to liver disease, the vascular stratification rule can be, for example, the 8-segment anatomical definition of the liver maps the portal vascular hierarchy, and the 8-segment anatomical definition of the liver maps the portal vascular hierarchy to the caudate lobe branch, left inner, left upper outer, left lower outer, right upper anterior, right lower anterior, right upper posterior, and right lower posterior. The vascular hierarchy system is a system that can characterize the vascular hierarchy corresponding to each vascular branch in the vascular centerline.

[0091] In the embodiments of the present invention, see Fig.11For example, the vascular centerlines may be classified and / or graded and stained and named according to the vascular stratification rules, and a vascular hierarchy system of the vascular centerlines may be constructed according to the obtained results; for another example, the vascular centerlines may be discretized and then modeled into a tree structure, and the vascular hierarchy of the tree structure obtained by modeling may be assigned according to the vascular stratification rules such as the definition of anatomical liver segments or lung segments, and a vascular hierarchy system of the vascular centerlines may be constructed according to the obtained results. In the embodiment of the present invention, there is no specific limitation on the manner of constructing the vascular hierarchy system of the vascular centerlines using the preset vascular stratification rules.

[0092] S340 , dividing the lung segmentation result according to the vascular hierarchy system and the watershed range corresponding to each vascular point to obtain at least one lung segment.

[0093] Among them, the lung segment is the end-level lung unit obtained by dividing the target lung.

[0094] In the embodiment of the present invention, for example, the area formed by the flow domain ranges corresponding to the vascular points of the same level and / or the same type on the vascular centerline can be regarded as a lung segment, and the interface between the lung segments is calculated to complete the allocation of the flow domains corresponding to the lung segments to obtain at least one lung segment. In the embodiment of the present invention, the scheme of dividing the lung segmentation result according to the vascular hierarchy system and the flow domain ranges corresponding to the vascular points to obtain at least one lung segment is not specifically limited.

[0095] For example, see Fig.12 When the technical solution of the embodiment of the present invention is applied to the target liver, the liver segmentation result is divided according to the vascular hierarchy system and the watershed range corresponding to each vascular point to obtain at least one liver segment Si (i=1, 2, ..., 8).

[0096] S350, determining a target resection region of the target lung for the target to be resected according to at least one lung segment, the segmentation result to be resected, and the watershed ranges corresponding to each vascular point.

[0097] In the embodiment of the present invention, there is no specific limitation on the method of determining the target resection area of ​​the target lung for the target to be resected based on at least one lung segment, the segmentation result to be resected and the watershed ranges corresponding to each vascular point.

[0098] The technical solution of the embodiment of the present invention, by constructing a vascular hierarchy system to divide at least one lung segment, and then taking at least one lung segment as a determining factor of the target resection area, can further improve the accuracy of the obtained target resection area, so that when performing surgical resection according to the target resection area, it can further ensure that the target to be resected is cleanly resected.

[0099] An optional technical solution determines a target resection area of ​​a target lung for a target to be resected based on at least one lung segment, a segmentation result to be resected, and a watershed range corresponding to each vascular point, including: determining an initial resection area of ​​a target lung for a target to be resected based on the segmentation result to be resected and a watershed range corresponding to each vascular point; determining a target resection area of ​​a target lung for a target to be resected based on the initial resection area and at least one lung segment.

[0100] The initial resection area is the resection area of ​​the target lung that is determined to be theoretically required to be resected and is targeted at the target to be resected.

[0101] In the embodiment of the present invention, the method of determining the initial resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to each vascular point can be the same as or different from other methods of determining the target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to each vascular point in the embodiment of the present invention. For example, for each point to be resected in the segmentation result to be resected, the closest point to be resected that is closest to the point to be resected can be determined from the center line of the vascular vessel; based on the closest point to be resected corresponding to each point to be resected and the watershed ranges corresponding to each vascular point, the initial resection area of ​​the target lung for the target to be resected can be determined.

[0102] In the embodiment of the present invention, for example, a lung segment in at least one lung segment whose area size belonging to the initial resection area is greater than a preset size, and a region belonging to the initial resection area in a lung segment whose area size belonging to the initial resection area is less than or equal to the preset size can be used as a target resection area. In the embodiment of the present invention, the method of determining the target resection area for the target to be resected of the target lung according to the initial resection area and at least one lung segment is not specifically limited.

[0103] For example, see Fig.13 , the segmentation result to be removed has an overlapping area with lung segments RS3 and RS5, see Fig.14 According to the segmentation results to be resected and the watershed ranges corresponding to each vascular point, the initial resection area of ​​the target lung for the target to be resected is determined to be the area corresponding to T1 and T2. Lung segments RS3 and RS5 that have overlapping areas with the initial resection area in at least one lung segment can be used as target resection areas.

[0104] In an embodiment of the present invention, by determining an initial resection area and determining a target resection area based on the initial resection area and at least one lung segment, it is possible to further ensure that the target to be resected is cleanly resected when performing surgical resection based on the target resection area.

[0105] Another optional technical solution is to determine the target resection area of ​​the target lung for the target to be resected based on the initial resection area and at least one lung segment, including: for each lung segment in at least one lung segment, determining the overlap size of the overlapping area between the lung segment and the initial resection area; when the overlap size is greater than a preset resection threshold, taking the entire area of ​​all lung segments as the segmental resection area in the lung segment; otherwise, determining the number of vessels of the same level in the lung segment that are outside the overlapping area, and determining the segmental resection area of ​​the lung segment based on the number of vessels and the preset resection threshold, wherein the level of vessels of the same level is the same as that of vessels within the overlapping area; and determining the target resection area of ​​the target lung for the target to be resected based on the segmental resection areas corresponding to at least one lung segment obtained.

[0106] The overlap area is the area of ​​overlap between the lung segment and the initial resection area. The overlap size is the size of the overlap area. The preset resection threshold is the threshold of the overlap size of all lung segments that need to be resected. The segment resection area is the area in the lung segment that needs to be resected, that is, the component of the target resection area in the lung segment.

[0107] In an embodiment of the present invention, the vascular branches that overlap with the overlapping area can be regarded as the vessels within the overlapping area, and the vascular branches that intersect with the overlapping area can also be understood as the vessels within the overlapping area; the level to which each vessel in the lung segment belongs is determined by a vascular hierarchy system or other means, that is, the level of each vascular branch is determined, and the vessels outside the overlapping area that have the same level as the vessels within the overlapping area can be regarded as vessels of the same level, and accordingly, the number of vessels is the number of vessels of the same level.

[0108] Exemplarily, the preset resection threshold may include a first resection threshold and a second resection threshold, the first resection threshold being greater than the second resection threshold; for each lung segment in at least one lung segment, the lung segment may be divided according to the vascular hierarchy system and the watershed ranges corresponding to each vascular point, to obtain at least one lung subsegment, and for each lung subsegment in at least one lung subsegment, the lung subsegment may be divided according to the vascular hierarchy system and the watershed ranges corresponding to each vascular point, to obtain at least one sub-subsegment; for each lung segment in at least one lung segment, the overlap size of the overlapping area between the lung segment and the initial resection area may be determined; when the overlap size is greater than the first resection threshold and there is only one overlapping area, or, when the overlap size is greater than the first resection threshold and there is at least one overlapping area, the entire area of ​​all lung segments is used as the segment resection area in the lung segment; when the overlap size is less than or equal to the first resection threshold, the initial resection area may be determined. Threshold, and, greater than or equal to the second resection threshold, and the number of vessels is greater than or equal to 1, the entire area of ​​the lung subsegments in the lung segment that overlap with the initial resection area is used as the segmental resection area in the lung segment; when the overlap size is less than or equal to the first resection threshold, and, greater than or equal to the second resection threshold, and the number of vessels is less than or equal to 1, the entire area of ​​all lung segments is used as the segmental resection area in the lung segment; when the overlap size is less than the second resection threshold and the number of vessels is greater than or equal to 2, the entire area of ​​the subsegments in the lung segment that overlap with the initial resection area is used as the segmental resection area in the lung segment; when the overlap size is less than the second resection threshold and the number of vessels is less than 2, the entire area of ​​the lung subsegments in the lung segment that overlap with the initial resection area is used as the segmental resection area in the lung segment, or the entire area of ​​all lung segments is used as the segmental resection area in the lung segment. In the embodiment of the present invention, the method of determining the segmental resection area of ​​the lung segment according to the number of vessels and the preset resection threshold is not specifically limited.

[0109] In the embodiment of the present invention, an area formed by segmental resection areas respectively corresponding to at least one lung segment may be used as a target resection area of ​​the target lung for the object to be resected.

[0110] In an embodiment of the present invention, the recommended anatomical resection mode can also be determined and displayed based on the segment relationship between the target resection area and the lung segments, lung subsegments and / or sub-subsegments. For example, when the number of lung segments or lung subsegments included in the target resection area is determined to be 1 according to the segment relationship, the recommended anatomical resection mode is determined to be single segment resection, or, lung subsegment or sub-subsegment resection; when the number of lung segments or lung subsegments included in the target resection area is determined to be greater than 1 according to the segment relationship and there is an adjacent relationship between the lung segments or lung subsegments included in the target resection area, the recommended anatomical resection mode is determined to be combined lung segment or lung subsegment resection; when the number of lung segments or lung subsegments included in the target resection area is determined to be greater than 1 according to the segment relationship and there is an adjacent relationship between the lung segments or lung subsegments included in the target resection area, the recommended anatomical resection mode is determined to be extended resection; when the number of lung segments included in the target resection area is determined to be greater than 1 according to the segment relationship and the target resection area includes all lung segments under the lobe definition, the recommended anatomical resection mode is determined to be lobectomy.

[0111] In the embodiment of the present invention, the position of the vascular clamp may also be determined according to the segment relationship between the target resection area and the lung segment, lung subsegment and / or sub-subsegment.

[0112] For example, when the technical solution of the embodiment of the present invention is applied to the target liver, see Fig.15 According to the segment relationship, the number of liver subsegments included in the target resection area is determined to be 3 and the liver segments or liver subsegments included in the target resection area have an adjacent relationship. The recommended anatomical resection mode is determined to be three liver subsegment resection, and the vascular clamps No. 1, 2, and 3 are determined to be clamped on the subsegmental branches of the S5, S8, and S3 liver segments, respectively; see Fig.16 , determine the recommended anatomical resection pattern is the whole resection of S6 and S7 liver segments combined with the resection of S5 and S8 liver subsegments, and determine that the No. 1 vascular clamp is clamped on the right posterior branch of the portal vein of the S6 and S7 liver segments, the No. 2 vascular clamp is clamped on the anterior inferior branch of the S5 liver subsegment, and the No. 3 vascular clamp is clamped on the right anterior superior branch of the S8 liver segment and displayed; see Fig.17 , determine the recommended anatomical resection mode as the whole resection of the S5 liver segment combined with the S6 and S7 liver subsegment resection, and determine the positions of the vascular clamps 1, 2, 3, 4 and 5 respectively and display them; when the technical solution of the embodiment of the present invention is applied to the target lung, refer to Fig.18 , determine that the left apex posterior sub-segment of the target lung meets the 5mm resection margin design, recommend the anatomical resection mode as lung sub-subsegment resection, and determine the position of the No. 1 vascular clamp and display it.

[0113] In the embodiment of the present invention, the total volume of the target lung can also be determined based on the lung segmentation result, and the residual lung volume can be determined and displayed based on the difference between the total volume and the target resection area.

[0114] In an embodiment of the present invention, when the overlap size is greater than a preset resection threshold, the entire area of ​​all lung segments is used as the segmental resection area in the lung segment; otherwise, the segmental resection area of ​​the lung segment is determined according to the number of blood vessels and the preset resection threshold, and the target resection area of ​​the target lung for the target to be resected is determined according to the segmental resection area corresponding to at least one lung segment obtained, so that the target resection area can be accurately determined to determine the target resection area in the lung with higher accuracy.

[0115] In order to better understand the technical solution of the above embodiment of the present invention, an optional example is provided here. Fig.19 , input a lung image; segment the lung image to obtain a lung segmentation result, a segmentation result to be removed, and a vascular segmentation result; expand the edge of the segmentation result to be removed, and update the segmentation result to be removed based on the obtained expansion result; determine the vascular centerline of the vessel based on the vascular segmentation result; segment the lung segmentation result according to the anatomical structure to obtain at least one lung segment; determine the responsible vascular set based on the vascular centerline and the segmentation result to be removed; determine the target resection area and vascular clamp position and display them based on the responsible vascular set; accept the user's manual modification of the vascular clamp position and / or the instruction to determine the vascular clamp position, and modify the vascular clamp position and / or determine the vascular clamp position according to the instruction, so that the user can manually modify the vascular clamp position and / or determine the vascular clamp position; determine the recommended anatomical resection mode as single segment resection, lung subsegment resection, sub-subsegment resection, combined lung segment resection, lobectomy and / or enlarged segment resection based on the segment relationship between the target resection area and the lung segment, lung subsegment and / or sub-subsegment.

[0116] The technical solution of the embodiment of the present invention utilizes the combined watershed range to obtain the optimal resection margin distribution, which is still applicable to special cases such as vascular variation and vascular branch omission. Through the resection margin distribution and the relationship between the anatomical segments of the organs automatically inferred by deep learning artificial intelligence, the target resection area of ​​a single or multiple targets to be resected can be automatically determined, supporting the surgical planning of multiple targets to be resected. The best surgical procedure can be recommended from single segment resection, expanded segment resection, combined segment resection, subsegment resection or sub-subsegment resection, etc., to automatically recommend an intelligent method for anatomical watershed surgical resection, to assist in guiding how to select anatomical resection plans for targets to be resected in the chest and abdomen. In summary, the technical solution of the embodiment of the present invention has the advantages of high efficiency, automation, and refined recommendation of surgical plans compared with the manual interaction and traditional imaging post-processing technical solutions in the prior art.

[0117] Fig. 20This is a structural block diagram of a lung resection area determination device provided in an embodiment of the present invention, and the device is used to execute the lung resection area determination method provided in any of the above embodiments. The device and the lung resection area determination method of the above embodiments belong to the same inventive concept. For details not fully described in the embodiments of the lung resection area determination device, reference can be made to the embodiments of the lung resection area determination method. Fig. 20 The device may specifically include: a vessel segmentation result acquisition module 410, a watershed range determination module 420 and a target resection area determination module 430.

[0118] Among them, the vascular segmentation result acquisition module 410 is used to obtain the lung segmentation result of the lung image of the target lung, the segmentation result of the target to be resected in the lung image, and the vascular segmentation result of the vessel in the lung image; the watershed range determination module 420 is used to determine the vascular centerline of the vessel according to the vascular segmentation result, and determine the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result; the target resection area determination module 430 is used to determine the target resection area for the target to be resected in the target lung according to the segmentation result to be resected and the watershed ranges corresponding to each vascular point.

[0119] Optionally, the watershed range determination module 420 includes: a lung voxel nearest point determination submodule, which is used to determine, for each lung voxel point in the lung segmentation result, the lung voxel nearest point on the vascular centerline that is closest to the lung voxel point; and a watershed range determination submodule, which is used to determine the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result according to the lung voxel nearest point corresponding to each lung voxel point.

[0120] Optionally, based on the above-mentioned device, a watershed range determination submodule includes: a watershed point determination unit, which is used to determine the watershed point of the vascular point for each vascular point on the vascular centerline, wherein the watershed point is located on a watershed branch on the vascular centerline, and the watershed branch starts from the vascular point and ends at the terminal point of the vascular branch where the vascular point is located; a target voxel point determination unit, which is used to determine, for each watershed point in all the obtained watershed points, a target voxel point among all the lung voxel points that uses the watershed point as the closest point to the lung voxel; and a watershed range determination unit, which is used to determine the watershed range of the vascular point in the lung segmentation result according to the target voxel points corresponding to all the watershed points.

[0121] Optionally, the target resection area determination module 430 includes: a submodule for determining the nearest point to be resected, which is used to determine, for each point to be resected in the segmentation result, the nearest point to be resected that is closest to the point to be resected from the center line of the vessel; and a first target resection area determination submodule, which is used to determine the target resection area of ​​the target lung for the target to be resected based on the nearest point to be resected corresponding to each point to be resected and the watershed range corresponding to each vascular point.

[0122] Optionally, based on the above-mentioned device, the first target resection area determination submodule includes: a target point determination unit, used to determine the target point corresponding to the nearest point to be resected in each vascular point for each nearest point to be resected; a target resection area determination unit, used to determine the target resection area of ​​the target lung for the target to be resected based on the watershed range corresponding to each target point obtained.

[0123] Optionally, the device also includes: a vascular hierarchy system construction module, which is used to construct a vascular hierarchy system of vascular centerlines using preset vascular stratification rules; a lung segment acquisition module, which is used to divide the lung segmentation results according to the vascular hierarchy system and the watershed ranges corresponding to each vascular point, so as to obtain at least one lung segment; a target resection area determination module 430, including: a second target resection area determination submodule, which is used to determine the target resection area of ​​the target lung for the target to be resected based on at least one lung segment, the segmentation result to be resected and the watershed ranges corresponding to each vascular point.

[0124] Optionally, based on the above-mentioned device, the second target resection area determination submodule includes: an initial resection area determination unit, which is used to determine the initial resection area of ​​the target lung for the target to be resected according to the segmentation result of the target to be resected and the watershed range corresponding to each vascular point; a target resection area determination unit, which is used to determine the target resection area of ​​the target lung for the target to be resected according to the initial resection area and at least one lung segment.

[0125] Optionally, based on the above-mentioned device, the target resection area determination unit includes: an overlap size determination subunit, which is used to determine the overlap size of the overlapping area between the lung segment and the initial resection area for each lung segment in at least one lung segment; a segment resection area as a subunit, which is used to use the entire area of ​​all lung segments as the segment resection area in the lung segment when the overlap size is greater than a preset resection threshold; a segment resection area determination subunit, which is used to determine the number of vessels of the same level in the lung segment that are located outside the overlapping area, and determine the segment resection area of ​​the lung segment based on the number of vessels and the preset resection threshold, wherein the level of the vessels of the same level is the same as that of the vessels within the overlapping area; a target resection area determination subunit, which is used to determine the target resection area of ​​the target lung for the target to be resected based on the segment resection areas corresponding to at least one lung segment obtained.

[0126] Optionally, the device may also include: a module for updating the segmentation results to be resected, which is used to expand the edge of the segmentation results to be resected by a preset size before determining the target resection area of ​​the target lung for the target to be resected based on the segmentation results to be resected and the watershed ranges corresponding to each vascular point, and update the segmentation results to be resected based on the obtained expansion results.

[0127] The lung resection area determination device provided by the embodiment of the present invention obtains the lung segmentation result of the lung image of the target lung, the to-be-resected segmentation result of the to-be-resected target in the lung image, and the vascular segmentation result of the vascular in the lung image through the vascular segmentation result acquisition module, so as to subsequently determine a more accurate target resection area according to the lung segmentation result, the to-be-resected segmentation result and the vascular segmentation result; determines the vascular centerline of the vascular according to the vascular segmentation result through the watershed range determination module, and determines the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result, so as to clarify the lung area related to the vascular point by determining the watershed ranges corresponding to each vascular point; determines the target resection area for the to-be-resected target of the target lung according to the to-be-resected segmentation result and the watershed ranges corresponding to each vascular point through the target resection area determination module, and determines the target resection area with higher accuracy according to the watershed ranges corresponding to each vascular point. The above-mentioned device determines the target resection area through the watershed range corresponding to each vascular point, and accurately determines the target resection area in the lung, so that when performing surgical resection according to the target resection area, it can ensure that the target to be resected is cleanly resected while retaining the residual volume of the lung to a greater extent.

[0128] The lung resection area determination device provided in the embodiment of the present invention can execute the lung resection area determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0129] It is worth noting that in the above-mentioned embodiment of the device for determining the lung resection area, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0130] Fig.21 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0131] like Fig.21 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0132] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0133] The processor 11 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a lung resection area.

[0134] In some embodiments, the method for determining a lung resection area may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining a lung resection area described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method for determining a lung resection area in any other appropriate manner (e.g., by means of firmware).

[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0140] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0141] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0142] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a lung resection area, characterized in that: include: Acquire a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vascular segmentation result of a vascular in the lung image; Determine, according to the vascular segmentation result, a vascular centerline of the vascular, and determine the flow domain ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result; A target resection region of the target lung for the target to be resected is determined according to the segmentation result of the target to be resected and the watershed ranges corresponding to the vascular points.

2. The method according to claim 1, characterized in that The determining of the flow domain ranges corresponding to the respective vascular points on the vascular centerline in the lung segmentation result includes: For each lung voxel point in the lung segmentation result, determining the lung voxel closest point that is closest to the lung voxel point on the vascular centerline; According to the lung voxel nearest point corresponding to each lung voxel point, the flow domain range corresponding to each vascular point on the vascular centerline in the lung segmentation result is determined.

3. The method according to claim 2, characterized in that The determining, according to the lung voxel nearest point corresponding to each lung voxel point, the flow domain range corresponding to each vascular point on the vascular centerline in the lung segmentation result, comprises: For each vascular point on the vascular centerline, determine a flow area point of the vascular point, wherein the flow area point is located on a flow area branch on the vascular centerline, and the flow area branch starts from the vascular point and ends at a terminal point of the vascular branch where the vascular point is located; For each of all the obtained watershed points, determine a target voxel point among all the lung voxel points that uses the watershed point as the closest point to the lung voxel; The flow domain range of the vascular point in the lung segmentation result is determined according to the target voxel points respectively corresponding to all the flow domain points.

4. The method according to claim 1, characterized in that The step of determining a target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges respectively corresponding to the vascular points includes: For each point to be resected in the segmentation result to be resected, determining the closest point to be resected that is closest to the point to be resected on the center line of the vessel; The target resection region of the target lung for the target to be resected is determined according to the nearest point to be resected corresponding to each point to be resected and the watershed range corresponding to each vascular point.

5. The method according to claim 4, characterized in that The step of determining a target resection area of ​​the target lung for the target to be resected according to the nearest point to be resected corresponding to each point to be resected and the watershed range corresponding to each vascular point, comprises: For each obtained closest point to be resected, determining a target point among the vascular points corresponding to the closest point to be resected; A target resection region of the target lung for the target to be resected is determined according to the obtained watershed ranges corresponding to the target points.

6. The method according to claim 1, characterized in that Also includes: Using a preset vascular stratification rule to construct a vascular hierarchical system of the vascular centerline; Dividing the lung segmentation result according to the vascular hierarchy system and the watershed ranges corresponding to each vascular point to obtain at least one lung segment; The step of determining a target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges respectively corresponding to the vascular points includes: A target resection region of the target lung for the target to be resected is determined according to the at least one lung segment, the segmentation result to be resected, and the flow domain ranges respectively corresponding to the vascular points.

7. The method according to claim 6, characterized in that The step of determining a target resection area of ​​the target lung for the target to be resected according to the at least one lung segment, the segmentation result to be resected, and the watershed ranges respectively corresponding to the vascular points, comprises: Determining an initial resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to the vascular points; A target resection region of the target lung for the object to be resected is determined according to the initial resection region and the at least one lung segment.

8. The method according to claim 7, characterized in that The step of determining a target resection area of ​​the target lung for the target to be resected according to the initial resection area and the at least one lung segment comprises: For each of the at least one lung segment, determining an overlap size of an overlap area between the lung segment and the initial resection area; When the overlap size is greater than a preset resection threshold, taking the entire area of ​​the entire lung segment as the segmental resection area in the lung segment; Otherwise, determining the number of vessels of the same level in the lung segment outside the overlapping area, and determining the segmental resection area of ​​the lung segment according to the number of vessels and the preset resection threshold, wherein the vessels of the same level have the same level as the vessels in the overlapping area; A target resection region of the target lung for the object to be resected is determined according to the obtained segmental resection regions respectively corresponding to the at least one lung segment.

9. The method according to claim 1, characterized in that: Before determining the target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges respectively corresponding to the vascular points, the method further includes: The edge of the segmentation result to be cut off is expanded outward by a preset size, and the segmentation result to be cut off is updated according to the obtained expansion result.

10. A device for determining a lung resection area, characterized in that: include: A vessel segmentation result acquisition module, used to acquire a lung segmentation result of a lung image of a target lung, a segmentation result of a target to be resected in the lung image, and a vessel segmentation result of a vessel in the lung image; A watershed range determination module, used to determine the vascular centerline of the vascular according to the vascular segmentation result, and determine the watershed ranges corresponding to each vascular point on the vascular centerline in the lung segmentation result; The target resection area determination module is used to determine the target resection area of ​​the target lung for the target to be resected according to the segmentation result to be resected and the watershed ranges corresponding to the vascular points.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining a lung resection region according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a lung resection area as described in any one of claims 1-9 when executed.

13. A computer program product, comprising a computer program, which, when executed by a processor, implements the method for determining a lung resection region according to any one of claims 1 to 9.

Images