# US 2026/0203909 A1 · Automatic generation of 3d anatomical models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0203909 A1
- Document ID: US20260203909A1
- Status: Published application
- Kind: A1
- Application number: 19/137,695
- Filed: 2023-12-20
- Published: 2026-07-16
- Earliest claimed: 2022-12-22
- Assignees: Assistance Publique-Hopitaux de Paris; Institut National de la Sante et de la Recherche Medicale; Université Paris Cité; Imagine Institut Des Maladies Genetiques Necker Enfants Malades; Institut Mines-Telecom; Sorbonne Universite; Centre National De La Recherche Scientifique
- Applicants: Assistance Publique Hopitaux De Paris; Institut National De La Sante Et De La Recherche Medicale; Universite Paris Cite; Imagine Institut Des Maladies Genetiques Necker Enfants Malades; Institut Mines Telecom; Sorbonne Universite; Centre National De La Recherche Scientifique
- Inventors: Alessandro DELMONTE; Sabine SARNACKI; Isabelle BLOCH; Pietro GORI; Cécile MULLER; Alessio VIRZI; Giammarco LA BARBERA; Enzo BONNOT
- Web page: https://patentgrep.com/patent/US20260203909A1

## CPC

- G06T 7/11: Region-based segmentation
- G06T 15/00: Three-dimensional [3D] image rendering
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30004: Biomedical image processing
- G06T 2207/30008: Bone
- G06T 2207/30081: Prostate
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06T 2207/30104: Vascular flow; Blood flow; Perfusion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for generating a 3D anatomical models using segmented images representing anatomical structures and 3D representation of fibers is disclosed. The method comprises obtaining an input image of said anatomical region of interest and a 3D representation of fibers in an anatomical region of interest; performing a segmentation of the input image to generate a first, second and third segmented images by detecting voxels that represent respectively a bone, an organ or a vessel and using respectively a first, second and third segmentation neural network applied to the input image; performing a segmentation of the input image to generate a fourth segmented image by detecting voxels that represent a bone, an organ or a vessel using a fourth segmentation neural network; generating an aggregated segmented image by combining the segmented images; performing a nerve detection in a 3D representation of fibers in an anatomical region of interest using a nerve definition and transforming the said nerve definition into 3D fuzzy search space composed by one or more 3D fuzzy areas. The 3D anatomical model is generated using the aggregated segmented image and the detected fibers representing the nerves.

## Claims

### Claim 1

A method for generating a 3D anatomical model of an anatomical region of interest, the method comprising:
obtaining an input image of said anatomical region of interest and a 3D representation of fibers in said anatomical region of interest;
generating an aggregated segmented image representing anatomical structures including at least one bone, at least one organ or at least one vessel;
detecting at least one fiber representing a nerve in said 3D representation of fibers in the anatomical region of interest,
generating said 3D anatomical model using the aggregated segmented image and the detected at least one fiber representing a nerve;
wherein generating the aggregated segmented image comprises:
performing a segmentation of the input image to generate a first segmented image by detecting voxels that represent a bone using a first segmentation neural network applied to the input image, wherein the first segmentation neural network is a bones specific neural network trained to detect one or more bones in an image;
performing a segmentation of the input image to generate a second segmented image by detecting voxels that represent an organ using a second segmentation neural network applied to the input image, wherein the second segmentation neural network is an organ specific neural network trained to detect one or more organs in an image;
performing a segmentation of the input image to generate a third segmented image by detecting voxels that represent a vessel using a third segmentation neural network applied to the input image, wherein the third segmentation neural network is a vessel specific neural network trained to detect one or more vessels in an image;
performing a segmentation of the input image to generate a fourth segmented image by detecting voxels that represent a bone, an organ or a vessel using a fourth segmentation neural network applied to the input image, wherein the fourth segmentation neural network is a multi-structure neural network trained to detect bones, vessels and at least one organ in an image;
combining the first, second, third and fourth segmented images;
wherein detecting said at least one fiber representing said nerve comprises:
obtaining a nerve definition expressed in the form of one or more spatial relationships between said nerve and one or more anatomical structures segmented in the aggregated segmented image;
detecting that said at least one fiber satisfies the nerve definition based on at least one fuzzy 3D anatomical area corresponding to the one or more spatial relationships expressed in said nerve definition.

### Claim 2 (depends on 1)

The method according to claim 1, wherein detecting at least one fiber satisfying the nerve definition comprises searching fibers in a 3D search space defined by said at least one fuzzy 3D anatomical area.

### Claim 3 (depends on 1)

A method according to claim 1- or 2, wherein the method comprises:
extracting each anatomical structure used in said nerve definition from the aggregated segmented image;
obtaining a segmentation mask from each extracted anatomical structure;
obtaining a fuzzy anatomical 3D area expressing a given spatial relationship of the nerve definition by dilating the segmentation mask based on a structuring element, said structuring element encoding at least one of a direction information, path information and connectivity information of the given spatial relationship.

### Claim 4 (depends on 1)

A method according to claim 1, wherein a dilation score is associated to each voxel in the at least one fuzzy anatomical 3D area, wherein the method comprises
computing, for each of the at least one fiber that falls in the at least one fuzzy anatomical 3D area, a fiber score based on dilation scores of voxels representing the considered fiber.
detecting that a nerve is represented by at least one fiber when said fiber is fully or partly within at least one fuzzy anatomical area and has a fiber score higher than a threshold.

### Claim 5 (depends on 1)

A method according to claim 1, wherein the nerve definition comprises a sequence of nerve sub-definitions, each nerve sub-definition being associated to a portion of the nerve,
the method comprising, for a first portion of the nerve with an associated first sub-definition that expresses at least one first spatial relationship between said first portion of the nerve and at least one first anatomical structure segmented in the aggregated segmented image:
a) obtaining a segmentation mask of the at least one first anatomical structure;
b) obtaining at least one first local fuzzy anatomical 3D area expressing the at least one first spatial relationship by dilating the segmentation mask based on a structuring element, the structuring element encoding at least one of a direction information, path information and connectivity information of the given spatial relationship;
c) computing, for each of a plurality of fibers, a fiber score based on dilation scores of voxels representing the considered fiber that fall in a first fuzzy anatomical 3D area defined by at the at least one first local fuzzy 3D anatomical area;
d) for at least one of the plurality of fibers, detecting that the first portion of the nerve is represented by the considered fiber when the considered fiber is fully or partly within the first fuzzy anatomical 3D area and has a fiber score higher than a threshold;
the method comprising: repeating steps a) to d) for a second portion of the nerve and by using the at least one fiber detected for the first portion to limit the plurality of fibers for which the fiber score is computed.

### Claim 6 (depends on 3)

A method according to claim 3, wherein the segmentation mask of the at least one anatomical structure is a fuzzy segmentation mask of the at least one anatomical structure, wherein the method comprises:
obtaining an initial segmentation mask by extraction of the at least one anatomical structure from the aggregated segmented image;
obtaining a dilated segmentation mask by dilating said initial segmentation mask based on a structuring element; and
extracting from said dilated segmented mask the voxels corresponding to the initial segmentation mask and normalizing said extracted voxels,
defining said fuzzy segmentation mask as said normalized extracted voxels.

### Claim 7 (depends on 1)

A method according to claim 1, wherein each voxel in the aggregated segmented image is a corresponding voxel of the fourth segmented image if the corresponding voxels in the first, second, third segmented images are detected as representing distinct anatomic structures.

### Claim 8 (depends on 1)

A method according to claim 1, wherein one or more or each of the first, second, third and fourth segmentation neural network has been trained using a loss function defined as a weighted sum of specific loss functions, wherein weighting coefficients of the weighted sum are specific to the considered segmentation neural network.

### Claim 9 (depends on 8)

A method according to claim 8, wherein a first specific loss function measures an accuracy based on global and local information over a 3D volume in a reference segmented image and a current segmented image.

### Claim 10 (depends on 8)

A method according to claim 8, wherein a second specific loss function measures local consistency between voxels in a reference segmented image and a current segmented image.

### Claim 11 (depends on 8)

A method according to claim 8, wherein a third specific loss function measures a distance between boundary points of a reference segmented image and a current segmented image.

### Claim 12 (depends on 8)

A method according to claim 8, wherein the weighting coefficients vary dynamically during the training of the segmentation neural networks.

### Claim 13 (depends on 1)

A method according to claim 1, wherein one or more or each of the first, second, third and fourth segmentation neural networks has been trained using image patches extracted from the input image, wherein the centers of the image patches have coordinates determined using a sampling algorithm adapted to the type of anatomic structure to be detected by the considered segmentation neural networks.

### Claim 14 (depends on 1)

A method according to claim 1, the method comprising:
determining for the input image a bounding box of interest using a deep regression network;
applying one or more or each of the first, second, third and fourth segmentation neural networks only to the bounding box of interest.

### Claim 15 (depends on 1)

A method according to claim 1, the method comprising:
displaying a segmented image generated by one of the segmentation neural networks, the concerned segmentation neural network including one or more additional convolutional layers whose output are merged respectively with inputs of corresponding encoder blocks of the concerned segmentation neural network;
generating a segmentation mask of an anatomical structure in the segmented image;
allowing a user to select in the displayed segmented image one or more voxels encoded as a false positive or false negative;
providing the segmentation mask and the selected voxels as input image to the one or more additional convolutional layers.

### Claim 16 (depends on 1)

A method according to claim 1, wherein generating the aggregated segmented image further comprises:
refining at least one of the first, second, third and fourth segmented images by using an iterative or automatic refinement process before combining the first, second, third and fourth segmented images.

### Claim 17 (depends on 1)

A method according to claim 1, wherein each of the first, second, third and fourth segmentation neural networks is a 3D convolutional neural network, CNN.

### Claim 18 (depends on 17)

A method according to claim 17, wherein one or more or each of the first, second, third and fourth 3D CNNs is based on a U-Net architecture.

### Claim 19 (depends on 1)

A method according to claim 1, comprising:
obtaining the 3D representation of fibers by applying a tractography algorithm to a diffusion weighted MR image inside a convex hull corresponding to the anatomical region of interest enveloping anatomical structures that has been segmented in the aggregated segmented image and by using random seed points for the tractography algorithm on the convex hull.

### Claim 20

An apparatus comprising at least one processor and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to generate a 3D anatomical model of an anatomical region of interest by:
obtaining an input image of said anatomical region of interest and a 3D representation of fibers in said anatomical region of interest;
generating an aggregated segmented image representing anatomical structures including at least one bone, at least one organ or at least one vessel;
detecting at least one fiber representing a nerve in said 3D representation of fibers in the anatomical region of interest. generating said 3D anatomical model using the aggregated segmented image and the detected at least one fiber representing a nerve;
wherein generating the aggregated segmented image comprises:
performing a segmentation of the input image to generate a first segmented image by detecting voxels that represent a bone using a first segmentation neural network applied to the input image, wherein the first segmentation neural network is a bones specific neural network trained to detect one or more bones in an image;
performing a segmentation of the input image to generate a second segmented image by detecting voxels that represent an organ using a second segmentation neural network applied to the input image, wherein the second segmentation neural network is an organ specific neural network trained to detect one or more organs in an image;
performing a segmentation of the input image to generate a third segmented image by detecting voxels that represent a vessel using a third segmentation neural network applied to the input image, wherein the third segmentation neural network is a vessel specific neural network trained to detect one or more vessels in an image;
performing a segmentation of the input image to generate a fourth segmented image by detecting voxels that represent a bone, an organ or a vessel using a fourth segmentation neural network applied to the input image, wherein the fourth segmentation neural network is a multi-structure neural network trained to detect bones, vessels and at least one organ in an image;
combining the first, second, third and fourth segmented images;
wherein detecting said at least one fiber representing said nerve comprises:
obtaining a nerve definition expressed in the form of one or more spatial relationships between said nerve and one or more anatomical structures segmented in the aggregated segmented image;
detecting that said at least one fiber satisfies the nerve definition based on at least one fuzzy 3D anatomical area corresponding to the one or more spatial relationships expressed in said nerve definition.
