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
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11497557-B2
Publication Date
2022-11-15
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 invention provides an end-to-end server/Web Application workflow for generating a 3D physical model of a patient specific anatomic feature from uploaded 2D medical images. A server receives the 2D medical images uploaded by an end-user via a Web Application and processes the images to automatically generate a 3D printable model of the patient specific anatomic feature.
Pixel segmentation is performed using a segmentation technique to classify pixels within the 2D medical images. An anatomic feature identification algorithm identifies the patient specific anatomic feature by probabilistically matching the classified pixels against a graph database of medical images anatomical features.
The workflow includes 3D printing of the generated 3D printable model as a 3D physical model such that the 3D physical model represents a 1:1 scale of the patient specific anatomic feature. The disclosure further supports the processing and identification workflow using components described for segmentation and anatomical feature identification, and provides downstream steps for producing print-ready physical models.
Claims Coverage
The partial content includes two independent claims: an end-user method and a computer implemented system. Across these independent claims, the inventive coverage centers on server-based receipt of 2D medical images via a Web Application/interface, segmentation with pixel classification and probabilistic patient-specific anatomic feature identification using a graph database, and 1:1 scale 3D printing of a patient-specific physical model.
Server-based generation of a 1:1 physical model from uploaded 2D medical images
A method comprising receiving, by a server, the 2D medical images uploaded by an end-user via a Web Application; processing, by the server, the 2D medical images to automatically generate a 3D printable model of a patient specific anatomic feature; and 3D printing the 3D printable model as a 3D physical model such that the 3D physical model represents a 1:1 scale of the patient specific anatomic feature.
Segmentation pixel classification with probabilistic graph database matching
Processing includes using a segmentation technique to classify pixels within the 2D medical images and an anatomic feature identification algorithm to identify the patient specific anatomic feature by probabilistically matching the classified pixels against a graph database of medical images anatomical features.
Interface-to-server processing and 3D printer execution in a computer implemented system
A computer implemented system comprising an interface module configured to receive 2D medical images and send them to a server; a server configured to process the 2D medical images to automatically generate a 3D printable model of a patient specific anatomic feature using a segmentation technique and an anatomic feature identification algorithm with probabilistic matching against a graph database; and a 3D printer configured to receive the 3D printable model and 3D print a 3D physical model representing a 1:1 scale of the patient specific anatomic feature.
The independent claim coverage is directed to server-based processing that segments and classifies pixels in 2D medical images and then probabilistically identifies a patient specific anatomic feature by matching against a graph database of anatomical features, followed by 3D printing of a 1:1 scale physical model; the system claim implements the same workflow via an interface module, server, and 3D printer.
Stated Advantages
Automatically generating a 3D printable model of a patient specific anatomic feature from uploaded 2D medical images.
Identifying the patient specific anatomic feature by probabilistically matching classified pixels against a graph database of medical images anatomical features.
Producing a 3D physical model that represents a 1:1 scale of the patient specific anatomic feature.
Documented Applications
Generating dental/orthodontic models based on medical imaging workflows described in the disclosure.
Generating calibration phantoms based on CT/MRI calibration workflows described in the disclosure.
Interested in licensing this patent?