CN-122005084-A - Scoliosis minimally invasive surgery auxiliary system based on AI identification cone shape change

Abstract

The invention provides a scoliosis minimally invasive surgery auxiliary system based on AI identification cone shape change, and relates to the technical field of medical instruments and artificial intelligence. The system comprises a multi-mode image input module, a vertebral body segmentation and three-dimensional reconstruction module, an AI vertebral body micro-morphology change identification module, a scoliosis comprehensive evaluation module, a minimally invasive surgery planning and navigation module, a minimally invasive surgery planning and distribution module and an intraoperative navigation support module, wherein the vertebral body segmentation and three-dimensional reconstruction module is used for automatically segmenting vertebral bodies and reconstructing a three-dimensional surface model, the AI vertebral body micro-morphology change identification module is used for quantitatively analyzing micro-morphology changes of each vertebral body, the scoliosis comprehensive evaluation module is used for automatically measuring Cobb angles, vertebral body rotation and trunk offset by combining the micro-morphology changes and the whole spinal column force lines, the minimally invasive surgery planning and navigation module is used for automatically designing a filling part, material consumption and distribution according to the micro-morphology characteristics of the individual vertebral bodies, and the minimally invasive surgery planning and navigation support is provided for doctors to use filling materials to fill, rest and correct asymmetric parts of the vertebral bodies under minimally invasive conditions. Based on AI identification, the minimally invasive open surgery is realized.

Inventors

• ZHANG JIAGENG
• HOU HUIFANG

Assignees

• 张嘉庚

Dates

Publication Date

20260512

Application Date

20260330

Claims (8)

1. 1. A minimally invasive surgical assistance system for identifying scoliosis based on AI changes in vertebral body shape, comprising: the multi-mode image input module is used for acquiring and preprocessing the spine image data; The cone segmentation and three-dimensional reconstruction module is used for automatically segmenting the cone and reconstructing a three-dimensional surface model; The AI vertebral body micro morphological change recognition module is used for quantitatively analyzing the micro morphological change of each vertebral body and outputting quantitative indexes and asymmetric degrees; the scoliosis comprehensive evaluation module is used for combining the small morphological change of the vertebral body with the whole spinal force line, automatically measuring the Cobb angle, the rotation of the vertebral body and the deviation of the trunk, and generating a standardized evaluation report; The minimally invasive surgery planning and navigation module is used for automatically designing a minimally invasive surgery scheme according to the tiny morphological characteristics of the individual vertebral bodies, planning the filling parts of the vertebral bodies, the material consumption and distribution, and providing navigation support in surgery, wherein the minimally invasive surgery scheme guides doctors to fill, rest and correct asymmetric parts of the vertebral bodies by using filling materials under minimally invasive conditions.
2. 2. The system of claim 1, further comprising a mechanical analysis and risk early warning module for assessing orthopedic stress distribution based on vertebral body microform asymmetry and early warning of intra-operative vertebral body injury, loss of orthopedic or risk of mechanical imbalance.
3. 3. The system of claim 1 or 2, further comprising an output and interaction module for generating a pre-operative assessment report, a surgical planning plan, and a visual callout map, and supporting interfacing minimally invasive surgical devices with a navigation system.
4. 4. The system of claim 1, wherein the AI vertebral body micro-morphology change recognition module detects and extracts differences in elevation, inclination, and asymmetry from side to side, front to back, up to down, and up to down, of the vertebral body.
5. 5. The system of claim 1, wherein the minimally invasive surgical planning and navigation module is further configured to plan a minimally invasive approach, avoid morphologically abnormally high risk areas, and generate a three-dimensional visualization path to support intra-operative real-time navigation.
6. 6. The system of claim 1, wherein the filler material is a commercially available filler material that is absorbable or non-absorbable.
7. 7. The system of claim 1, wherein the multi-modality image input module supports the introduction of DICOM data for full-length X-ray, CT, MRI of the spine and performs image registration, noise reduction, and normalization preprocessing.
8. 8. The system of claim 1, wherein the vertebral body segmentation and three-dimensional reconstruction module automatically segments the thoracic and lumbar vertebrae of each segment based on a deep learning model and precisely locates the endplates, edges, and central anatomy.

Description

Scoliosis minimally invasive surgery auxiliary system based on AI identification cone shape change Technical Field The invention relates to the technical field of medical equipment and artificial intelligence, in particular to a scoliosis minimally invasive surgery auxiliary system based on AI identification of cone shape change, which is suitable for minimally invasive orthopedic surgery planning, navigation and safety assessment of teenagers with idiopathic scoliosis, humen disease and other minor cone shape abnormalities. Background The occurrence and progression of scoliosis is often accompanied by minor morphological differences and asymmetric changes of the vertebral body itself, and these minor structural changes are key determinants of scoliosis progression, mechanical imbalance and surgical effect. The traditional evaluation mode depends on visual reading of doctors, is difficult to stably capture early and fine morphological changes of the vertebral bodies, and is easy to cause missed judgment or subjective deviation. At present, the main surgery for clinically treating scoliosis is the traditional open orthopedic surgery, and large steel bars and large steel nails are widely adopted for fixation and orthopedic. The mode has large incision, high trauma and more soft tissue damage, and the operation planning is highly dependent on the experience of doctors, so that the fine design is difficult according to the individual small morphological difference of the vertebral bodies of each patient. In the prior art, although the minimally invasive surgery direction exists, a set of intelligent auxiliary system capable of accurately identifying the tiny morphological changes of the vertebral body is generally lacking, the degradation of the traditional high-trauma open surgery of a large steel rod and a large steel nail into the minimally invasive surgery cannot be realized, and the accurate support for minimally invasive stabilization of the vertebral body shape is also lacking. Disclosure of Invention The invention aims to solve the main technical problems that the small morphological change of the vertebral body is accurately identified through artificial intelligence, the traditional high-trauma open operation relying on a large steel rod and a large steel nail is degraded into the minimally invasive operation, and the accurate filling, the rest and the correction of the asymmetric part of the vertebral body are realized under the minimally invasive condition, so that the problems of strong evaluation subjectivity, insufficient individuation of operation planning, large trauma and slow recovery caused by incapability of capturing the small morphological difference of the vertebral body in the prior art are solved. In order to solve the technical problems, the technical scheme provided by the invention is as follows: a scoliosis minimally invasive surgical assistance system for identifying changes in vertebral body shape based on AI, comprising: the multi-mode image input module is used for acquiring and preprocessing the spine image data; The cone segmentation and three-dimensional reconstruction module is used for automatically segmenting the cone and reconstructing a three-dimensional surface model; The AI vertebral body micro morphological change recognition module is used for quantitatively analyzing the micro morphological change of each vertebral body and outputting quantitative indexes and asymmetric degrees; the scoliosis comprehensive evaluation module is used for combining the small morphological change of the vertebral body with the whole spinal force line, automatically measuring the Cobb angle, the rotation of the vertebral body and the deviation of the trunk, and generating a standardized evaluation report; The minimally invasive surgery planning and navigation module is used for automatically designing a minimally invasive surgery scheme according to the tiny morphological characteristics of the individual vertebral bodies, planning the filling parts of the vertebral bodies, the material consumption and distribution, and providing navigation support in surgery, wherein the minimally invasive surgery scheme guides doctors to fill, rest and correct asymmetric parts of the vertebral bodies by using filling materials under minimally invasive conditions. Optionally, the system further comprises a mechanical analysis and risk early warning module for evaluating orthopedic stress distribution based on the tiny form asymmetry of the vertebral body and early warning the risk of damage, loss of orthopedic or mechanical unbalance of the vertebral body during operation. Optionally, the system further comprises an output and interaction module for generating a preoperative evaluation report, an operative planning scheme and a visual label graph, and supporting docking of minimally invasive surgical equipment and a navigation system. Optionally, the AI vertebral body micro morphological change recogni