Medical image digital auxiliary analysis method and system

Abstract

The invention discloses a medical image digital auxiliary analysis method and system, and relates to the data processing and image processing technology, and the method comprises the steps: building a typical three-dimensional model containing a target organ in advance, and obtaining a medical image containing an organ focus region; aligning the medical image on a corresponding tangent plane based on the typical three-dimensional model, and identifying a focus area in the medical image; mapping the lesion area based on the aligned tangent planes of the typical three-dimensional model; determining at least one local center point from the lesion area, and performing local scanning on the typical three-dimensional model based on the local center point and the lesion boundary to establish a local lesion three-dimensional range; and presenting to a user based on the typical three-dimensional model after the three-dimensional range of the local focus is established. According to the method, the auxiliary section can be performed according to the user operation, and the auxiliary effect of the medical image is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and image processing, and in particular to a medical image digital auxiliary analysis method and system. Background Art

[0002] Computer-assisted analysis of medical images uses advanced computer software and hardware systems to analyze and process digital radiological images in order to discover and detect lesion characteristics. The results are provided as a "second opinion" for diagnostic physicians to help radiologists improve lesion detection rates, increase diagnostic accuracy and improve diagnostic reproducibility, shorten film reading time, and improve work efficiency.

[0003] In the prior art, traditional computer-aided measurement (CAM) and computer-aided diagnosis (CAD) technologies used in medical ultrasound imaging systems have many problems and limitations. Their detection results are one-sided and non-intuitive, and cannot truly achieve a comprehensive and accurate analysis of organ conditions. Summary of the invention

[0004] The embodiments of the present application provide a medical image digital auxiliary analysis method and system for determining the range of the lesion area by combining a three-dimensional model of a typical organ and a medical image of a patient, and performing auxiliary sectioning according to user operations to improve the auxiliary effect of medical images.

[0005] The present application embodiment provides a medical image digital auxiliary analysis method, including: Establish a typical three-dimensional model containing the target organ in advance, and obtain medical images containing the organ lesion area; Aligning the medical images on corresponding sections based on the typical three-dimensional model, and identifying lesion areas in the medical images; mapping the lesion region based on the aligned slices in the representative three-dimensional model; Determine at least one local center point from the lesion area, and perform a local scan on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion; A typical three-dimensional model based on the established three-dimensional range of the local lesion is presented to the user, and a section image containing the local lesion area is presented in association with the typical three-dimensional model according to the rotation angle selected by the user.

[0006] Optionally, aligning the medical images on corresponding sections based on the typical three-dimensional model includes: extracting an organ boundary in the medical image, and determining a plurality of reference positions from the medical image outside the organ boundary; Matching the organ boundary with the typical three-dimensional model to determine an alignment interval in the typical three-dimensional model; The section is cut in the alignment interval to obtain a section image, and each section image is used to perform secondary matching with the organ boundary and each reference position, so as to determine the section with the greatest matching degree as the alignment section image to complete the alignment.

[0007] Optionally, performing slicing in the alignment interval to obtain slice images, and performing secondary matching with the organ boundary and each reference position using each slice image respectively includes: In the alignment interval area in the typical three-dimensional model, determine a first section image by sectioning at any angle; Based on the first section image, calculating the specification relationship with each reference position in the medical image; adjusting the angle of the section according to a changing trend of the specification relationship along the boundary of the organ; The second section image is repeatedly obtained for the typical three-dimensional model section according to the adjusted section angle, and the specification relationship with each reference position in the medical image is repeatedly calculated until the calculated specification relationships are within a preset fluctuation range.

[0008] Optionally, adjusting the section angle according to the changing trend of the specification relationship along the boundary of the organ includes: determining a specification relationship along a boundary of the organ that is closest to a reference position; Determine the specification change trend of other reference positions on both sides of the reference position whose specification relationship is closest; Determine the cutting angle that needs to be adjusted based on the increase or decrease relationship of the specification change trend of other reference positions.

[0009] Optionally, determining at least one local center point from the lesion area, and performing a local scan on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion includes: Determine a plurality of arc segments according to the identified lesion area in the medical image, and determine the center of each arc segment; Clustering the determined circle centers to obtain at least one local center point; Based on the local center point and the lesion boundary, a local scan is performed on the typical three-dimensional model based on the mapped lesion area to establish a three-dimensional range of the local lesion.

[0010] Optionally, based on the local center point and the lesion boundary, performing a local scan based on the mapped lesion area in the typical three-dimensional model includes: Based on each local center point and the lesion boundary, surface scanning is performed on the typical three-dimensional model; Determine the connection boundary of each surface scan result; Keep one of the overlapping areas between any two face scan results, and keep the areas outside each connection boundary; Each connected boundary is smoothed to establish the three-dimensional range of the local lesion.

[0011] Optionally, smoothing each connection boundary includes: for a concave boundary in the connection boundary, taking areas on both sides of the concave boundary within a preset pixel distance as smooth boundaries.

[0012] Optionally, based on the typical three-dimensional model after the three-dimensional range of the local lesion is established, the following is presented to the user: Determine the user's rotation angle of the typical three-dimensional model after establishing the three-dimensional range of the local lesion; According to the rotation angle and the model display direction of the screen, the typical three-dimensional model after the three-dimensional range of the local lesion is established is cut in the largest area of ​​the three-dimensional range of the local lesion to present it to the user.

[0013] The embodiment of the present application further proposes a medical image digital assisted analysis system, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the medical image digital assisted analysis method as described above are implemented.

[0014] The method of the embodiment of the present application combines the three-dimensional model of the typical organ and the medical image of the patient to determine the range of the lesion area, and performs auxiliary sectioning according to the user operation, which can effectively improve the auxiliary effect of medical images on doctors.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 The following is a schematic diagram of the basic process of the medical image digital auxiliary analysis method of this embodiment. DETAILED DESCRIPTION

[0017] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0018] The present application embodiment proposes a medical image digital auxiliary analysis method, such as Figure 1 As shown, the following steps are included: In step S101, a typical three-dimensional model including the target organ is pre-established, and a medical image including the organ lesion area is obtained. In some embodiments, for example, organs such as the heart and liver, typical three-dimensional models of corresponding age groups can be established according to the age group of the patient. In some specific examples, a typical three-dimensional model including the organ part and nearby tissues can be established.

[0019] In step S102, the medical image is aligned on the corresponding section based on the typical three-dimensional model, and the lesion area in the medical image is identified. In a specific example, for imaging of an organ or lesion, a medical image with a maximum contour range can generally be obtained, based on which the section can be aligned to the typical three-dimensional model.

[0020] In step S103, the lesion region is mapped based on the aligned sections of the typical three-dimensional model, that is, the lesion region is mapped according to the aligned typical three-dimensional model.

[0021] In step S104, at least one local center point is determined from the lesion area, and a local scan is performed on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion.

[0022] In step S105, a typical three-dimensional model based on the establishment of the three-dimensional range of the local lesion is presented to the user, and a cross-sectional image containing the local lesion area is presented in association with the typical three-dimensional model according to the rotation angle selected by the user. In a specific example, the three-dimensional model at a set angle can be presented by default according to the type of organ, and the lesion area can be cross-sectioned at this angle, so that, for example, the three-dimensional model and the cross-sectional image are presented simultaneously on the interface.

[0023] The method of the embodiment of the present application combines the three-dimensional model of the typical organ and the medical image of the patient to determine the range of the lesion area, and performs auxiliary sectioning according to the user operation, which can effectively improve the auxiliary effect of medical images on doctors.

[0024] In some embodiments, aligning the medical images on corresponding slices based on the typical three-dimensional model comprises: Extracting the organ boundary in the medical image, and determining multiple reference positions from the medical image outside the organ boundary. For example, for a medical image of the lung, multiple reference positions can be determined based on the lung boundary and landmark tissues or structures outside the boundary.

[0025] The organ boundary is matched with the typical three-dimensional model to determine an alignment interval in the typical three-dimensional model.

[0026] The slices are cut in the alignment interval to obtain the slice images, and each slice image is used to perform secondary matching with the organ boundary and each reference position, so that the slice with the greatest matching degree is used as the alignment slice image to complete the alignment. That is, by determining the alignment interval in the typical three-dimensional model, and performing accurate secondary matching according to multiple reference positions in the alignment interval, the medical image is matched to the established typical three-dimensional model of the target organ.

[0027] In some embodiments, performing slicing in the alignment interval to obtain slice images, and performing secondary matching with the organ boundary and each reference position using each slice image respectively comprises: In the alignment interval area in the typical three-dimensional model, a first section image is determined by cutting at any angle. In this example, the fine alignment step is further performed in the alignment interval area determined by the aforementioned rough alignment, and the alignment interval area is cut in the typical three-dimensional model to obtain a first section image.

[0028] Based on the first section image, the specification relationship with each reference position in the medical image is calculated. The specification relationship referred to in the embodiment of the present application can be a size relationship, and for example, it can be based on the extraction of the medical image. If the reference position specification in the first section image is smaller than the medical image, the size relationship is negative; if the reference position specification in the first section image is larger than the medical image, the size relationship is positive, and if it is an exact match, it is close to 0.

[0029] The section angle is adjusted according to the changing trend of the specification relationship along the boundary of the organ, and the section angle is adjusted according to the changing trend of the aforementioned size relationship outside the boundary as a reference.

[0030] The second section image is obtained by repeatedly cutting the typical three-dimensional model according to the adjusted section angle, and the specification relationship with each reference position in the medical image is repeatedly calculated until the calculated specification relationship is within the preset fluctuation range. The above operation is repeated to complete the fine alignment step.

[0031] In some embodiments, adjusting the cut plane angle according to the changing trend of the specification relationship along the boundary of the organ comprises: The reference position that is closest to zero along the organ boundary is determined.

[0032] Determine the specification change trends of other reference positions on both sides of the reference position whose specification relationships are closest. Based on other change trends on both sides of the reference position, such as a gradual increase in the positive and negative specifications on both sides, the section angle can be fine-tuned based on the increase and decrease relationship to complete precise alignment.

[0033] Determine the cutting angle that needs to be adjusted based on the increase or decrease relationship of the specification change trend of other reference positions.

[0034] In some embodiments, determining at least one local center point from the lesion area, and performing a local scan on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion includes: Based on the identified lesion area in the medical image, multiple arc segments are determined, and the center of each arc segment is determined. In some embodiments, the arc segments of the lesion area in the medical image can be divided, and then the centers corresponding to the multiple arc segments are determined.

[0035] The determined circle centers are clustered to obtain at least one local center point. For example, if the circle centers determined for a pair of small arc segments are in approximately the same position, they are clustered into one center point.

[0036] Based on the local center point and the lesion boundary, in the typical three-dimensional model, a local scan is performed based on the mapped lesion area to establish a three-dimensional range of the local lesion. The scanning referred to in the embodiment of the present application can be performed on a sphere with the local center point as the center and the corresponding arc segment as the radius in the typical three-dimensional model. In a specific example, the three-dimensional range of the lesion of the accurate lesion can be determined in conjunction with medical images of the target organ at multiple angles. Further, for lines outside the determined arc segments, such as straight lines and quasi-straight lines, they are directly mapped, and then the three-dimensional range of the lesion can be determined in the typical three-dimensional model by splicing and combining the scanning results of medical images at multiple angles in the lesion area.

[0037] In some embodiments, based on the local center point and the lesion boundary, performing a local scan based on the mapped lesion area in the typical three-dimensional model includes: Based on each local center point and the lesion boundary, surface scanning is performed on the typical three-dimensional model; Determine the connection boundaries of each face scan result.

[0038] One of the overlapping areas in any two face scan results is retained, and the area outside each connection boundary is retained, that is, the union of the scan results is taken as the three-dimensional range of the local lesion.

[0039] Each connected boundary is smoothed to establish the three-dimensional range of the local lesion.

[0040] In some embodiments, smoothing each connection boundary includes: for a concave boundary in the connection boundary, taking the area on both sides of the concave boundary within a preset pixel distance as a smooth boundary. In a specific example, the lesion shape area formed after the connection boundary combination is not smooth, and the shortest pixel distance between the two sides of the boundary is determined. If the shortest pixel distance is less than the preset pixel distance, the corresponding pixel filling is performed to complete the boundary smoothing.

[0041] In some embodiments, based on the typical three-dimensional model after the three-dimensional range of the local lesion is established, presenting to the user includes: Determine the user's rotation angle of the typical three-dimensional model after establishing the three-dimensional range of the local lesion; According to the rotation angle and the model display direction of the screen, the typical three-dimensional model after the three-dimensional range of the local lesion is established is sliced ​​in the largest area of ​​the three-dimensional range of the local lesion to present it to the user.

[0042] In a specific example, by cutting the typical three-dimensional model after establishing the three-dimensional range of the local lesion in the largest area of ​​the local lesion three-dimensional range, it is possible to assist doctors in observing and analyzing the lesion area from various angles, thereby improving the efficiency of digital assisted analysis of medical images.

[0043] The embodiment of the present application further proposes a medical image digital assisted analysis system, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the medical image digital assisted analysis method as described above are implemented.

[0044] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present disclosure with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. It is not limited to the examples described in this specification or during the implementation of this application, and its examples will be interpreted as non-exclusive.

[0045] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art may use other embodiments when reading the above description.

[0046] The above embodiments are merely exemplary embodiments of the present disclosure. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the essence and protection scope of the present disclosure, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present invention.

Claims

1. A medical image digitalization-assisted analysis method, It is characterized in that include: Establish a typical three-dimensional model containing the target organ in advance, and obtain medical images containing the organ lesion area; Aligning the medical images on corresponding sections based on the typical three-dimensional model, and identifying lesion areas in the medical images; mapping the lesion region based on the aligned slices in the representative three-dimensional model; Determine at least one local center point from the lesion area, and perform a local scan on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion; A typical three-dimensional model based on the established three-dimensional range of the local lesion is presented to the user, and a section image containing the local lesion area is presented in association with the typical three-dimensional model according to the rotation angle selected by the user.

2. The medical image digitalization-assisted analysis method according to claim 1, It is characterized in that Aligning the medical images on corresponding sections based on the typical three-dimensional model comprises: extracting an organ boundary in the medical image, and determining a plurality of reference positions from the medical image outside the organ boundary; Matching the organ boundary with the typical three-dimensional model to determine an alignment interval in the typical three-dimensional model; The section is cut in the alignment interval to obtain a section image, and each section image is used to perform secondary matching with the organ boundary and each reference position, so as to determine the section with the greatest matching degree as the alignment section image to complete the alignment.

3. The medical image digitalization-assisted analysis method according to claim 2, It is characterized in that Performing slicing in the alignment interval to obtain slice images, and performing secondary matching with the organ boundary and each reference position using each slice image respectively comprises: In the alignment interval area in the typical three-dimensional model, determine a first section image by sectioning at any angle; Based on the first section image, calculating the specification relationship with each reference position in the medical image; adjusting the angle of the section according to a changing trend of the specification relationship along the boundary of the organ; The second section image is repeatedly obtained for the typical three-dimensional model section according to the adjusted section angle, and the specification relationship with each reference position in the medical image is repeatedly calculated until the calculated specification relationships are within a preset fluctuation range.

4. The medical image digitalization-assisted analysis method according to claim 3, It is characterized in that Adjusting the section angle according to the changing trend of the specification relationship along the boundary of the organ includes: determining a specification relationship along a boundary of the organ that is closest to a reference position; Determine the specification change trend of other reference positions on both sides of the reference position whose specification relationship is closest; Determine the cutting angle that needs to be adjusted based on the increase or decrease relationship of the specification change trend of other reference positions.

5. The medical image digitalization-assisted analysis method according to claim 3, It is characterized in that Determining at least one local center point from the lesion area, and performing a local scan on the typical three-dimensional model based on the local center point and the lesion boundary to establish a three-dimensional range of the local lesion includes: Determine a plurality of arc segments according to the identified lesion area in the medical image, and determine the center of each arc segment; Clustering the determined circle centers to obtain at least one local center point; Based on the local center point and the lesion boundary, a local scan is performed on the typical three-dimensional model based on the mapped lesion area to establish a three-dimensional range of the local lesion.

6. The medical image digitalization-assisted analysis method according to claim 5, It is characterized in that Based on the local center point and the lesion boundary, performing a local scan based on the mapped lesion area in the typical three-dimensional model includes: Based on each local center point and the lesion boundary, surface scanning is performed on the typical three-dimensional model; Determine the connection boundary of each surface scan result; Keep one of the overlapping areas between any two face scan results, and keep the areas outside each connection boundary; Each connected boundary is smoothed to establish the three-dimensional range of the local lesion.

7. The medical image digitalization-assisted analysis method according to claim 6, It is characterized in that Smoothing each connection boundary includes: for a concave boundary in the connection boundary, taking areas on both sides of the concave boundary within a preset pixel distance as smooth boundaries.

8. The medical image digitalization-assisted analysis method according to claim 3, It is characterized in that Based on the typical 3D model after the 3D range of the local lesion is established, the following information is presented to the user: Determine the user's rotation angle of the typical three-dimensional model after establishing the three-dimensional range of the local lesion; According to the rotation angle and the model display direction of the screen, the typical three-dimensional model after the three-dimensional range of the local lesion is established is sliced ​​in the largest area of ​​the three-dimensional range of the local lesion to present it to the user.

9. A medical image digital auxiliary analysis system, It is characterized in that The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the medical image digital auxiliary analysis method as described in any one of claims 1 to 8 are implemented.

Images