Memorial Sloan Kettering Cancer Center had six patents in artificial intelligence during Q3 2023. The patent abstracts describe systems and methods for identifying regions of interest in images, particularly biomedical images of tissue samples. The techniques involve analyzing and extracting patches of images that correspond to regions of interest, while disqualifying patches that do not include features of interest or include disqualifying features. The relevant patches can be analyzed individually or in parallel to determine the pixels that correspond to features of interest. GlobalData’s report on Memorial Sloan Kettering Cancer Center gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Memorial Sloan Kettering Cancer Center grant share with artificial intelligence as a theme is 17% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Identifying regions of interest from whole slide images (Patent ID: US20230252807A1)
The patent application from the Memorial Sloan Kettering Cancer Center describes systems and methods for identifying regions of interest in images, particularly biomedical images of tissue samples. The techniques involve obtaining patches of images that are adjacent to each other and identified as candidate regions of interest (ROIs). A feature detection process is applied to these patches to determine a first set of interest points. Another set of patches is obtained, and a second set of interest points is identified from a predetermined ROI in these patches. The first set of interest points is compared with the second set to find matching interest points. An association between the candidate ROI and the predetermined ROI is stored based on the matching interest points.
The method also includes determining whether the number of matching interest points satisfies a threshold number. If it does not, it is determined that the first set of patches does not correspond to the second set of patches. On the other hand, if the number of matching interest points satisfies the threshold number, an image registration process is performed to determine a correspondence between the first set of patches and the second set of patches.
The system described in the patent application includes a data processing system with processors and memory. This system is configured to obtain the first set of patches, apply the feature detection process, identify the second set of interest points, compare the sets of interest points, and store the association between the candidate ROI and the predetermined ROI.
Additional features of the method and system include performing an image registration process to determine the number of inliers between the sets of interest points, determining overlap between the candidate ROI and the predetermined ROI, and performing multiple iterations of the image registration process. The feature detection process can utilize techniques such as speeded up robust features (SURF), scale-invariant feature transform (SIFT), or convolutional neural network (CNN). The system can also select subsets of patches based on magnification factors and determine a quality control metric for the patches.
Overall, the patent application describes a comprehensive approach to identifying and analyzing regions of interest in biomedical images, allowing for efficient and accurate analysis of tissue samples.
To know more about GlobalData’s detailed insights on Memorial Sloan Kettering Cancer Center, 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 across the world’s largest industries.
