Lung recognition processing method, device and server

Abstract

The application provides a lung recognition processing method and device and a server, relates to model processing technology, and the method comprises the following steps: obtaining a model recognition instruction, the model recognition instruction comprises a lung model identifier, determining a lung model corresponding to the lung model identifier, and the lung model comprises a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model. Based on the growth information of at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, a plurality of initial segmentation cross sections of the lung parenchyma model are determined. According to at least one of the intrasegment trachea, intrasegment vein and intrasegment artery in each initial lung segment, a plurality of target segmentation cross sections of the lung parenchyma model are generated. According to the target segmentation cross sections of the reconstructed lung model, the distribution information of each lung segment can be obtained, thereby helping to improve the accuracy of the surgical plan, reduce the surgical risk index, improve the surgical success rate, and solve the technical problem that it is difficult to recognize the distribution of the intrapulmonary trachea, blood vessels and lung segments.

Description

TECHNICAL FIELD

[0001] The present application relates to a model processing technology, in particular to a lung recognition processing method and device and a server. BACKGROUND

[0002] At present, lung cancer has become the first cancer killer threatening the health of Chinese people. Surgical operation plays a decisive role in the treatment of resectable lung cancer. Thoracoscope operation (minimally invasive) improves the postoperative life quality and survival rate of patients. Thoracoscope anatomical lung segment resection is safe and feasible, and the treatment effect has basically been confirmed.

[0003] In the prior art, the lung segment resection requires the doctor to accurately recognize the distribution of the trachea, blood vessels and lung segments in the patient's lung. The division of the lung segment is determined based on the distribution of the trachea and blood vessels.

[0004] However, in the prior art, the invasion of the tumor in the lung will cause the trachea and blood vessels to vary, or the lung fissure of some patients is poorly developed or completely undeveloped. If the distribution of the trachea, blood vessels and lung segments in the patient's lung is determined according to the conventional segmentation method, the distribution will be inaccurate, and thus the lung segment resection may damage the main artery and other tissues, thereby increasing the risk index of the operation. SUMMARY

[0005] The present application provides a lung recognition processing method, device and server to solve the technical problem that it is difficult to recognize the distribution of the trachea, blood vessels and lung segments in the lung.

[0006] In a first aspect, the present application provides a lung recognition processing method, comprising:

[0007] obtaining a model recognition instruction, wherein the model recognition instruction comprises a lung model identifier, and determining a lung model corresponding to the lung model identifier, the lung model comprising a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model;

[0008] determining a plurality of initial segmentation sections of the lung parenchyma model based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model; wherein the initial segmentation section divides the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of a segmental trachea, a segmental vein and a segmental artery;

[0009] generating a plurality of target segmentation sections of the lung parenchyma model according to the growth information of at least one of the segmental trachea, the segmental vein and the segmental artery in each initial lung segment; wherein the target segmentation section divides the lung parenchyma model into a plurality of target lung segments, and each target lung segment comprises distribution information of at least one of the segmental trachea, the segmental vein and the segmental artery.

[0010] Further, the determining the plurality of initial segmented cross sections of the lung parenchyma model based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model comprises:

[0011] acquiring interlobar veins based on the pulmonary vein model; wherein the interlobar veins are veins located between pulmonary lobes;

[0012] determining the plurality of initial segmented cross sections of the lung parenchyma model according to the interlobar veins.

[0013] Further, the determining the plurality of initial segmented cross sections of the lung parenchyma model according to the interlobar veins comprises:

[0014] acquiring trachea grading results based on the trachea model, and / or acquiring pulmonary artery grading results based on the pulmonary artery model; wherein the trachea grading results are determined according to preset trachea naming rule information, and the pulmonary artery grading results are determined according to preset pulmonary artery naming rule information;

[0015] determining the plurality of initial segmented cross sections of the lung parenchyma model based on any one or two of the interlobar veins, the trachea grading results and the pulmonary artery grading results.

[0016] Further, the determining the plurality of initial segmented cross sections of the lung parenchyma model based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model comprises:

[0017] acquiring trachea grading results based on the trachea model, and / or acquiring pulmonary artery grading results based on the pulmonary artery model; wherein the trachea grading results are determined according to preset trachea naming rule information, and the pulmonary artery grading results are determined according to preset pulmonary artery naming rule information;

[0018] determining the plurality of initial segmented cross sections of the lung parenchyma model based on the trachea grading results and / or the pulmonary artery grading results.

[0019] Further, the generating the plurality of target segmented cross sections of the lung parenchyma model according to at least one of the intralobar trachea, the intralobar vein and the intralobar artery in each initial lung lobe comprises:

[0020] determining at least one of the intralobar trachea, the intralobar vein and the intralobar artery of each initial lung lobe;

[0021] determining growth information of at least one of the intralobar vein and the intralobar artery in each initial lung lobe;

[0022] determine whether at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments has a preset abnormality according to growth information of the at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments;

[0023] If it is determined that at least one of the intrasegmental vein and the intrasegmental artery has a preset abnormality, a plurality of target segmentation sections of the lung parenchyma model are generated based on preset first rule information; wherein the preset first rule information is used to indicate that at least a part of the intrasegmental artery in the initial lung segment passes through a target segmentation section corresponding to a target lung segment where the intrasegmental artery is located, and / or at least a part of the intrasegmental vein passes through a target segmentation section corresponding to a target lung segment where the intrasegmental vein is located.

[0024] Further, the determination of at least one of the intrasegmental bronchus, the intrasegmental vein and the intrasegmental artery of each initial lung segment comprises:

[0025] obtaining a bronchial grading result based on the bronchial model, and determining the intrasegmental bronchus of each initial lung segment in the initial segmentation section based on the bronchial grading result; and / or,

[0026] obtaining a pulmonary vein grading result based on the pulmonary vein model, and determining the intrasegmental vein of each initial lung segment in the initial segmentation section based on the pulmonary vein grading result; and / or,

[0027] obtaining a pulmonary artery grading result based on the pulmonary artery model, and determining the intrasegmental artery of each initial lung segment in the initial segmentation section based on the pulmonary artery grading result.

[0028] Further, the determination of whether at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments has a preset abnormality according to growth information of the at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments comprises:

[0029] determining whether the intrasegmental vein grows across segments according to growth information of the intrasegmental vein in each of the initial lung segments; and / or, determining whether the intrasegmental artery grows across segments according to growth information of the intrasegmental artery in each of the initial lung segments;

[0030] If it is determined that the intrasegmental vein grows across segments, it is determined that the intrasegmental vein has a preset abnormality; and / or, if it is determined that the intrasegmental artery grows across segments, it is determined that the intrasegmental artery has a preset abnormality.

[0031] Further, the determination of whether the intrasegmental vein grows across segments according to growth information of the intrasegmental vein in each of the initial lung segments comprises:

[0032] determine, according to the growth information of the intrasegmental vein in each initial lung segment, whether a first distance between the intrasegmental vein and a first adjacent blood vessel is greater than a vein threshold value; wherein the first adjacent blood vessel comprises an intrasegmental vein and / or an intrasegmental artery adjacent to the intrasegmental vein;

[0033] if it is determined that the first distance is less than the vein threshold value, determine that the intrasegmental vein has trans-segment growth;

[0034] if it is determined that the first distance is greater than the vein threshold value, determine that the intrasegmental vein does not have trans-segment growth.

[0035] Further, the determining, according to the growth information of the intrasegmental artery in each initial lung segment, whether the intrasegmental artery has trans-segment growth, comprises:

[0036] determine, according to the growth information of the intrasegmental artery in each initial lung segment, whether a second distance between the intrasegmental artery and a second adjacent blood vessel is greater than an artery threshold value; wherein the second adjacent blood vessel comprises an intrasegmental artery and / or an intrasegmental vein adjacent to the intrasegmental artery;

[0037] if it is determined that the second distance is less than the artery threshold value, determine that the intrasegmental artery has trans-segment growth;

[0038] if it is determined that the second distance is greater than the artery threshold value, determine that the intrasegmental artery does not have trans-segment growth.

[0039] Further, the method further comprises:

[0040] if it is determined that neither the intrasegmental artery nor the intrasegmental vein has the preset abnormality, generate a target segmented section of the lung parenchyma model based on preset second rule information; wherein the preset second rule information is used to indicate that the intrasegmental artery in the initial lung segment does not pass through a target segmented section corresponding to a target lung segment where the intrasegmental artery is located, and the intrasegmental vein does not pass through a target segmented section corresponding to a target lung segment where the intrasegmental vein is located. Further, the method further comprises:

[0041] issue a prompt information; wherein the prompt information is used to indicate a target lung segment having a preset abnormality in the target segmented section.

[0042] In a second aspect, the present application provides a lung recognition processing device, comprising:

[0043] a first acquisition unit configured to acquire a model recognition instruction, wherein the model recognition instruction comprises a lung model identifier;

[0044] The first determining unit is configured to determine a lung model corresponding to the lung model identifier, the lung model comprising a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model;

[0045] The second determining unit is configured to determine a plurality of initial segmentation cross sections of the lung parenchyma model based on growth information of at least one of the trachea model, the pulmonary vein model, and the pulmonary artery model; wherein the initial segmentation cross sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of a segmental trachea, a segmental vein, and a segmental artery;

[0046] The generating unit is configured to generate a plurality of target segmentation cross sections of the lung parenchyma model according to the at least one of the segmental trachea, the segmental vein, and the segmental artery in each initial lung segment; wherein the target segmentation cross sections divide the lung parenchyma model into a plurality of target lung segments, and each target lung segment comprises distribution information of the at least one of the segmental trachea, the segmental vein, and the segmental artery.

[0047] Further, the second determining unit comprises:

[0048] The first obtaining module is configured to obtain an intersegmental vein based on the pulmonary vein model; wherein the intersegmental vein is a vein located between lung segments.

[0049] The first determining module is configured to determine a plurality of initial segmentation cross sections of the lung parenchyma model according to the intersegmental vein.

[0050] Further, the first determining module comprises:

[0051] The first obtaining submodule is configured to obtain a trachea grading result based on the trachea model, and / or obtain a pulmonary artery grading result based on the pulmonary artery model; wherein the trachea grading result is determined according to preset trachea naming rule information, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rule information.

[0052] The first determining submodule is configured to determine a plurality of initial segmentation cross sections of the lung parenchyma model based on any one or two of the intersegmental vein, the trachea grading result, and the pulmonary artery grading result.

[0053] Further, the second determining unit comprises:

[0054] The second obtaining module is configured to obtain a trachea grading result based on the trachea model, and / or obtain a pulmonary artery grading result based on the pulmonary artery model; wherein the trachea grading result is determined according to preset trachea naming rule information, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rule information.

[0055] The second determining module is configured to determine a plurality of initial segmented sections of the lung parenchyma model based on the trachea grading result and / or the pulmonary artery grading result.

[0056] Further, the generating unit comprises:

[0057] The third determining module is configured to determine at least one of an intrasegmental trachea, an intrasegmental vein and an intrasegmental artery in each initial lung segment.

[0058] The fourth determining module is configured to determine growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment.

[0059] The fifth determining module is configured to determine whether at least one of the intrasegmental artery and the intrasegmental vein has a preset abnormality according to the growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment.

[0060] The first generating module is configured to generate a plurality of target segmented sections of the lung parenchyma model based on preset first rule information if it is determined that at least one of the intrasegmental artery and the intrasegmental vein has a preset abnormality, wherein the preset first rule information is used to indicate that at least a part of the intrasegmental artery in the initial lung segment passes through a target segmented section corresponding to a target lung segment where the intrasegmental artery is located, and / or at least a part of the intrasegmental vein passes through a target segmented section corresponding to a target lung segment where the intrasegmental vein is located.

[0061] Further, the third determining module is specifically configured to:

[0062] The trachea grading result is obtained based on the trachea model, and the intrasegmental trachea of each initial lung segment in the initial segmented sections is determined based on the trachea grading result; and / or, the pulmonary vein grading result is obtained based on the pulmonary vein model, and the intrasegmental vein of each initial lung segment in the initial segmented sections is determined based on the pulmonary vein grading result; and / or, the pulmonary artery grading result is obtained based on the pulmonary artery model, and the intrasegmental artery of each initial lung segment in the initial segmented sections is determined based on the pulmonary artery grading result.

[0063] Further, the fifth determining module comprises:

[0064] The second determining submodule is configured to determine whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each initial lung segment; and / or,

[0065] The third determining submodule is configured to determine whether the intrasegmental artery grows across segments according to the growth information of the intrasegmental artery in each initial lung segment.

[0066] The fourth determining sub-module is configured to determine that the intrasegmental vein has a preset abnormality if it is determined that the intrasegmental vein grows across segments; and / or determine that the intrasegmental artery has a preset abnormality if it is determined that the intrasegmental artery grows across segments.

[0067] Further, the second determining sub-module comprises:

[0068] The fifth determining sub-module is configured to determine whether a first distance between the intrasegmental vein and a first adjacent blood vessel is greater than a vein threshold value according to the growth information of the intrasegmental vein in each initial lung segment; wherein the first adjacent blood vessel comprises an intrasegmental vein and / or an intrasegmental artery adjacent to the intrasegmental vein.

[0069] The sixth determining sub-module is configured to determine that the intrasegmental vein grows across segments if it is determined that the first distance is less than the vein threshold value.

[0070] The seventh determining sub-module is configured to determine that the intrasegmental vein does not grow across segments if it is determined that the first distance is greater than the vein threshold value.

[0071] Further, the third determining sub-module comprises:

[0072] The eighth determining sub-module is configured to determine whether a second distance between the intrasegmental artery and a second adjacent blood vessel is greater than an artery threshold value according to the growth information of the intrasegmental artery in each initial lung segment; wherein the second adjacent blood vessel comprises an intrasegmental artery and / or an intrasegmental vein adjacent to the intrasegmental artery.

[0073] The ninth determining sub-module is configured to determine that the intrasegmental artery grows across segments if it is determined that the second distance is less than the artery threshold value.

[0074] The tenth determining sub-module is configured to determine that the intrasegmental artery does not grow across segments if it is determined that the second distance is greater than the artery threshold value.

[0075] Further, the apparatus further comprises:

[0076] The second generating module is configured to generate a target segmentation section of the lung parenchyma model based on preset second rule information if it is determined that the intrasegmental artery and the intrasegmental vein do not have preset abnormalities; wherein the preset second rule information is used to indicate that the intrasegmental artery in the initial lung segment does not pass through a target segmentation section corresponding to a target lung segment where the intrasegmental artery is located, and the intrasegmental vein does not pass through a target segmentation section corresponding to a target lung segment where the intrasegmental vein is located.

[0077] Further, the apparatus further comprises:

[0078] The prompt unit is configured to send prompt information, wherein the prompt information is used to indicate that a target lung segment with a preset abnormality exists in the target segment cross section.

[0079] In a third aspect, the present application provides a server, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor executes the computer program to implement the method of the first aspect.

[0080] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method of the first aspect.

[0081] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0082] This application provides a lung identification processing method, apparatus, and server. The method involves acquiring a model identification instruction, which includes a lung model identifier and determining the lung model corresponding to the lung model identifier. The lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model. Based on the growth information of at least one of the trachea model, pulmonary vein model, and pulmonary artery model, multiple initial segmented sections of the lung parenchyma model are determined. Each initial segmented section divides the lung parenchyma model into multiple initial lung segments, and each initial lung segment includes at least one of an intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Based on at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, multiple target segmented sections of the lung parenchyma model are generated. Each target segmented section divides the lung parenchyma model into multiple target lung segments, and each target lung segment includes distribution information of at least one of an intrasegmental trachea, intrasegmental vein, and intrasegmental artery. In this scheme, the lung model corresponding to the lung model identifier is determined according to the model identification instruction in the model identification instruction. The lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model. Then, based on any one or more of the tracheal model, pulmonary vein model, and pulmonary artery model, multiple initial segmental sections of the lung parenchyma model are determined. These initial segmental sections divide the lung parenchyma model into multiple initial lung segments, each including at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Based on the growth information of any one or more of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, multiple target segmental sections of the lung parenchyma model are generated. These target segmental sections divide the lung parenchyma model into multiple target lung segments, each including the distribution information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Therefore, based on the target segmental sections of the reconstructed lung model, the distribution information of each lung segment can be obtained, thereby helping to improve the accuracy of surgical planning, reduce the surgical risk index, increase the surgical success rate, and solve the technical problem of the difficulty in identifying the distribution of trachea, blood vessels, and lung segments within the lung. Attached Figure Description

[0083] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0084] Figure 1 A schematic flowchart of a lung identification processing method provided in an embodiment of this application;

[0085] Figure 2 A schematic diagram of the structure of a lung model in its first state, provided in an embodiment of this application;

[0086] Figure 3 A schematic diagram of the second state of a lung model provided in an embodiment of this application;

[0087] Figure 4 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0088] Figure 5 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0089] Figure 6 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0090] Figure 7 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0091] Figure 8 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0092] Figure 9 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0093] Figure 10 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0094] Figure 11 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0095] Figure 12 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0096] Figure 13 A flowchart of another lung recognition processing method provided by an embodiment of the present application is shown in FIG. 18.

[0097] The specific embodiments of the present disclosure have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the present disclosure concept in any way, but to illustrate the present disclosure concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0098] The exemplary embodiments will be described in detail herein below with reference to the drawings. In the following description, the same drawings refer to the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present disclosure.

[0099] At present, lung cancer has become the first cancer killer threatening the health of Chinese people. Surgical operation plays a decisive role in the treatment of resectable lung cancer. Thoracoscope operation (minimally invasive) improves the postoperative life quality and survival rate of patients. Thoracoscopic anatomical segmentectomy is safe and feasible, and its therapeutic effect has been basically confirmed.

[0100] In one example, lung segmentectomy requires the doctor to accurately understand the distribution of the trachea, blood vessels and lung segments in the patient's lung. The division of lung segments is determined based on the distribution of the trachea and blood vessels. However, in the prior art, due to the invasion of the tumor in the lung, the trachea and blood vessels will be changed, or part of the patient's lung fissure is underdeveloped or completely undeveloped. If the distribution of the trachea, blood vessels and lung segments in the patient's lung is determined according to the conventional segmentation method, the distribution will be inaccurate, and the lung segmentectomy may damage the main artery and other tissues, thereby increasing the risk index of the operation.

[0101] Specifically, 1. Pulmonary anatomy

[0102] The pulmonary anatomy of a patient that is discernible in a medical image includes the pulmonary airways, pulmonary veins, and pulmonary arteries, each of which forms a tree-like system or network within each lung. Veins and arteries can be more generally referred to as blood vessels or vessels.

[0103] Each lung is composed of multiple lobes. Each lobe has its own independent and distinct sub-tree of each of the three branching systems (airways, veins, and arteries). The pulmonary arteries, veins, and airways do not cross the boundaries of the lobes. The lobes are separated by fissures that are discernible in some medical images. In some special cases, such as when the pulmonary fissure is underdeveloped or not developed, the fissure can also not exist. The lung tissue that is not a blood vessel or airway is referred to as the lung parenchyma.

[0104] In human anatomy, the left lung is smaller than the right lung and is divided into two lobes: the upper lobe and the lower lobe. The right lung is composed of three lobes: the upper, middle, and lower. Each lobe can be further subdivided into pulmonary segments, similar to the lobes, each of which also has independent branching of blood supply and bronchus. Similar to the lobes, a subsegment within a lobe can be resected, leaving the other segments as functional units of the lung. However, unlike the lobes, the segments are not separated by fissures. In rare cases, a "minor" fissure is visible in medical images and divides the boundaries of two segments within a lobe. In this application, the common case is taken as an example for introduction and description, i.e., there is no minor fissure in the medical image being processed. In the left lung, each lobe contains four segments, for a total of eight segments in the lung. In the right lung, there are a total of ten segments, five of which are in the lower lobe (four of which are called basal segments), two of which are in the middle lobe, and three of which are in the upper lobe.

[0105] In medical imaging, the identification of lung segments is much more difficult than the identification of lung lobes. Unlike lung lobes, lung segments are not separated by visible fissures. Without this visual cue, the physician must identify the lung segments based on his understanding of the blood vessels and bronchi that define the lung segments. Specifically, one definition of the region of a lung segment is that it corresponds to the region of a branch of the pulmonary artery and a branch of the bronchus. Every part of the lung parenchyma tissue other than the blood vessels, bronchi belongs to a segment, which means that it is also included by the segment a branch of the bronchus + and a branch of the pulmonary artery fed. Just as the sub-trees of the pulmonary artery and bronchus are distinct and independent between different lung lobes, within a lung lobe, the intra-segmental pulmonary artery and intra-segmental bronchus sub-trees of one lung segment are also distinct and independent from the intra-segmental pulmonary artery and intra-segmental bronchus sub-trees of other segments. Some veins can reside entirely within a segment (called intrasegmental veins), and some veins pass along portions of the boundaries between lung segments (called intersegmental veins) + variations + compression. However, there is considerable variation between people in the structure and branching of the vessels at the segment level, which makes the identification of segments complicated because the identification must take into account the possible variations in human vascular anatomy.

[0106] 2. Lung cancer surgery

[0107] Surgery performed by a surgeon will have different names depending on the nature and number of lung portions that are resected.

[0108] Lobectomy is the removal of an entire lung.

[0109] Lobectomy is the removal of an entire lung.

[0110] Lobectomy is the removal of an entire lung.

[0111] Wedge resection refers to the removal of a triangular portion of the lung, which is not defined by a lobe or a segment, as opposed to segmentectomy, wedge resection is a "non-anatomical" resection, as the resection line does not follow the anatomical boundaries. Wedge resection is not the most popular approach due to oncological and / or functional reasons. Wedge resection is typically performed in cases where segmentectomy cannot be performed for some reason.

[0112] 3. Use of medical imaging in surgical planning

[0113] When deciding on a surgical approach, the surgeon will rely mainly on the patient's medical images, such as CT scans, MRI and / or PET scans. Among other things, the surgeon will consider the location of the lesion. In considering the location, the surgeon first identifies the relevant lobe and / or segment, identifying the relevant lobe is a prerequisite for performing a lobectomy, and identifying the relevant segment is a prerequisite for performing a segmentectomy.

[0114] In addition to viewing the patient's CT scans and other medical images, the surgeon can also view 3D reconstructions of such images. Currently, 3D reconstructions of the lungs will typically include a visual depiction of the lobes as defined by fissures, but lack a visual depiction of the segments.

[0115] While it would be very helpful for the surgeon to have a visual depiction of the segments within the 3D reconstruction, this is very difficult to achieve due to the wide variation in human segmental anatomy.

[0116] The present application provides a lung recognition processing method, device and server, which aims to solve the above technical problems of the prior art.

[0117] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0118] Figure 1 A flowchart of a lung recognition processing method provided by an embodiment of the present application is shown in Figure 1 The method comprises:

[0119] Step 101, obtaining a model recognition instruction, wherein the model recognition instruction comprises a lung model identifier, and determining a lung model corresponding to the lung model identifier, the lung model comprising a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model.

[0120] Exemplarily, the execution subject of the embodiment can be a server. First, the server acquires a model identification instruction. Specifically, a user clicks a start identification button on a display screen corresponding to the server to trigger generation of the model identification instruction, the server acquires the model identification instruction, or the server receives a model identification instruction sent by another server, etc., wherein the model identification instruction comprises a lung model identifier. The server determines a lung model corresponding to the lung model identifier according to the lung model identifier in the model acquisition instruction, the lung model comprises a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model, the lung parenchyma model refers to lung tissue in the lung model except for blood vessels and airways, and the trachea model, the pulmonary vein model and the pulmonary artery model are all inserted in the lung parenchyma model.

[0121] Step 102, determining a plurality of initial segmentation cross sections of the lung parenchyma model based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model; wherein the initial segmentation cross sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of an intra-segment trachea, an intra-segment vein and an intra-segment artery.

[0122] Exemplarily, the plurality of initial segmentation cross sections of the lung parenchyma model can be determined based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, and the plurality of initial segmentation cross sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of an intra-segment trachea, an intra-segment vein and an intra-segment artery.

[0123] Step 103, generating a plurality of target segmentation cross sections of the lung parenchyma model according to growth information of at least one of the intra-segment trachea, the intra-segment vein and the intra-segment artery in each initial lung segment; wherein the target segmentation cross sections divide the lung parenchyma model into a plurality of target lung segments, and each target lung segment comprises distribution information of at least one of the intra-segment trachea, the intra-segment vein and the intra-segment artery.

[0124] Exemplarily, the server can determine growth information of at least one of the intra-segment trachea, the intra-segment vein and the intra-segment artery in each initial lung segment, and generate a plurality of target segmentation cross sections of the lung parenchyma model according to the growth information of at least one of the intra-segment trachea, the intra-segment vein and the intra-segment artery in each initial lung segment, wherein the target segmentation cross sections divide the lung parenchyma model into a plurality of target lung segments, and the target lung segment comprises distribution information of at least one of the intra-segment trachea, the intra-segment vein and the intra-segment artery, and the distribution information refers to actual growth information of the intra-segment trachea, the intra-segment vein and the intra-segment artery in the lung segment, for example, the distribution information comprises position information and volume information, etc.

[0125] In this embodiment, a model recognition instruction is obtained, which includes a lung model identifier and determines the lung model corresponding to the lung model identifier. The lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model. Based on the growth information of at least one of the trachea model, pulmonary vein model, and pulmonary artery model, multiple initial segmented sections of the lung parenchyma model are determined. Each initial segmented section divides the lung parenchyma model into multiple initial lung segments, and each initial lung segment includes at least one of an intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Based on at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, multiple target segmented sections of the lung parenchyma model are generated. Each target segmented section divides the lung parenchyma model into multiple target lung segments, and each target lung segment includes distribution information of at least one of an intrasegmental trachea, intrasegmental vein, and intrasegmental artery. In this scheme, the lung model corresponding to the lung model identifier is determined according to the model recognition instruction in the model recognition instruction. The lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model. Then, based on any one or more of the tracheal model, pulmonary vein model, and pulmonary artery model, multiple initial segmental sections of the lung parenchyma model are determined. These initial segmental sections divide the lung parenchyma model into multiple initial lung segments, each including at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Based on the growth information of any one or more of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, multiple target segmental sections of the lung parenchyma model are generated. These target segmental sections divide the lung parenchyma model into multiple target lung segments, each including the distribution information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery. Therefore, based on the target segmental sections of the reconstructed lung model, the distribution information of each lung segment can be obtained, thereby helping to improve the accuracy of surgical planning, reduce the surgical risk index, increase the surgical success rate, and solve the technical problem of the difficulty in identifying the distribution of trachea, blood vessels, and lung segments within the lung.

[0126] For example, Figure 2 This is a schematic diagram of the first state of a lung model provided in an embodiment of this application. Figure 3 This application provides a schematic diagram of the structure of a lung model in its second state, as shown in the embodiments of the present application. Figure 2 and Figure 3 Each includes multiple target segment sections. Figure 2 The first state is when the lung parenchyma is opaque. Figure 3 The second state is a transparent state of the lung parenchyma. Specifically, Figure 2 , Figure 3 And the following attached figures Figures 5-10Includes: S1-S10 are all lung segments, specifically: S1 - apical segment, S2 - posterior segment, S3 - anterior segment, S4 - lateral segment, S5 - medial segment, S6 - dorsal segment, S7 - medial basal segment, S8 - anterior basal segment, S9 - lateral basal segment, S10 - posterior basal segment, L - lung parenchyma, B - trachea, B1 - apical trachea, B2 - posterior trachea, B3 - anterior trachea, B4 - lateral trachea, B5 - medial trachea, B6 - dorsal trachea, B7 - medial basal trachea, B8 - anterior basal trachea, B9 - lateral basal trachea, B10 - posterior basal trachea, V - pulmonary vein, V1 - apical pulmonary vein, V... 2 - Posterior pulmonary vein, V3 - Anterior pulmonary vein, V4 - Lateral pulmonary vein, V5 - Medial pulmonary vein, V6 - Dorsal pulmonary vein, V7 - Medial basal pulmonary vein, V8 - Anterior basal pulmonary vein, V9 - Lateral basal pulmonary vein, V10 - Posterior basal pulmonary vein, A - Pulmonary artery, A1 - Apical pulmonary artery, A2 - Posterior pulmonary artery, A3 - Anterior pulmonary artery, A4 - Lateral pulmonary artery, A5 - Medial pulmonary artery, A6 - Dorsal pulmonary artery, A7 - Medial basal pulmonary artery, A8 - Anterior basal pulmonary artery, A9 - Lateral basal pulmonary artery, A10 - Posterior basal pulmonary artery, P - Target segment section. Figure 4 A schematic flowchart of another lung recognition processing method provided in this application embodiment is shown below. Figure 4 As shown, the method includes:

[0127] Step 201: Obtain model recognition instructions, wherein the model recognition instructions include lung model identifiers and determine the lung models corresponding to the lung model identifiers. The lung models include lung parenchyma models, trachea models, pulmonary vein models, and pulmonary artery models.

[0128] For example, this step can be referred to Figure 1 Step 101 in the text will not be repeated here.

[0129] Step 202: Based on at least one of the tracheal model, pulmonary vein model, and pulmonary artery model, determine multiple initial segment sections of the lung parenchyma model; wherein, the initial segment sections divide the lung parenchyma model into multiple initial lung segments, and each initial lung segment includes at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery.

[0130] Step 202 includes two implementation methods:

[0131] The first implementation of step 202 is as follows: obtain intersegmental veins based on the pulmonary vein model; wherein, intersegmental veins are veins located between lung segments; determine multiple initial segmental sections of the lung parenchyma model based on the intersegmental veins.

[0132] The method for determining the plurality of initial segment cross sections of the lung parenchyma model according to the intersegmental vein comprises: obtaining a trachea grading result based on a trachea model, and / or obtaining a pulmonary artery grading result based on a pulmonary artery model; wherein the trachea grading result is determined according to preset trachea naming rule information, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rule information; and determining the plurality of initial segment cross sections of the lung parenchyma model based on any one or two of the intersegmental vein, the trachea grading result and the pulmonary artery grading result.

[0133] The second implementation of step 202: obtaining a trachea grading result based on a trachea model, and / or obtaining a pulmonary artery grading result based on a pulmonary artery model; wherein the trachea grading result is determined according to preset trachea naming rule information, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rule information; and determining the plurality of initial segment cross sections of the lung parenchyma model based on the trachea grading result and / or the pulmonary artery grading result.

[0134] Exemplarily, the plurality of initial segment cross sections of the lung parenchyma model can be determined based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, and the initial segment cross sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of a segmental trachea, a segmental vein and a segmental artery.

[0135] When the initial segment cross section is determined based on the pulmonary vein model, the server first obtains the intersegmental vein based on the pulmonary vein model, and determines the initial segment cross section based on the intersegmental vein. Specifically, Figure 5 A scene schematic diagram of another lung recognition processing method provided by the embodiment of the present application is as follows: Figure 5As shown, the veins of the right superior lobe converge into an apical segment vein VI, a posterior segment vein V2, and an anterior segment vein V3. The apical segment vein VI includes an apical branch and an anterior branch, where the anterior branch is an intersegmental branch. The posterior segment vein V2 includes a central portion and an interlobar portion. The central portion includes an apical branch, a posterior branch, and an anterior branch, where the apical branch is an intersegmental branch. The interlobar portion includes a distal branch, which is located at the interlobar side. The anterior segment vein V3 includes an upper branch and a lower branch, where the upper branch is an intersegmental branch. The veins of the right middle lobe converge into a lateral segment vein V4 and a medial segment vein V5, which converge into a right superior pulmonary vein that, after exiting the hilum, drains into the left atrium. The veins of the right middle lobe are more complex than the bronchi and arteries, and the branching of the lateral segment bronchus B4 and the medial segment bronchus B5 often varies. Typically, the parent branch of V4 is located at the intersegmental position, and in a few cases, the parent branch of V5 is located at the intersegmental position. The veins of the dorsal segment of the right inferior lobe and the surrounding veins converge into a dorsal segment vein V6, which includes a medial branch, an upper branch, and a lateral branch, where the medial branch and the lateral branch are intersegmental branches. Each basal segment first converges into an inner basal segment vein V7, an anterior basal segment vein V8, an outer basal segment vein V9, and a posterior basal segment vein V10. The anterior basal segment vein V8 and the outer basal segment vein V9 converge into an upper basal segment vein, the posterior basal segment vein V10 continues as a lower basal segment vein, and the inner basal segment vein V7, which is relatively thin, can drain into the upper basal segment vein or the lower basal segment vein, or into the common basal segment vein formed by the convergence of the upper basal segment vein and the lower basal segment vein. The dorsal segment vein and the common basal segment vein finally converge into a right inferior pulmonary vein that, after exiting the hilum, drains into the left atrium. The inner basal segment vein V7 includes an anterior branch and a medial branch. The anterior basal segment vein V8 includes a lateral branch and a basal branch, where the basal branch is an intersegmental branch. The outer basal segment vein V9 includes a lateral branch and a basal branch, where the basal branch is an intersegmental branch. The posterior basal segment vein V10 includes a posterior branch, a lateral basal branch, and a medial basal branch. As indicated above, the intersegmental branches are intersegmental veins, and a plurality of initial segmental cross-sections are created according to the intersegmental veins, which extend along the growth direction of the intersegmental veins.

[0136] In the process of determining the initial segmentation cross section based on the trachea model, the server first obtains a trachea classification result based on the trachea model, and determines the initial segmentation cross section based on the trachea classification result, wherein the trachea classification result is determined according to preset trachea naming rule information, and the trachea naming rule information can refer to naming and marking the trachea according to the growth direction of the trachea and / or the branching order of the trachea. Specifically, the first main trachea is located above the hilum, and the second trachea is called the leaf trachea after entering the hilum, wherein the left lung has 2 leaf tracheas, the right lung has 3 leaf tracheas, the third trachea is called the segment trachea, the left lung has 8 segment tracheas, and the right lung has 10 segment tracheas. The segment trachea can also be divided into the fourth trachea-small trachea, the fifth trachea-fine trachea, and the sixth trachea-terminal fine trachea. In this embodiment, the fine trachea and the terminal fine trachea are difficult to reconstruct according to the image data, and therefore the reconstruction of the trachea by the three-dimensional model only includes the segment trachea and its branches (small trachea) that can be used to determine the lung segmentation. This embodiment takes the right lung as an example for description, Figure 6 The scene diagram of another lung recognition processing method provided by the embodiment of the present application is shown in FIG. 6, Figure 6 As shown in FIG. 6, the right lung trachea includes the tip segment trachea B1, the rear segment trachea B2, the front segment trachea B3, the outer side segment trachea B4, the inner side segment trachea B5, the back segment trachea B6, the inner base segment trachea B7, the front base segment trachea B8, the outer base segment trachea B9, and the rear base segment trachea B10 corresponding to the tip segment S1, the rear segment S2, the front segment S3, the outer side segment S4, the inner side segment S5, the back segment S6, the inner base segment S7, the front base segment S8, the outer base segment S9, and the rear base segment S10 respectively. According to the trachea classification result, a plurality of initial segmentation cross sections are created, the initial segmentation cross sections do not contact the segment tracheas, and the segment tracheas are located in independent regions respectively. In some embodiments, the initial segmentation cross section can be an equidistant surface created between adjacent segment tracheas.

[0137] In the process of determining the initial segmentation cross section based on the pulmonary artery model, the server first obtains a pulmonary artery classification result based on the pulmonary artery model, and determines the initial segmentation cross section based on the pulmonary artery classification result, wherein the pulmonary artery classification result is determined according to preset pulmonary artery naming rule information, and the pulmonary artery naming rule information can refer to naming and marking the pulmonary artery according to the growth direction of the pulmonary artery and / or the branching order of the pulmonary artery. Specifically, Figure 7 The scene diagram of another lung recognition processing method provided by the embodiment of the present application is shown in FIG. 6, Figure 7As shown, the right superior lobar artery ascends along the anteromedial aspect of the superior lobar bronchus, accompanying the lobar bronchus and its branches; the superior lobar artery divides into three branches, which are segmental arteries: the apical segmental artery A1 ascends along the anteromedial aspect of the apical segmental bronchus B1; the anterior segmental artery A3 ascends along the anteromedial aspect of the anterior segmental bronchus B3, and then runs forward and laterally; the posterior segmental artery A2 ascends along the anteromedial aspect of the posterior segmental bronchus B2, and then runs backward and laterally, and distributes in the corresponding lung segments; the ascending artery is emitted from the proximal end of the interlobar artery, runs along the upper part of the oblique fissure, and then enters the posterior segment of the right lung; the interlobar artery spirally runs around the intermediate bronchus, and then is emitted from the anterior wall of the intermediate bronchus; the right middle lobar artery is emitted from the interlobar artery, and its starting point is usually located at the anterolateral superior of the intermediate bronchus; the middle lobar artery divides into two branches: the lateral segmental artery A4 runs along the lateral aspect of the lateral segmental bronchus B4, and distributes in the lateral segment of the right middle lobe; the medial segmental artery A5 obliquely runs forward and laterally along the lateral aspect of the medial segmental bronchus B5, and distributes in the medial segment of the right middle lobe; the right inferior lobar artery is the direct continuation of the interlobar fissure artery, and is emitted from the posterior segmental artery A6, which distributes in the posterior segment of the right lung; the trunk continues to descend and then turns to the posterior and lateral aspect of the bronchus, and is called the basal trunk; the basal trunk is radially divided into the medial basal segmental artery A7, the anterior basal segmental artery A8, the lateral basal segmental artery A9, and the posterior basal segmental artery A10, which accompany the medial basal segmental bronchus B7, the anterior basal segmental bronchus B8, the lateral basal segmental bronchus B9, and the posterior basal segmental bronchus B10, respectively, and distribute in the corresponding lung segments. According to the results of the pulmonary artery classification, a plurality of initial segmentation sections are created, which do not contact the pulmonary segmental arteries and make the pulmonary segmental arteries located in independent regions. In some embodiments, the initial segmentation section can be an equidistant plane created between adjacent pulmonary segmental arteries.

[0138] In the first implementation of determining the initial segmentation section, since the plurality of initial segmentation sections of the lung parenchyma model can be determined based on at least one of the bronchial model, the pulmonary vein model, and the pulmonary artery model, in this step, the server acquires the intersegmental vein according to the pulmonary vein model, and determines the plurality of initial segmentation sections of the lung parenchyma model according to the intersegmental vein. Further, in order to make the initial lung segments in the initial segmentation section more accurate, the bronchial classification results can also be acquired based on the bronchial model, and / or the pulmonary artery classification results can also be acquired based on the pulmonary artery model, and the plurality of initial segmentation sections of the lung parenchyma model are determined based on any one or both of the intersegmental vein, the bronchial classification results, and the pulmonary artery classification results. The processes of determining the initial segmentation section based on the bronchial model, determining the initial segmentation section based on the pulmonary vein model, and determining the initial segmentation section based on the pulmonary artery model are described above, and will not be described here.

[0139] In the second implementation of determining the initial segmentation section, the server obtains a trachea classification result based on the trachea model, and determines the plurality of initial segmentation sections of the lung parenchyma model based on the trachea classification result. Alternatively, a pulmonary artery classification result is obtained based on the pulmonary artery model, and the plurality of initial segmentation sections of the lung parenchyma model are determined based on the pulmonary artery classification result. Alternatively, a trachea classification result is obtained based on the trachea model, and a pulmonary artery classification result is obtained based on the pulmonary artery model, and the plurality of initial segmentation sections of the lung parenchyma model are determined based on the trachea classification result and the pulmonary artery classification result. Details of the process of determining the initial segmentation section based on the trachea model, determining the initial segmentation section based on the pulmonary vein model, and determining the initial segmentation section based on the pulmonary artery model are described above and will not be repeated here.

[0140] It should be understood that, in the lung model reconstruction process, because the blood vessels and trachea of each person are different, the identification marks corresponding to the same initial segmentation section can be different, and therefore different initial segmentation sections can be created in different ways as indicated above. Alternatively, because the identification marks of different initial segmentation sections can be different, all initial segmentation sections of the entire lung parenchyma model can not be determined according to one type of anatomical structure in the above embodiments. Alternatively, due to variations in trachea and / or blood vessels, the initial segmentation section determined according to one type of anatomical structure cannot divide the trachea of the same name and / or the artery of the same name into independent regions, and therefore one or more types of anatomical structures in the above embodiments can be combined to determine the initial segmentation section, for example, the initial segmentation section is determined based on the trachea classification result of the trachea model and the pulmonary artery classification result of the pulmonary artery model; or the initial segmentation section is determined based on the trachea classification result of the trachea model and the intersegmental vein; or the initial segmentation section is determined based on the pulmonary artery classification result of the pulmonary artery model and the intersegmental vein; or the initial segmentation section is determined based on the trachea classification result of the trachea model, the pulmonary artery classification result of the pulmonary artery, and the intersegmental vein.

[0141] For example, Figure 8 A scene schematic diagram of another lung identification processing method provided by the embodiments of the present application is as follows, Figure 8As shown, for the lateral segment S4 and the medial segment S5, when the lateral segment artery A4, the lateral segment vein V4, the lateral segment bronchus B4 in the lateral segment S4 and the medial segment artery A5, the medial segment vein V5 and the medial segment bronchus B5 in the medial segment S5 are not varied, the intersegmental branch of the lateral segment vein V4 can be used as the identification mark of the segmental section, that is, the initial segmental section P between the lateral segment S4 and the medial segment S5 is created along the direction of the intersegmental branch of the lateral segment vein V4, so that the lateral segment bronchus B4 is located in the lateral segment S4 and the medial segment bronchus B5 is located in the medial segment S5, that is, the initial segmental section is determined based on the pulmonary vein model; if the medial segment bronchus B5 in the medial segment S5 is varied, one branch of the medial segment bronchus B5 is not common with other branches and grows close to the lateral segment bronchus B4, and the intersegmental branch of the lateral segment vein V4 in the lateral segment S4 is also varied and grows close to the lateral segment bronchus B4, when the initial segmental section is directly created through the “intersegmental branch” of the lateral segment vein V4, part of the lateral segment bronchus B4 is divided into the medial segment S5, therefore, the initial segmental section created in this way is unreasonable, and the initial segmental section needs to be adjusted in combination with the distribution of the lateral segment bronchus B4 and the medial segment bronchus B5 so that the lateral segment bronchus B4 is located in the lateral segment S4 and the medial segment bronchus B5 is located in the medial segment S5, that is, the initial segmental section is determined based on the bronchus model and the pulmonary vein model.

[0142] For example, Figure 9 Another lung recognition processing method provided by the embodiment of the present application is shown in the scene schematic diagram of FIG. 6. Figure 9 As shown, for the posterior segment S2 and the dorsal segment S6, under normal circumstances, the posterior segment S2 and the dorsal segment S6 are separated by the pulmonary fissure, and the initial segmental section can be created along the extension direction of the pulmonary fissure, but for patients with underdeveloped or no developed pulmonary fissure, the initial segmental section can be created in combination with the bronchus model, the pulmonary artery model and the pulmonary vein model, and the initial segmental section does not pass through the posterior segment bronchus B2, the dorsal segment bronchus B6, the posterior segment artery A2, the dorsal segment artery A6, the posterior segment vein V2 and the dorsal segment vein V6.

[0143] Step 203, determining at least one of the intrasegment bronchus, the intrasegment vein and the intrasegment artery of each initial lung segment.

[0144] In one example, step 203 includes: obtaining a bronchus classification result based on the bronchus model, and determining the intrasegment bronchus of each initial lung segment in the initial segmental section based on the bronchus classification result; and / or, obtaining a pulmonary vein classification result based on the pulmonary vein model, and determining the intrasegment vein of each initial lung segment in the initial segmental section based on the pulmonary vein classification result; and / or, obtaining a pulmonary artery classification result based on the pulmonary artery model, and determining the intrasegment artery of each initial lung segment in the initial segmental section based on the pulmonary artery classification result.

[0145] Exemplarily, the initial segmenting section divides the lung parenchyma model into a plurality of initial lung segments, each of which includes at least one of an intrasegmental bronchus, an intrasegmental vein and an intrasegmental artery, and the server can determine the at least one of the intrasegmental bronchus, the intrasegmental vein and the intrasegmental artery in each of the initial lung segments. Specifically, when determining the intrasegmental bronchus in each of the initial lung segments, a bronchial grading result is obtained based on the bronchial model, and the intrasegmental bronchus of each of the initial lung segments in the initial segmenting section is determined based on the bronchial grading result; when determining the intrasegmental vein in each of the initial lung segments, a pulmonary vein grading result is obtained based on the pulmonary vein model, and the intrasegmental vein of each of the initial lung segments in the initial segmenting section is determined based on the pulmonary vein grading result; and when determining the intrasegmental artery in each of the initial lung segments, a pulmonary artery grading result is obtained based on the pulmonary artery model, and the intrasegmental artery of each of the initial lung segments in the initial segmenting section is determined based on the pulmonary artery grading result. If any two or three of the intrasegmental bronchus, the intrasegmental vein and the intrasegmental artery in each of the initial lung segments are determined, the processes of determining the intrasegmental bronchus, the intrasegmental vein and the intrasegmental artery are described above and will not be repeated here.

[0146] The grading principles and grading results of the right lung bronchus, the right lung artery and the right lung vein can be referred to the above, and will not be repeated here.

[0147] Step 204, determining growth information of at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments.

[0148] Exemplarily, the server determines the growth information of the intrasegmental vein in each of the initial lung segments, and / or determines the growth information of the intrasegmental artery.

[0149] Step 205, determining whether at least one of the intrasegmental vein and the intrasegmental artery has a preset abnormality according to the growth information of at least one of the intrasegmental vein and the intrasegmental artery in each of the initial lung segments.

[0150] In one example, step 205 includes: determining whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each of the initial lung segments; and / or determining whether the intrasegmental artery grows across segments according to the growth information of the intrasegmental artery in each of the initial lung segments; if it is determined that the intrasegmental vein grows across segments, it is determined that the intrasegmental vein has a preset abnormality; and / or if it is determined that the intrasegmental artery grows across segments, it is determined that the intrasegmental artery has a preset abnormality.

[0151] In one example, determining whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each initial lung segment comprises: determining whether a first distance between the intrasegmental vein and a first adjacent vessel is greater than a vein threshold according to the growth information of the intrasegmental vein in each initial lung segment; wherein the first adjacent vessel comprises an intrasegmental vein and / or an intrasegmental artery adjacent to the intrasegmental vein; if it is determined that the first distance is less than the vein threshold, it is determined that the intrasegmental vein grows across segments; if it is determined that the first distance is greater than the vein threshold, it is determined that the intrasegmental vein does not grow across segments.

[0152] In one example, determining whether the intrasegmental artery grows across segments according to the growth information of the intrasegmental artery in each initial lung segment comprises: determining whether a second distance between the intrasegmental artery and a second adjacent vessel is greater than an artery threshold according to the growth information of the intrasegmental artery in each initial lung segment; wherein the second adjacent vessel comprises an intrasegmental artery and / or an intrasegmental vein adjacent to the intrasegmental artery; if it is determined that the second distance is less than the artery threshold, it is determined that the intrasegmental artery grows across segments; if it is determined that the second distance is greater than the artery threshold, it is determined that the intrasegmental artery does not grow across segments.

[0153] In one example, determining whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each initial lung segment comprises: determining whether a first distance between the intrasegmental vein and a first adjacent vessel is greater than a vein threshold according to the growth information of the intrasegmental vein in each initial lung segment; wherein the first adjacent vessel comprises an intrasegmental vein and / or an intrasegmental artery adjacent to the intrasegmental vein; if it is determined that the first distance is less than the vein threshold, it is determined that the intrasegmental vein grows across segments; if it is determined that the first distance is greater than the vein threshold, it is determined that the intrasegmental vein does not grow across segments.

[0154] In one example, determining whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each initial lung segment comprises: determining whether a first distance between the intrasegmental vein and a first adjacent vessel is greater than a vein threshold according to the growth information of the intrasegmental vein in each initial lung segment; wherein the first adjacent vessel comprises an intrasegmental vein and / or an intrasegmental artery adjacent to the intrasegmental vein; if it is determined that the first distance is less than the vein threshold, it is determined that the intrasegmental vein grows across segments; if it is determined that the first distance is greater than the vein threshold, it is determined that the intrasegmental vein does not grow across segments.

[0155] To determine whether an intrasegmental artery has grown across segments, a second distance is determined between the intrasegmental artery and a second adjacent vessel based on growth information within each initial lung segment. This second distance is then assessed to determine if it exceeds an arterial threshold. The second adjacent vessel includes intrasegmental arteries and / or intrasegmental veins adjacent to the intrasegmental artery. If the second distance is determined to be less than the arterial threshold, cross-segmental growth of the intrasegmental artery is confirmed. If the second distance is determined to be greater than the arterial threshold, cross-segmental growth of the intrasegmental artery is confirmed not to occur.

[0156] Both the venous threshold and the arterial threshold can be 0. Specifically, the vessels of the first initial lung segment can be projected onto the vessels of the second initial lung segment. If the projection lines of the vessels of the first and second initial lung segments overlap, i.e., the distance between the vessels of the first and second initial lung segments is less than 0, then it is determined that the vessels within the segment are growing across segments. If the projection lines of the vessels of the first and second initial lung segments do not overlap, i.e., the distance between the vessels of the first and second initial lung segments is greater than 0, then it is determined that the vessels within the segment are not growing across segments. Vessels within a segment can refer to intrasegmental veins and / or intrasegmental arteries. In this embodiment, only the vessel segments closest to the initial segment cross-section can be analyzed to determine whether vessels are growing across segments.

[0157] For example, Figure 10 This is a schematic diagram illustrating a scenario for another lung recognition processing method provided in an embodiment of this application, as shown below. Figure 10 As shown, the medial basal pulmonary artery A7, medial basal pulmonary vein V7, and posterior basal pulmonary artery A10 and posterior basal pulmonary vein V10 grow interlaced, meaning the distance between the medial basal pulmonary artery A7 and the posterior basal pulmonary artery A10 and posterior basal pulmonary vein V10 is less than the arterial threshold. Alternatively, the distance between the medial basal pulmonary vein V7 and the posterior basal pulmonary artery A10 and posterior basal pulmonary vein V10 is less than the venous threshold. In this case, it can be determined that one or more of the medial basal pulmonary artery A7, medial basal pulmonary vein V7, and posterior basal pulmonary artery A10 and posterior basal pulmonary vein V10 grow across segments. In this case, the target segmented cross section between the medial basal segment S7 and the posterior basal segment S10 can be determined using the first rule information; that is, this target segmented cross section passes through one or more of the medial basal pulmonary artery A7, medial basal pulmonary vein V7, and posterior basal pulmonary artery A10 and posterior basal pulmonary vein V10. (Continue to refer to...) Figure 9, the posterior pulmonary vein V2, the posterior pulmonary artery A2 and the dorsal pulmonary vein V6, the dorsal pulmonary artery A6 do not exist staggered growth, that is, the distance between the posterior pulmonary vein V2, the posterior pulmonary artery A2 and the dorsal pulmonary vein V6, the dorsal pulmonary artery A6 is greater than the arterial threshold value, at this time, it can be judged that the posterior pulmonary vein V2, the posterior pulmonary artery A2 and the dorsal pulmonary vein V6, the dorsal pulmonary artery A6 do not have cross-segment growth, at this time, the target segmentation section between the posterior segment S2 and the dorsal segment S6 can be determined according to the second rule information, that is, the target segmentation section does not pass through any one of the posterior pulmonary vein V2, the posterior pulmonary artery A2 and the dorsal pulmonary vein V6, the dorsal pulmonary artery A6.

[0158] In another embodiment, some lung models may have a lung fissure fusion, and the intrasegmental artery and / or intrasegmental vein may have cross-segment growth at the position of the lung fissure fusion, at this time, the shape of the lung fissure when the lung fissure fusion does not occur can be predicted according to the lung fissure shape, and whether the intrasegmental artery and / or intrasegmental vein has cross-segment growth can be determined according to the predicted lung fissure shape, that is, when the intrasegmental artery and / or intrasegmental vein passes through the predicted lung fissure, it is determined that the intrasegmental artery and / or intrasegmental vein has cross-segment growth, and when the intrasegmental artery and / or intrasegmental vein does not pass through the predicted lung fissure, it is determined that the intrasegmental artery and / or intrasegmental vein does not have cross-segment growth.

[0159] Normally, the same-named intrasegmental bronchus, the same-named intrasegmental artery and the same-named intrasegmental vein are located in the same-named lung segment. When the intrasegmental artery and / or intrasegmental vein has cross-segment growth, the same-named intrasegmental artery and the same-named intrasegmental vein may have cross-segment growth, that is, the target segmentation section passes through at least part of the intrasegmental artery and / or intrasegmental vein.

[0160] Therefore, by determining whether the pulmonary artery and / or the pulmonary vein have cross-segment growth, and selecting different rule information to determine the target segmentation section according to the cross-segment growth and non-cross-segment growth of the blood vessels, the problem that the target segmentation section created is inaccurate in order to make each intrasegmental artery and / or intrasegmental vein different and independent from other intrasegmental arteries and / or intrasegmental veins under abnormal blood vessel conditions can be avoided, thereby helping to improve the accuracy of the surgical plan, reduce the surgical risk index, and improve the success rate of surgery.

[0161] Specifically, when the intersegmental artery and / or the intersegmental vein has a cross-segment growth, and the target segmental cross-section in the reconstructed lung model still wraps the corresponding lung segment, the doctor determines the surgical plan based on the three-dimensional model, which can cause the doctor to take the cross-segment growth blood vessel as a reference when searching for the target segmental cross-section of the lung segment during the operation, that is, to cut the cross-segment growth intersegmental artery and / or vein completely in order to cut the lung segment completely, thereby causing damage to the tissues of other lung segments. Moreover, the inaccurate target segmental cross-section creates a lung model that does not match the actual segmentation of the lung, which can cause the position information and volume information of each lung segment obtained based on the lung model to be inaccurate, and the surgical path determined based on the lung model to be determined to be not applicable to the actual situation, thereby causing a higher risk index of the operation.

[0162] In step 206, if it is determined that at least one of the intersegmental artery and the intersegmental vein has a preset abnormality, a plurality of target segmental cross-sections of the lung parenchymal model are generated based on preset first rule information. The preset first rule information is used to indicate that at least a part of the intersegmental artery in the initial lung segment passes through a target segmental cross-section corresponding to a target lung segment where the intersegmental artery is located, and / or at least a part of the intersegmental vein passes through a target segmental cross-section corresponding to a target lung segment where the intersegmental vein is located.

[0163] For example, the preset first rule information is pre-stored information. The first rule information is used to indicate that at least a part of the intersegmental artery in the initial lung segment passes through a target segmental cross-section corresponding to a target lung segment where the intersegmental artery is located, and / or at least a part of the intersegmental vein passes through a target segmental cross-section corresponding to a target lung segment where the intersegmental vein is located. If the server determines that the intersegmental artery has a preset abnormality, the target segmental cross-section of the lung parenchymal model is generated based on the preset first rule information, at this time, the target segmental cross-section has been passed through by the intersegmental artery in the target lung segment; or if the server determines that the intersegmental vein has a preset abnormality, the target segmental cross-section of the lung parenchymal model is generated based on the preset first rule information, at this time, the target segmental cross-section has been passed through by the intersegmental vein in the target lung segment; or if the server determines that the intersegmental vein has a preset abnormality and the intersegmental artery has a preset abnormality, the target segmental cross-section of the lung parenchymal model is generated based on the preset first rule information, at this time, the target segmental cross-section has been passed through by the intersegmental artery in the target lung segment and has been passed through by the intersegmental vein in the target lung segment.

[0164] In step 207, if it is determined that neither the intersegmental artery nor the intersegmental vein has a preset abnormality, a target segmental cross-section of the lung parenchymal model is generated based on preset second rule information. The preset second rule information is used to indicate that the intersegmental artery in the initial lung segment does not pass through a target segmental cross-section corresponding to a target lung segment where the intersegmental artery is located, and the intersegmental vein does not pass through a target segmental cross-section corresponding to a target lung segment where the intersegmental vein is located.

[0165] Exemplarily, the preset second rule information is pre-stored information, and the second rule information is used to indicate that the intrasegmental artery in the initial segmented cross section does not pass through the target segmented cross section corresponding to the target lung segment where the intrasegmental artery is located, and the intrasegmental vein does not pass through the target segmented cross section corresponding to the target lung segment where the intrasegmental vein is located. If the server determines that neither the intrasegmental artery nor the intrasegmental vein has the preset abnormality, the initial segmented cross section is determined as the target segmented cross section of the lung parenchyma model based on the preset second rule information. At this time, the target segmented cross section is not passed through by the intrasegmental artery in the target lung segment and is not passed through by the intrasegmental vein in the target lung segment.

[0166] In step 208, prompt information is sent, and the prompt information is used to indicate the target lung segment with the preset abnormality in the target segmented cross section.

[0167] Exemplarily, the server can send prompt information, and the prompt information is used to prompt the user about the target lung segment with the preset abnormality in the target segmented cross section.

[0168] In the embodiments of the present application, a model identification instruction is acquired, wherein the model identification instruction comprises a lung model identifier, and a lung model corresponding to the lung model identifier is determined, the lung model comprising a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model. Based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, a plurality of initial segmentation sections of the lung parenchyma model are determined; wherein the initial segmentation sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment comprises at least one of an intrasegmental trachea, an intrasegmental vein and an intrasegmental artery. At least one of the intrasegmental trachea, the intrasegmental vein and the intrasegmental artery in each initial lung segment is determined. Growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment is determined. Whether at least one of the intrasegmental artery and the intrasegmental vein has a preset abnormality is determined according to the growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment. If it is determined that at least one of the intrasegmental artery and the intrasegmental vein has the preset abnormality, a plurality of target segmentation sections of the lung parenchyma model are generated based on preset first rule information; wherein the preset first rule information is used to indicate that at least a part of the intrasegmental artery in the initial lung segment passes through a target segmentation section corresponding to a target lung segment where the intrasegmental artery is located, and / or at least a part of the intrasegmental vein passes through a target segmentation section corresponding to a target lung segment where the intrasegmental vein is located. If it is determined that neither the intrasegmental artery nor the intrasegmental vein has the preset abnormality, a target segmentation section of the lung parenchyma model is generated based on preset second rule information; wherein the preset second rule information is used to indicate that the intrasegmental artery in the initial lung segment does not pass through a target segmentation section corresponding to a target lung segment where the intrasegmental artery is located, and the intrasegmental vein does not pass through a target segmentation section corresponding to a target lung segment where the intrasegmental vein is located. A prompt information is issued; wherein the prompt information is used to indicate a target lung segment having a preset abnormality in the target segmentation section. Therefore, according to the target segmentation section of the reconstructed lung model, distribution information of each lung segment can be obtained, thereby helping to improve the accuracy of the surgical plan, reduce the surgical risk index, improve the success rate of surgery, and solve the technical problem that it is difficult to identify the distribution of the trachea, blood vessels and lung segments in the lung.

[0169] Figure 11 A structural schematic diagram of a lung recognition processing device provided by the embodiments of the present application is shown in FIG. 1. Figure 11 As shown in FIG. 1, the device comprises:

[0170] A first acquisition unit 31 is configured to acquire a model identification instruction, wherein the model identification instruction comprises a lung model identifier.

[0171] A first determination unit 32 is configured to determine a lung model corresponding to the lung model identifier, the lung model comprising a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model.

[0172] The second determination unit 33 is configured to determine a plurality of initial segmentation sections of the lung parenchyma model based on at least one of the trachea model, the pulmonary vein model and the pulmonary artery model, wherein the initial segmentation sections divide the lung parenchyma model into a plurality of initial lung segments, and each initial lung segment includes at least one of a segmental trachea, a segmental vein and a segmental artery.

[0173] The generation unit 34 is configured to generate a plurality of target segmentation sections of the lung parenchyma model according to the growth information of at least one of the segmental trachea, the segmental vein and the segmental artery in each initial lung segment, wherein the target segmentation sections divide the lung parenchyma model into a plurality of target lung segments, and each target lung segment includes distribution information of at least one of the segmental trachea, the segmental vein and the segmental artery.

[0174] The device of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be repeated here.

[0175] Figure 12 Another structure schematic diagram of a lung recognition processing device provided by the embodiment is shown in Figure 11 Based on the embodiment shown in Figure 12 The second determination unit 33 includes:

[0176] The first acquisition module 331 is configured to acquire an intersegmental vein based on the pulmonary vein model, wherein the intersegmental vein is a vein located between lung segments.

[0177] The first determination module 332 is configured to determine a plurality of initial segmentation sections of the lung parenchyma model according to the intersegmental vein.

[0178] In one example, the first determination module 332 includes:

[0179] The first acquisition sub-module 3321 is configured to acquire a trachea grading result based on the trachea model, and / or acquire a pulmonary artery grading result based on the pulmonary artery model, wherein the trachea grading result is determined according to preset trachea naming rule information, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rule information.

[0180] The first determination sub-module 3322 is configured to determine a plurality of initial segmentation sections of the lung parenchyma model based on any one or two of the intersegmental vein, the trachea grading result and the pulmonary artery grading result.

[0181] In one example, the second determination unit 33 includes:

[0182] The second acquisition module 333 is configured to acquire a trachea classification result based on the trachea model, and / or acquire a pulmonary artery classification result based on the pulmonary artery model; the trachea classification result is determined according to preset trachea naming rule information, and the pulmonary artery classification result is determined according to preset pulmonary artery naming rule information.

[0183] The second determination module 334 is configured to determine a plurality of initial segmentation cross sections of the lung parenchyma model based on the trachea classification result and / or the pulmonary artery classification result.

[0184] In one example, the generation unit 34 includes:

[0185] The third determination module 341 is configured to determine at least one of an intrasegmental trachea, an intrasegmental vein and an intrasegmental artery in each initial lung segment.

[0186] The fourth determination module 342 is configured to determine growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment.

[0187] The fifth determination module 343 is configured to determine whether at least one of the intrasegmental vein and the intrasegmental artery has a preset abnormality according to the growth information of at least one of the intrasegmental vein and the intrasegmental artery in each initial lung segment.

[0188] The first generation module 344 is configured to generate a plurality of target segmentation cross sections of the lung parenchyma model based on preset first rule information if it is determined that at least one of the intrasegmental vein and the intrasegmental artery has a preset abnormality; the preset first rule information is used to indicate that at least a part of the intrasegmental artery in the initial lung segment passes through a target segmentation cross section corresponding to a target lung segment where the intrasegmental artery is located, and / or at least a part of the intrasegmental vein passes through a target segmentation cross section corresponding to a target lung segment where the intrasegmental vein is located.

[0189] In one example, the third determination module 341 is specifically configured to:

[0190] acquire the trachea classification result based on the trachea model, and determine the intrasegmental trachea of each initial lung segment in the initial segmentation cross section based on the trachea classification result; and / or acquire the pulmonary vein classification result based on the pulmonary vein model, and determine the intrasegmental vein of each initial lung segment in the initial segmentation cross section based on the pulmonary vein classification result, and / or acquire the pulmonary artery classification result based on the pulmonary artery model, and determine the intrasegmental artery of each initial lung segment in the initial segmentation cross section based on the pulmonary artery classification result.

[0191] In one example, the fifth determination module 343 includes:

[0192] The second determination sub-module 3431 is configured to determine whether the intrasegmental vein grows across segments according to the growth information of the intrasegmental vein in each initial lung segment. And / or,

[0193] The third determining sub-module 3432 is configured to determine whether the intralobar artery grows across the segment according to the growth information of the intralobar artery in each initial lung segment.

[0194] The fourth determining sub-module 3433 is configured to determine that the intralobar vein has a preset abnormality if it is determined that the intralobar vein grows across the segment, and / or determine that the intralobar artery has a preset abnormality if it is determined that the intralobar artery grows across the segment.

[0195] In one example, the second determining sub-module 3431 includes:

[0196] The fifth determining sub-module 34311 is configured to determine whether a first distance between the intralobar vein and a first adjacent blood vessel is greater than a vein threshold according to the growth information of the intralobar vein in each initial lung segment, wherein the first adjacent blood vessel includes an intralobar vein and / or an intralobar artery adjacent to the intralobar vein.

[0197] The sixth determining sub-module 34312 is configured to determine that the intralobar vein grows across the segment if it is determined that the first distance is less than the vein threshold.

[0198] The seventh determining sub-module 34313 is configured to determine that the intralobar vein does not grow across the segment if it is determined that the first distance is greater than the vein threshold.

[0199] In one example, the third determining sub-module 3432 includes:

[0200] The eighth determining sub-module 34321 is configured to determine whether a second distance between the intralobar artery and a second adjacent blood vessel is greater than an artery threshold according to the growth information of the intralobar artery in each initial lung segment, wherein the second adjacent blood vessel includes an intralobar artery and / or an intralobar vein adjacent to the intralobar artery.

[0201] The ninth determining sub-module 34322 is configured to determine that the intralobar artery grows across the segment if it is determined that the second distance is less than the artery threshold.

[0202] The tenth determining sub-module 34323 is configured to determine that the intralobar artery does not grow across the segment if it is determined that the second distance is greater than the artery threshold.

[0203] In one example, the apparatus further includes:

[0204] The second generating module 345 is configured to generate a target segmented section of the lung parenchyma model based on preset second rule information if it is determined that the intralobar artery and the intralobar vein do not have preset abnormalities, wherein the preset second rule information is used to indicate that the intralobar artery in the initial lung segment does not pass through a target segmented section corresponding to a target lung segment where the intralobar artery is located and the intralobar vein does not pass through a target segmented section corresponding to a target lung segment where the intralobar vein is located.

[0205] In one example, the apparatus further includes:

[0206] The prompting unit 41 is configured to issue a prompt information, wherein the prompt information is used to indicate that the target lung segment in the target segment cross-section has a preset abnormality.

[0207] The apparatus of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be repeated here.

[0208] In one embodiment, the embodiment of the present application provides a lung segment model and a lung segment digital model, both of which include a lung model, the lung model including a lung parenchyma model, a trachea model, a pulmonary vein model and a pulmonary artery model, the lung model including a target segment cross-section, each lung segment including one or more of an intra-segment artery, an intra-segment vein and an intra-segment trachea.

[0209] The lung model in the lung segment model and the lung model in the lung segment digital model are both the lung model mentioned in the above embodiment, and the lung model is applied to a server to enable the server to obtain the target segment cross-section according to the lung model.

[0210] It should be noted that the lung segment digital model is a three-dimensional digital model reconstructed based on the above lung recognition processing method, and the lung segment model is a three-dimensional entity model obtained by printing the lung segment digital model through a three-dimensional printer.

[0211] Figure 13 A structural diagram of a server provided by the embodiment of the present application is shown in FIG. 1. Figure 13 The server includes a memory 51 and a processor 52.

[0212] The memory 51 stores a computer program that can run on the processor 52.

[0213] The processor 52 is configured to execute the method provided by the above embodiment.

[0214] The server further includes a receiver 53 and a transmitter 54. The receiver 53 is configured to receive instructions and data sent by an external device, and the transmitter 54 is configured to send instructions and data to the external device.

[0215] The embodiment of the present application further provides a non-transitory computer readable storage medium, when the instructions in the storage medium are executed by the processor of the server, the server can execute the method provided by the above embodiment.

[0216] The embodiment of the present application further provides a computer program product, which comprises a computer program stored in a readable storage medium, at least one processor of a server can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the server executes the scheme provided by any one of the above embodiments.

[0217] Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the present disclosure cover any and all variations of the present disclosure including those variations contained within the scope of the features presented by and knowledge of one of ordinary skill in the art at the time of application. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0218] It should be understood that the present disclosure is not limited to the precise structures herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. A lung identification processing method, characterized in that, include: Obtain a model recognition instruction, wherein the model recognition instruction includes a lung model identifier, and determine the lung model corresponding to the lung model identifier, wherein the lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model, wherein the trachea model, the pulmonary vein model, and the pulmonary artery model are all interspersed in the lung parenchyma model; Based on at least one of the tracheal model, pulmonary vein model, and pulmonary artery model, multiple initial segmented sections of the lung parenchyma model are determined; wherein, the initial segmented sections divide the lung parenchyma model into multiple initial lung segments, and each initial lung segment includes at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery; Based on the growth information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, multiple target segment sections of the lung parenchyma model are generated; wherein, the target segment sections divide the lung parenchyma model into multiple target lung segments, and each target lung segment includes the distribution information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery; The process of generating multiple target segmental sections of the lung parenchyma model based on growth information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment includes: Identify at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment; Determine the growth information of at least one of the intrasegmental veins and intrasegmental arteries in each initial lung segment; Based on the growth information of at least one of the intrasegmental veins and intrasegmental arteries in each initial lung segment, determine whether there is a predetermined abnormality in at least one of the intrasegmental arteries and intrasegmental veins; If it is determined that at least one of the intrasegmental artery and intrasegmental vein has a preset abnormality, then multiple target segment sections of the lung parenchyma model are generated based on preset first rule information; wherein, the preset first rule information is used to indicate that at least a portion of the intrasegmental artery in the initial lung segment passes through the target segment section corresponding to the target lung segment where the intrasegmental artery is located, and / or, at least a portion of the intrasegmental vein passes through the target segment section corresponding to the target lung segment where the intrasegmental vein is located.

2. The method according to claim 1, characterized in that, The determination of multiple initial segmented sections of the lung parenchyma model based on at least one of the trachea model, pulmonary vein model, and pulmonary artery model includes: Intersegmental veins are obtained based on the pulmonary vein model; wherein, the intersegmental veins are veins located between lung segments; Multiple initial segmental sections of the lung parenchyma model are determined based on the intersegmental veins.

3. The method according to claim 2, characterized in that, The determination of multiple initial segmental sections of the lung parenchyma model based on the intersegmental veins includes: The tracheal grading result is obtained based on the tracheal model, and / or the pulmonary artery grading result is obtained based on the pulmonary artery model; wherein the tracheal grading result is determined according to preset tracheal naming rules, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rules. Based on any one or both of the intersegmental veins, the tracheal grading results, and the pulmonary artery grading results, multiple initial segmental sections of the lung parenchyma model are determined.

4. The method according to claim 1, characterized in that, The determination of multiple initial segmented sections of the lung parenchyma model based on at least one of the trachea model, pulmonary vein model, and pulmonary artery model includes: The tracheal grading result is obtained based on the tracheal model, and / or the pulmonary artery grading result is obtained based on the pulmonary artery model; wherein the tracheal grading result is determined according to preset tracheal naming rules, and the pulmonary artery grading result is determined according to preset pulmonary artery naming rules. Based on the tracheal grading results and / or the pulmonary artery grading results, multiple initial segmental sections of the lung parenchyma model are determined.

5. The method according to claim 1, characterized in that, Identifying at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment, including: Based on the tracheal model, tracheal grading results are obtained, and based on the tracheal grading results, the intrasegmental trachea in each initial lung segment of the initial segmented cross-section is determined; and / or, Based on the pulmonary vein model, pulmonary vein grading results are obtained, and based on the pulmonary vein grading results, the intrasegmental veins of each initial lung segment in the initial segmented cross-section are determined, and / or, Based on the pulmonary artery model, the pulmonary artery grading results are obtained, and based on the pulmonary artery grading results, the intrasegmental artery of each initial lung segment in the initial segmented cross section is determined.

6. The method according to claim 1, characterized in that, The step of determining whether at least one of the intrasegmental artery and intrasegmental vein has a predetermined abnormality based on the growth information of at least one of the intrasegmental vein and intrasegmental artery in each initial lung segment includes: Based on the growth information of the intrasegmental veins in each initial lung segment, determine whether the intrasegmental veins grow across segments; and / or, based on the growth information of the intrasegmental arteries in each initial lung segment, determine whether the intrasegmental arteries grow across segments; If it is determined that a vein within the segment is growing across segments, then it is determined that a pre-defined abnormality exists in the vein within the segment; and / or, if it is determined that an artery within the segment is growing across segments, then it is determined that a pre-defined abnormality exists in the artery within the segment.

7. The method according to claim 6, characterized in that, The step of determining whether a segmental vein has grown across segments based on the growth information of the segmental veins in each initial lung segment includes: Based on the growth information of the intrasegmental veins in each initial lung segment, it is determined whether a first distance between the intrasegmental vein and a first adjacent vessel is greater than a vein threshold; wherein, the first adjacent vessel includes intrasegmental veins and / or intrasegmental arteries adjacent to the intrasegmental veins; If it is determined that the first distance is less than the vein threshold, then it is determined that the vein in the segment has cross-segment growth; If it is determined that the first distance is greater than the vein threshold, then it is determined that there is no cross-segment growth of veins within the segment.

8. The method according to claim 6, characterized in that, The step of determining whether an intrasegmental artery has grown across segments based on growth information in the intrasegmental artery of each initial lung segment includes: Based on the growth information in the intrasegmental artery in each initial lung segment, determine whether a second distance between the intrasegmental artery and a second adjacent vessel is greater than an arterial threshold; wherein, the second adjacent vessel includes an intrasegmental artery and / or an intrasegmental vein adjacent to the intrasegmental artery; If it is determined that the second distance is less than the arterial threshold, then it is determined that there is transsegmental growth of the artery within the segment; If it is determined that the second distance is greater than the arterial threshold, then it is determined that there is no cross-segment growth of the artery within the segment.

9. The method according to claim 1, characterized in that, The method further includes: If it is determined that neither the intrasegmental artery nor the intrasegmental vein has any preset abnormalities, then the target segment cross section of the lung parenchyma model is generated based on preset second rule information; wherein, the preset second rule information is used to indicate that the intrasegmental artery in the initial lung segment does not pass through the target segment cross section corresponding to the target lung segment where the intrasegmental artery is located, and the intrasegmental vein does not pass through the target segment cross section corresponding to the target lung segment where the intrasegmental vein is located.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Issue a prompt message; wherein the prompt message is used to indicate that there is a target lung segment with a preset abnormality in the target segment cross section.

11. A lung recognition processing device, characterized in that, include: The first acquisition unit is used to acquire model recognition instructions, wherein the model recognition instructions include a lung model identifier; The first determining unit is used to determine the lung model corresponding to the lung model identifier. The lung model includes a lung parenchyma model, a trachea model, a pulmonary vein model, and a pulmonary artery model. The trachea model, the pulmonary vein model, and the pulmonary artery model are all interspersed in the lung parenchyma model. The second determining unit is used to determine multiple initial segment sections of the lung parenchyma model based on at least one of the tracheal model, pulmonary vein model, and pulmonary artery model; wherein the initial segment sections divide the lung parenchyma model into multiple initial lung segments, and each initial lung segment includes at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery; The generation unit is configured to generate multiple target segment sections of the lung parenchyma model based on the growth information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment; wherein the target segment sections divide the lung parenchyma model into multiple target lung segments, and each target lung segment includes the distribution information of at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery. The generation unit includes: The third determining module is used to determine at least one of the intrasegmental trachea, intrasegmental vein, and intrasegmental artery in each initial lung segment; The fourth determining module is used to determine the growth information of at least one of the intrasegmental veins and intrasegmental arteries in each initial lung segment; The fifth determining module is used to determine whether there is a preset abnormality in at least one of the intrasegmental artery and intrasegmental vein based on the growth information of at least one of the intrasegmental vein and intrasegmental artery in each initial lung segment; A first generation module is configured to generate multiple target segment sections of the lung parenchyma model based on preset first rule information if it is determined that at least one of the intrasegmental artery and intrasegmental vein has a preset abnormality; wherein the preset first rule information is used to indicate that at least a portion of the intrasegmental artery in the initial lung segment passes through the target segment section corresponding to the target lung segment where the intrasegmental artery is located, and / or that at least a portion of the intrasegmental vein passes through the target segment section corresponding to the target lung segment where the intrasegmental vein is located.

12. A server, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method of any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-10.

Images