System and method for diagnosing, monitoring, screening for or evaluating a musculoskeletal disease or condition
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11727562-B2
Publication Date
2023-08-15
Expiration Date
Abstract
A computer-implemented image analysis method and system. The method comprises: quantifying one or more features segmented and identified from a medical image of a subject; extracting clinically relevant features from non-image data pertaining to the subject; assessing the features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model; and outputting one or more results of the assessing of the features.
Core Innovation
The invention provides a computer-implemented musculoskeletal disease or condition assessment that uses medical image analysis and non-image patient data. One or more features are quantified from features segmented and identified from a medical image of a subject, while non-image data pertaining to the subject and pertinent to the musculoskeletal disease or condition is extracted from one or more non-image data sources and clinically relevant features are extracted from the non-image data.
The quantified features from the medical image and the clinically relevant features from the non-image data are assessed together using a trained machine learning model. The trained machine learning model is trained to diagnose, monitor, screen for or evaluate musculoskeletal diseases or conditions, and the results of the diagnosing, monitoring, screening for or evaluating are output as one or more results.
In related embodiments, the approach includes segmenting and identifying the one or more features from the medical image using a trained machine learning model, including a deep convolutional neural network. The trained machine learning model may further be a disease classification model, including a deep learning neural network and/or other machine learning algorithms, and can be updated using additional labelled data derived from new or newly analysed subject data.
Claims Coverage
The independent claims cover four inventive features: a computer-implemented method and corresponding system for diagnosing, monitoring, screening for, or evaluating a musculoskeletal disease or condition, and an analogous method and system for determining a treatment or producing guidelines for treatment. Across the claims, the key inventive features are trained-machine-learning assessment of both segmented medical image features and extracted non-image clinically relevant features, with output of one or more results.
Quantifying segmented and identified medical image features and extracting clinically relevant non-image features
A computer-implemented method comprising quantifying one or more features segmented and identified from a medical image of a subject; extracting non-image data pertaining to the subject and pertinent to the musculoskeletal disease or condition from one or more non-image data sources; extracting clinically relevant features from the non-image data; diagnosing, monitoring, screening for or evaluating the musculoskeletal disease or condition by assessing the quantified features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model; and outputting one or more results.
Feature quantifier, non-image data processor, feature assessor and output for combined assessment
A system comprising a feature quantifier configured to quantify one or more features segmented and identified from a medical image of a subject; a non-image data processor configured to extract non-image data pertaining to the subject and pertinent to the musculoskeletal disease or condition from one or more non-image data sources and to extract clinically relevant features from the non-image data; a feature assessor configured to diagnose, monitor, screen for or evaluate the musculoskeletal disease or condition by assessing the quantified features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model trained to diagnose, monitor, screen for or evaluate one or more musculoskeletal diseases or conditions; and an output configured to output one or more results.
Determining treatment or producing treatment guidelines using combined image and non-image features
A computer-implemented method comprising quantifying one or more features segmented and identified from a medical image of a subject; extracting non-image data pertaining to the subject and pertinent to the musculoskeletal disease or condition from one or more non-image data sources; extracting clinically relevant features from the non-image data; determining a treatment, or producing guidelines for treatment of, the musculoskeletal disease or condition by assessing the quantified features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model trained to determine a treatment, or produce guidelines for treatment of, one or more musculoskeletal diseases or conditions; and outputting one or more results of the determining a treatment, or producing guidelines for treatment of.
System for treatment determination or treatment guideline production
A system comprising a feature quantifier configured to quantify one or more features segmented and identified from a medical image of a subject; a non-image data processor configured to extract non-image data pertaining to the subject and pertinent to the musculoskeletal disease or condition from one or more non-image data sources and to extract clinically relevant features from the non-image data; a feature assessor configured to determine a treatment, or produce guidelines for treatment of, the musculoskeletal disease or condition by assessing the quantified features segmented from the medical image and the features extracted from the non-image data with a trained machine learning model trained to determine a treatment, or produce guidelines for treatment of, one or more musculoskeletal diseases or conditions; and an output configured to output one or more results of the determining a treatment, or producing guidelines for treatment of.
Overall, the independent claims focus on combining quantified segmented and identified medical image features with clinically relevant features extracted from non-image data, and using a trained machine learning model to output results for diagnosing, monitoring, screening for or evaluating, or for determining treatment or producing treatment guidelines.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?