Exploring Instance-Level Uncertainty for Medical Detection
This work provides an incremental improvement in lung nodule detection for clinicians by enhancing the reliability and performance of deep learning models through instance-level uncertainty estimation.
This paper addresses the limited application of uncertainty estimation in bounding-box-based medical detection by augmenting a 2.5D detection CNN with predictive variance and Monte Carlo sample variance. The method improved lung nodule detection on the LUNA16 dataset from 84.57% to 88.86% by combining both variance types, and further boosted performance to 89.52% by leveraging the generated uncertainty for superior operating points.
The ability of deep learning to predict with uncertainty is recognized as key for its adoption in clinical routines. Moreover, performance gain has been enabled by modelling uncertainty according to empirical evidence. While previous work has widely discussed the uncertainty estimation in segmentation and classification tasks, its application on bounding-box-based detection has been limited, mainly due to the challenge of bounding box aligning. In this work, we explore to augment a 2.5D detection CNN with two different bounding-box-level (or instance-level) uncertainty estimates, i.e., predictive variance and Monte Carlo (MC) sample variance. Experiments are conducted for lung nodule detection on LUNA16 dataset, a task where significant semantic ambiguities can exist between nodules and non-nodules. Results show that our method improves the evaluating score from 84.57% to 88.86% by utilizing a combination of both types of variances. Moreover, we show the generated uncertainty enables superior operating points compared to using the probability threshold only, and can further boost the performance to 89.52%. Example nodule detections are visualized to further illustrate the advantages of our method.