Method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images

Inventors

HASLAM, Niall • TROJAN, Lorenzo • CRAWFORD, Daniel

Assignees

Axial Medical Printing Ltd

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Publication Number

US-12277712-B2

Patent

Publication Date

2025-04-15

Expiration Date


Abstract

There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.

Core Innovation

The described invention provides a computer-implemented method for defining patient specific anatomical features from medical images by receiving medical images and information on bone and/or soft tissue of a patient. The method applies the information as an input to a segmentation algorithm that automatically processes the medical images to assign a label for each pixel based at least partially on the bone and/or soft tissue, and the segmentation algorithm includes a convolutional Neural Network method trained from a database of existing medical images that have been labelled and a medical imaging ontology.

After pixel labeling, the method accesses a database of medical image anatomical features and uses an anatomical feature identification algorithm to probabilistically match the labeled pixels against the database. This probabilistic matching generates segmentation data that defines one or more patient specific anatomical features comprising the bone and/or soft tissue based on the labeled pixels, and the method then generates a 3D model of the one or more patient specific anatomical features using the generated segmentation data.

In parallel, the disclosed invention includes a system with at least one processor configured to perform the same core workflow: receive medical images and information on bone and/or soft tissue, apply the information to the segmentation algorithm with a convolutional Neural Network trained using a database of labelled images and a medical imaging ontology, and use the anatomical feature identification algorithm to probabilistically match labeled pixels against a database of anatomical features. The system generates segmentation data defining one or more patient specific anatomical features and generates a 3D model based on that segmentation data.

Claims Coverage

The partial set includes two independent claims, a computer-implemented method and a corresponding system. Across the claims, the core inventive features are centered on CNN-based pixel labeling using a medical imaging ontology, probabilistic anatomical feature identification against a database, and generating a 3D model from the generated segmentation data.

Pixel labeling with CNN trained on labeled images and medical imaging ontology

Applying patient bone and/or soft tissue information as an input to a segmentation algorithm to automatically process the medical images and assign a label for each pixel, wherein the segmentation algorithm includes a convolutional Neural Network method trained from a database of existing medical images that have been labelled and a medical imaging ontology.

Probabilistic anatomical feature identification against an anatomical feature database

Using an anatomical feature identification algorithm to probabilistically match the labeled pixels of the medical images against a database of medical image anatomical features to generate segmentation data that defines one or more patient specific anatomical features based on the labeled pixels of the medical images.

Generating a 3D model from segmentation data defining patient-specific features

Generating a 3D model of the one or more patient specific anatomical features comprising the bone and/or soft tissue using the generated segmentation data.

System implementing the method with processors

A system comprising at least one processor configured to receive medical images and information on bone and/or soft tissue of a patient, apply the information as an input to a segmentation algorithm including a convolutional Neural Network method trained from a database of existing medical images that have been labelled and a medical imaging ontology, use an anatomical feature identification algorithm to probabilistically match the labeled pixels against a database of medical image anatomical features to generate segmentation data defining one or more patient specific anatomical features, and generate a 3D model using the generated segmentation data.

The claim coverage focuses on a CNN-based segmentation that labels each pixel using a medical imaging ontology, followed by probabilistic anatomical feature identification against an anatomical-feature database to produce segmentation data defining patient-specific anatomical features, and generating a 3D model of those features.

Stated Advantages

Not explicitly described in patent.

Documented Applications

Generating 1:1, 3D printable patient-specific anatomic models from 2D DICOM medical images, including producing 3D surfaces/meshes and printing physical models.

Extending applications to dentistry/orthodontics.

Using phantoms for imaging calibration.

Surgical training, including surgical training with augmented reality/haptic feedback.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.