Machine learning detection and classification of maxillofacial bone lesions in CBCT
A computer-implemented method comprising: receiving a plurality of CBCT scans, each comprising a series of axial slices, wherein the CBCT scans are associated with a cohort of subjects comprising a first subgroup of subjects having each one or more maxillofacial bone lesions, and a second subgroup o...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | English |
Published |
26.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | A computer-implemented method comprising: receiving a plurality of CBCT scans, each comprising a series of axial slices, wherein the CBCT scans are associated with a cohort of subjects comprising a first subgroup of subjects having each one or more maxillofacial bone lesions, and a second subgroup of subjects having no maxillofacial bone lesions; applying a feature extraction operation to extract a set of features from the axial slices in each of the CBCT scans; at a training stage, training a machine learning model on a training dataset comprising: (i) all of the extracted sets of features, and (ii) annotations indicating boundaries of bone lesions in the axial slices, to obtain a trained machine learning model configured to detect and segment a bone lesion in an axial slice from a CBCT scan. |
---|---|
Bibliography: | Application Number: US202318312260 |