CN-122005079-A - Puncture path planning method and system based on ray projection and collision detection

CN122005079ACN 122005079 ACN122005079 ACN 122005079ACN-122005079-A

Abstract

The invention provides a puncture path planning method and a puncture path planning system based on ray projection and collision detection, wherein the method comprises the steps of obtaining a 3D voxel data model of an object to be punctured, and dividing focuses and organs of the 3D voxel data model according to a pre-trained organ division model; and performing collision detection on each path in the initial path set, calculating the length of each path passing through the collision detection, and determining a candidate puncture path set according to the ascending order of the lengths of the paths and combining with a preset candidate threshold value. The invention effectively solves the technical problems of low reliability and low efficiency of puncture path planning in the prior art.

Inventors

YAO YUHANG
LIANG CHEN
CHEN XINYUAN
CHEN KUI
ZHANG ZHEMING
FAN PEIHUA
ZHANG BO

Assignees

苏州艾米特医疗科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251223

Claims (10)

1. A puncture path planning method based on ray casting and collision detection is characterized by comprising the following steps: acquiring a 3D voxel data model of an object to be punctured, and dividing a focus and an organ by the 3D voxel data model according to a pre-trained organ dividing model; Generating uniformly distributed direction vectors from the center of a target focus in the segmented 3D voxel data model to the surrounding space by adopting a fibonacci sphere sampling algorithm to obtain an initial path set; and performing collision detection on each path in the initial path set, calculating the length of each path passing through the collision detection, and determining a candidate puncture path set according to the ascending sequence of the length of the paths and the preset candidate threshold value.
2. The puncture path planning method based on ray casting and collision detection according to claim 1, further comprising, after the performing focus and organ segmentation on the 3D voxel data model according to a pre-trained organ segmentation model: calculating arithmetic mean value of all vertex coordinates in the partitioned focus sub-model to obtain a focus geometric center point serving as the target focus center.
3. The puncture path planning method based on ray casting and collision detection according to claim 2, further comprising: distributing corresponding attribute type identifiers for each segmented organ sub-model, wherein the attribute types comprise skin surfaces, static/arterial blood vessels, dangerous organs, penetration-allowing organs and bones; And constructing a corresponding hierarchical bounding volume for each forbidden organ sub-model according to the attribute category identification.
4. A puncture path planning method based on ray casting and collision detection according to claim 3, characterized in that: After the uniformly distributed direction vectors are generated, before the initial path set is obtained, invalid direction vectors are removed according to preset direction constraints; and determining an in-vivo puncture path from the body surface puncture entry point to the center of the target focus as an initial path according to the body surface puncture entry point where the single direction vector intersects the skin surface sub-model.
5. The puncture path planning method based on ray casting and collision detection according to claim 4, wherein the collision detection for each path in the initial path set comprises: Judging whether the current path intersects with any hierarchical bounding volume; If the current path intersects any hierarchical bounding volume, the collision detection result of the current path is not passed; If the current path is not intersected with any hierarchical bounding volume, the collision detection result of the current path is passing.
6. The puncture path planning method based on ray casting and collision detection according to claim 5, wherein the preset candidate threshold is determined according to a difference between a total length of the puncture needle and an external extension safety length.
7. The puncture path planning method based on ray casting and collision detection according to claim 6, further comprising: And in the candidate puncture path set, calculating the minimum value of the distance between each path and each hierarchical bounding volume, and determining the path with the maximum minimum value as the target puncture path.
8. A puncture path planning system based on ray casting and collision detection, comprising: The object segmentation module is used for acquiring a 3D voxel data model of an object to be punctured and carrying out focus and organ segmentation on the 3D voxel data model according to a pre-trained organ segmentation model; the ray projection module is used for generating uniformly distributed direction vectors from the center of a target focus in the segmented 3D voxel data model to the surrounding space by adopting a fibonacci spherical sampling algorithm to obtain an initial path set; And the path screening module is used for carrying out collision detection on each path in the initial path set, calculating the length of each path passing through the collision detection, and determining a candidate puncture path set according to the ascending order of the lengths of the paths and combining with a preset candidate threshold value.
9. A computer device comprising a memory and a processor, said memory and said processor being communicatively coupled to each other, said memory having stored therein computer instructions, said processor implementing a penetration path planning method based on ray casting and collision detection as claimed in any of claims 1-7 by executing said computer instructions.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the puncture path planning method based on ray casting and collision detection according to any of claims 1-7.

Description

Puncture path planning method and system based on ray projection and collision detection Technical Field The invention relates to the field of medical control, in particular to a puncture path planning method, a puncture path planning system, puncture path planning equipment and puncture path planning medium based on ray projection and collision detection. Background The medical puncture is used as a core technology of minimally invasive interventional diagnosis and treatment, has been widely applied to clinical scenes such as tumor biopsy, focus ablation, effusion drainage and the like, and realizes diagnosis sampling or local treatment with minimum trauma, thereby remarkably reducing the risk of traditional open surgery and the recovery period of patients. Along with the development of the deep and imaging technology and the robot technology of the precise medical concept, the clinic puts forward higher requirements on the precision, safety and dynamic adaptability of puncture path planning. In clinic, the ratio of the lesion sites of the small nodules with the diameter less than or equal to 10mm and located in the adjacent areas of important organs is improved year by year, such as lung-ground glass nodules, such as hepatic portal tumors and deep cerebral hematomas, the target point precision of a puncture path is extremely high, the accurate arrival of a puncture needle at the active area of the lesion sites rather than the necrotic area is ensured, peripheral blood vessels and nerves are prevented from being damaged, such as hepatic portal tumors need to avoid portal veins and bile ducts, and deep cerebral lesions need to avoid nerves of functional areas. Traditional path planning relies on doctor experience and combines two-dimensional image judgment, so that erroneous judgment is easy to cause target deviation due to space relation of anatomical structures, and further biopsy positive rate is low or treatment is incomplete. Furthermore, the complications of puncture are clinical core pain points, and the complications of traditional manual puncture mainly result from path deviation caused by the fact that the path does not avoid dangerous structures or organ displacement in operation. In view of this, there is a need for reducing the damage to blood vessels, nerves, and vital organs from the source through accurate path planning, and simultaneously reducing the risk of secondary puncture due to unreasonable paths, and alleviating the pain of patients. The above problems are to be solved. Disclosure of Invention In view of the above, the invention provides a puncture path planning method, a puncture path planning system and a puncture path planning storage medium based on ray projection and collision detection, so as to solve the technical problems of reliability, low efficiency and the like in puncture path planning in the prior art. In a first aspect, the present invention provides a puncture path planning method based on ray casting and collision detection, including: acquiring a 3D voxel data model of an object to be punctured, and dividing a focus and an organ by the 3D voxel data model according to a pre-trained organ dividing model; Generating uniformly distributed direction vectors from the center of a target focus in the segmented 3D voxel data model to the surrounding space by adopting a fibonacci sphere sampling algorithm to obtain an initial path set; and performing collision detection on each path in the initial path set, calculating the length of each path passing through the collision detection, and determining a candidate puncture path set according to the ascending sequence of the length of the paths and the preset candidate threshold value. As an alternative embodiment, after the performing focus and organ segmentation on the 3D voxel data model according to the pre-trained organ segmentation model, the method further includes: calculating arithmetic mean value of all vertex coordinates in the partitioned focus sub-model to obtain a focus geometric center point serving as the target focus center. As an alternative embodiment, further comprising: distributing corresponding attribute type identifiers for each segmented organ sub-model, wherein the attribute types comprise skin surfaces, static/arterial blood vessels, dangerous organs, penetration-allowing organs and bones; And constructing a corresponding hierarchical bounding volume for each forbidden organ sub-model according to the attribute category identification. As an optional implementation manner, after the generating of the uniformly distributed direction vectors and before the obtaining of the initial path set, the method further includes removing the invalid direction vectors according to a preset direction constraint; and determining an in-vivo puncture path from the body surface puncture entry point to the center of the target focus as an initial path according to the body surface puncture entry point where the single dir