Bayesian deep learning for reliable oral cancer image classification
Authors:
- 20 September 2021
- journal article
- research article
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 12 (10) , 6422-6430
Abstract
In medical imaging, deep learning-based solutions have achieved state-of-the-art performance. However, reliability restricts the integration of deep learning into practical medical workflows since conventional deep learning frameworks cannot quantitatively assess model uncertainty. In this work, we propose to address this shortcoming by utilizing a Bayesian deep network capable of estimating uncertainty to assess oral cancer image classification reliability. We evaluate the model using a large intraoral cheek mucosa image dataset captured using our customized device from high-risk population to show that meaningful uncertainty information can be produced. In addition, our experiments show improved accuracy by uncertainty-informed referral. The accuracy of retained data reaches roughly 90% when referring either 10% of all cases or referring cases whose uncertainty value is greater than 0.3. The performance can be further improved by referring more patients. The experiments show the model is capable of identifying difficult cases needing further inspection.Keywords
Funding Information
- National Institute of Cancers (UH3CA239682)
- National Institute of Biomedical Imaging and Bioengineering (UH2EB022623)
- National Institute of Dental and Craniofacial Research (R01DE030682)
This publication has 20 references indexed in Scilit:
- Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learningNature Medicine, 2018
- Clinically applicable deep learning for diagnosis and referral in retinal diseaseNature Medicine, 2018
- Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep LearningCell, 2018
- Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast CancerJAMA, 2017
- Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep LearningScientific Reports, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Probabilistic machine learning and artificial intelligenceNature, 2015
- Oral squamous cell cancer: early detection and the role of alcohol and smokingHead & Neck Oncology, 2011
- Oral cancer prevention and control – The approach of the World Health OrganizationOral Oncology, 2009
- A Practical Bayesian Framework for Backpropagation NetworksNeural Computation, 1992