1. Classification of squamous cell carcinoma from FF-OCT images: Data selection and progressive model construction
- Author
-
Manuel Calderon-Delgado, Sheng-Lung Huang, Ming-Yi Lin, Chi-Jui Ho, Jeng-Wei Tjiu, and Homer H. Chen
- Subjects
Speedup ,Radiological and Ultrasound Technology ,medicine.diagnostic_test ,Channel (digital image) ,Computer science ,business.industry ,Deep learning ,Health Informatics ,Pattern recognition ,Computer Graphics and Computer-Aided Design ,Convolutional neural network ,Regularization (mathematics) ,Mice ,Optical coherence tomography ,Feature (computer vision) ,Classifier (linguistics) ,Carcinoma, Squamous Cell ,medicine ,Animals ,Radiology, Nuclear Medicine and imaging ,Neural Networks, Computer ,Computer Vision and Pattern Recognition ,Artificial intelligence ,business ,Tomography, Optical Coherence - Abstract
We investigate the speed and performance of squamous cell carcinoma (SCC) classification from full-field optical coherence tomography (FF-OCT) images based on the convolutional neural network (CNN). Due to the unique characteristics of SCC features, the high variety of CNN, and the high volume of our 3D FF-OCT dataset, progressive model construction is a time-consuming process. To address the issue, we develop a training strategy for data selection that makes model training 16 times faster by exploiting the dependency between images and the knowledge of SCC feature distribution. The speedup makes progressive model construction computationally feasible. Our approach further refines the regularization, channel attention, and optimization mechanism of SCC classifier and improves the accuracy of SCC classification to 87.12% at the image level and 90.10% at the tomogram level. The results are obtained by testing the proposed approach on an FF-OCT dataset with over one million mouse skin images.
- Published
- 2021
- Full Text
- View/download PDF