Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics across five cancer types. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment and can predict diverse molecular signatures (AUROC 0.601–0.864), including expression of four immune checkpoint proteins and homologous recombination deficiency, with performance comparable to ‘black-box’ methods. Our HIF-based approach provides a comprehensive, quantitative, and interpretable window into the composition and spatial architecture of the tumor microenvironment.
The superoxide dismutase mimetic manganese [III] tetrakis [5,10,15,20]-benzoic acid porphyrin (MnTBAP) is a potent antioxidant compound that has been shown to limit weight gain during short-term high fat feeding without preventing insulin resistance. However, whether MnTBAP has therapeutic potential to treat pre-existing obesity and insulin resistance remains unknown. To investigate this, mice were treated with MnTBAP or vehicle during the last five weeks of a 24-week high fat diet (HFD) regimen. MnTBAP treatment significantly decreased body weight and reduced white adipose tissue (WAT) mass in mice fed a HFD and a low fat diet (LFD). The reduction in adiposity was associated with decreased caloric intake without significantly altering energy expenditure, indicating that MnTBAP decreases adiposity in part by modulating energy balance. MnTBAP treatment also improved insulin action in HFD-fed mice, a physiologic response that was associated with increased protein kinase B (PKB) phosphorylation and expression in muscle and WAT. Since MnTBAP is a metalloporphyrin molecule, we hypothesized that its ability to promote weight loss and improve insulin sensitivity was regulated by heme oxygenase-1 (HO-1), in a similar fashion as cobalt protoporphyrins. Despite MnTBAP treatment increasing HO-1 expression, administration of the potent HO-1 inhibitor tin mesoporphyrin (SnMP) did not block the ability of MnTBAP to alter caloric intake, adiposity, or insulin action, suggesting that MnTBAP influences these metabolic processes independent of HO-1. These data demonstrate that MnTBAP can ameliorate pre-existing obesity and improve insulin action by reducing caloric intake and increasing PKB phosphorylation and expression.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.