CPC G16H 50/20 (2018.01) [A61B 34/10 (2016.02); G06N 3/08 (2013.01); G06Q 20/102 (2013.01); G06Q 30/0185 (2013.01); G06T 7/0012 (2013.01); G16H 10/40 (2018.01); G16H 15/00 (2018.01); G16H 30/40 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); G16H 70/60 (2018.01); H04L 63/08 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30096 (2013.01)] | 20 Claims |
1. A method for generating, with a processor, a model of tissue for use in diagnostic and surgical clinical and research procedures comprising the steps of:
receiving whole slide images (WSI) of tissue removed from a patient or a research specimen;
determining, using a machine learning process operating on the processor and trained on a set of tissue type-separated images,
(a) if each image of the WSI is of a tissue type that contains complete or incomplete tissue samples, based on a sample completeness score thereof, and
(b) if each of a plurality of segments of the image of the WSI is of a tissue type that contains tumorous tissue or an absence of tumorous tissue based on a margin analysis thereof;
generating, with the processor, a visual model of the removed tissue based on a plurality of the WSI containing complete tissue samples prepared in a sequence, the visual model mapping of types tissue segments determined by the machine learning process across adjacent WSI in the prepared sequence; and
facilitating use and manipulation of the visual model by a user in an interactive interface via a display under control of the processor, or use in a pathology report.
|