It appears you don't have support to open PDFs in this web browser. To view this file, Open with your PDF reader
Abstract
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.
Safe clinical deployment of deep learning models for digital pathology requires reliable estimates of predictive uncertainty. Here the authors describe an algorithm for quantifying whole-slide image uncertainty, demonstrating their approach with models trained to distinguish lung cancer subtypes.
You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer
Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer
Details






1 University of Chicago Medical Center, Section of Hematology/Oncology, Department of Medicine, Chicago, USA (GRID:grid.412578.d) (ISNI:0000 0000 8736 9513)
2 Icahn School of Medicine at Mount Sinai, Tisch Cancer Institute, New York, USA (GRID:grid.59734.3c) (ISNI:0000 0001 0670 2351)
3 DV Group, LLC, Chicago, USA (GRID:grid.59734.3c)
4 University of Chicago, Department of Pathology, Chicago, USA (GRID:grid.170205.1) (ISNI:0000 0004 1936 7822)
5 Mayo Clinic, Division of Medical Oncology, Rochester, USA (GRID:grid.66875.3a) (ISNI:0000 0004 0459 167X)
6 Mayo Clinic, Department of Laboratory Medicine and Pathology, Rochester, USA (GRID:grid.66875.3a) (ISNI:0000 0004 0459 167X)
7 Mayo Clinic, Divisions of Pulmonary Medicine and Critical Care, Rochester, USA (GRID:grid.66875.3a) (ISNI:0000 0004 0459 167X)
8 University of Wisconsin at Madison, Department of Pathology and Laboratory Medicine, Madison, USA (GRID:grid.14003.36) (ISNI:0000 0001 2167 3675)