Skip to main contentdfsdf

dr tech

Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides | Nature Communications

"Cancer diagnosis and management depend upon the extraction of complex information from microscopy images by pathologists, which requires time-consuming expert interpretation prone to human bias. Supervised deep learning approaches have proven powerful, but are inherently limited by the cost and quality of annotations used for training. Therefore, we present Histomorphological Phenotype Learning, a self-supervised methodology requiring no labels and operating via the automatic discovery of discriminatory features in image tiles. Tiles are grouped into morphologically similar clusters which constitute an atlas of histomorphological phenotypes (HP-Atlas), revealing trajectories from benign to malignant tissue via inflammatory and reactive phenotypes. These clusters have distinct features which can be identified using orthogonal methods, linking histologic, molecular and clinical phenotypes. Applied to lung cancer, we show that they align closely with patient survival, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype. These properties are maintained in a multi-cancer study."

Shared by dr tech, 1 save total

dr tech

UK startup uses AI to discover new rare earth-free magnet for EVs

"A UK-based startup has used an AI algorithm to identify a previously unknown kind of rare-earth free magnet, in a potential breakthrough for how we discover and create new materials.

Materials Nexus, headquartered in London, used its machine learning algorithm to identify and analyse over 100 million combinations of materials that could produce a viable rare-earth free magnet."

Shared by dr tech, 1 save total

Show more items

Highlighter, Sticky notes, Tagging, Groups and Network: integrated suite dramatically boosting research productivity. Learn more »

Join Diigo