In Nature communications ; h5-index 260.0
A model's ability to express its own predictive uncertainty is an essential attribute for maintaining clinical user confidence as computational biomarkers are deployed into real-world medical settings. In the domain of cancer digital histopathology, we describe a clinically-oriented approach to uncertainty quantification for whole-slide images, estimating uncertainty using dropout and calculating thresholds on training data to establish cutoffs for low- and high-confidence predictions. We train models to identify lung adenocarcinoma vs. squamous cell carcinoma and show that high-confidence predictions outperform predictions without uncertainty, in both cross-validation and testing on two large external datasets spanning multiple institutions. Our testing strategy closely approximates real-world application, with predictions generated on unsupervised, unannotated slides using predetermined thresholds. Furthermore, we show that uncertainty thresholding remains reliable in the setting of domain shift, with accurate high-confidence predictions of adenocarcinoma vs. squamous cell carcinoma for out-of-distribution, non-lung cancer cohorts.
Dolezal James M, Srisuwananukorn Andrew, Karpeyev Dmitry, Ramesh Siddhi, Kochanny Sara, Cody Brittany, Mansfield Aaron S, Rakshit Sagar, Bansal Radhika, Bois Melanie C, Bungum Aaron O, Schulte Jefree J, Vokes Everett E, Garassino Marina Chiara, Husain Aliya N, Pearson Alexander T
2022-Nov-02
