PathAI has been granted a patent for a method that uses machine learning to predict tissue characteristics in pathology images. The method involves training a statistical model using annotated pathology images and their corresponding annotations. The trained model can then be used to predict various entities of interest, such as survival time, drug response, and patient clinical outcomes, based on the features extracted from the pathology images. The predicted entities of interest are stored on a storage device. GlobalData’s report on PathAI gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
According to GlobalData’s company profile on PathAI, AI-assisted medical imaging was a key innovation area identified from patents. PathAI's grant share as of September 2023 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
Predicting tissue characteristics for pathology images using machine learning
A recently granted patent (Publication Number: US11756198B1) describes a method and system for predicting an entity of interest for a pathology image using machine learning. The method involves receiving an annotated pathology image with one or more annotations, extracting values for various features from the image, and retrieving a machine learning model from storage. The extracted feature values are then processed using the machine learning model to predict an entity of interest, such as survival time, drug response, patient level phenotype/molecular characteristics, or patient clinical outcomes. The predicted entity of interest is stored on a storage device.
The method also includes training the machine learning model using extracted feature values from a plurality of annotated training pathology images collected from patients participating in a randomized controlled clinical trial. The training may also incorporate clinical metadata values associated with the trial participants, as well as genomic, transcriptomic, and/or protein expression data. The machine learning model is specifically trained to output survival time.
The features extracted from the annotated pathology image include various measurements such as the area of epithelium, stroma, necrosis, cancer cells, macrophages, and lymphocytes. Other features include the number of mitotic figures, average nuclear grade, average distance between fibroblasts and lymphocytes, average distance between immunohistochemistry-positive macrophages and cancer cells, standard deviation of nuclear grade, and average distance between blood vessels and tumor cells.
The system described in the patent includes at least one computer hardware processor and a non-transitory computer-readable storage medium. The storage medium stores processor-executable instructions that enable the processor to perform the steps of receiving an annotated pathology image, extracting feature values, retrieving a trained machine learning model, processing the feature values using the model to predict an entity of interest, and storing the predicted entity of interest.
Overall, this patent presents a method and system for predicting various entities of interest in pathology images using machine learning. By training the model on annotated training pathology images and incorporating additional data sources, the system aims to provide accurate predictions for survival time, drug response, patient characteristics, and clinical outcomes.
To know more about GlobalData’s detailed insights on PathAI, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies
