arXiv Analytics

Sign in

arXiv:1902.03233 [cs.CV]AbstractReferencesReviewsResources

A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans

Onur Ozdemir, Rebecca L. Russell, Andrew A. Berlin

Published 2019-02-08Version 1

We introduce a new end-to-end computer aided detection and diagnosis system for lung cancer screening using low-dose CT scans. Our system is based on 3D convolutional neural networks and achieves state-of-the-art performance for both lung nodule detection and malignancy classification tasks on the publicly available LUNA16 and Kaggle Data Science Bowl challenges. Furthermore, we characterize model uncertainty in our system and show that we can use this to provide well-calibrated classification probabilities for nodule detection and patient malignancy diagnosis. To the best of our knowledge, model uncertainty has not been considered in the context of lung CT analysis before. These calibrated probabilities informed by model uncertainty can be used for subsequent risk-based decision making towards diagnostic interventions or disease treatments, as we demonstrate using a probability-based patient referral strategy to further improve our results.

Related articles: Most relevant | Search more
arXiv:1811.09800 [cs.CV] (Published 2018-11-24)
Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Control
arXiv:1511.02680 [cs.CV] (Published 2015-11-09)
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
arXiv:1810.02492 [cs.CV] (Published 2018-10-05)
Co-Learning Feature Fusion Maps from PET-CT Images of Lung Cancer