Apparatus and methods for identifying abnormal biomedical features within images of biomedical data
Inventors
Vaidya, Suthirth • Barve, Rakesh
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12310736-B1
Publication Date
2025-05-27
Expiration Date
Abstract
Apparatus for identification of abnormal biomedical features within images of biomedical data and methods used therein are described. The apparatus includes an image capture device, a processor connected to the image capture device, a memory connected to the processor, and a display device connected to the processor. The image capture device is configured to capture an image of biomedical data. The memory contains instructions configuring the processor to receive the image, extract a plurality of biomedical features from the biomedical data, receive repository data from a medical repository as a function of the plurality of biomedical features, generate at least a distance metric as a function of the plurality of biomedical features and the repository data, and highlight at least a biomedical feature within the image as a function of the at least a distance metric.
Core Innovation
An apparatus identifies at least one abnormal biomedical feature within at least one image of biomedical data for a first patient. The apparatus captures the at least one image of biomedical data, extracts a plurality of biomedical features from the biomedical data, and receives repository data from a medical repository as a function of the plurality of biomedical features. The apparatus generates at least one distance metric as a function of the plurality of biomedical features and the repository data.
The apparatus highlights the at least one abnormal biomedical feature within the at least one image as a function of the at least one distance metric and displays the at least one highlighted abnormal biomedical feature on a display device. The apparatus identifies within the medical repository at least one second patient associated with at least one similar distance metric. The identifying comprises matching a first set of statistical parameters extracted as a function of the at least one image with a second set of statistical parameters extracted as a function of the at least one image associated with the at least one second patient using a statistical model.
Related implementations describe distance metrics and highlighting tied to hypotheses and labels, biomedical data including electrocardiogram (ECG) and time series data, and transforming biomedical parameters and signals into an in-silicon image with quality diagnostic information. The document further describes using trained feature extraction models and visualization with color-coded heat maps and user interface query-driven highlighting to present abnormal biomedical features.
Claims Coverage
The document includes two independent claims that cover both an apparatus and a method. Across the independent claims, the core inventive features total 7: image capture, biomedical feature extraction, repository-data-driven distance metrics, distance-metric-based abnormal-feature highlighting, second-patient identification using statistical-parameter matching with a statistical model, and display of highlighted results.
Distance-metric-driven highlighting of abnormal biomedical features
Generate at least one distance metric as a function of the plurality of biomedical features and the repository data and highlight the at least one abnormal biomedical feature within the at least one image as a function of the at least one distance metric.
Repository-data retrieval as a function of extracted biomedical features
Receive repository data from a medical repository as a function of the plurality of biomedical features.
Statistical model matching of patient-associated statistical parameters
Identify within the medical repository at least one second patient associated with at least one similar distance metric, where identifying comprises matching a first set of statistical parameters extracted as a function of the at least one image with at least one second set of statistical parameters extracted as a function of at least one image associated with the at least one second patient using a statistical model.
Biomedical image capture for a first patient
Capture the at least one image of biomedical data pertaining to a first patient.
Biomedical feature extraction from biomedical data
Extract a plurality of biomedical features from the biomedical data as a function of the biomedical data.
Display of highlighted abnormal biomedical features
Display the at least one highlighted abnormal biomedical feature within the at least one image.
The independent claims are centered on computing distance metrics using repository data tied to extracted biomedical features, using those distance metrics to highlight abnormal biomedical features within the biomedical image, and identifying similar second patients by matching statistical parameters with a statistical model. The method and apparatus structures differ, but both independently require image capture, feature extraction, repository-data input, distance-metric generation, abnormal-feature highlighting, and display.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?