Investigating the Effects of Transfer Learning on ROI-based Classification of Chest CT Images: A Case Study on Diffuse Lung Diseases

• Published in: Journal of signal processing systems 2020-03, Vol.92 (3), p.307-313
• Main Authors: Mabu, Shingo, Atsumo, Ami, Kido, Shoji, Kuremoto, Takashi, Hirano, Yasushi
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Chest; Circuits and Systems; Computed tomography; Computer Imaging; Datasets; Deep learning; Electrical Engineering; Engineering; Image classification; Image Processing and Computer Vision; Image segmentation; Lung diseases; Machine learning; Medical imaging; Medical research; Neural networks; Organs; Pattern Recognition; Pattern Recognition and Graphics; Signal,Image and Speech Processing; Training; Vision
• ISSN: 1939-8018; 1939-8115
• DOI: 10.1007/s11265-019-01499-w

Research on Computer-Aided Diagnosis (CAD) of medical images has been actively conducted to support decisions of radiologists. Since deep learning has shown distinguished abilities in classification, detection, segmentation, etc. in various problems, many studies on CAD have been using deep learning. One of the reasons behind the success of deep learning is the availability of large application-specific annotated datasets. However, it is quite tough work for radiologists to annotate hundreds or thousands of medical images for deep learning, and thus it is difficult to obtain large scale annotated datasets for various organs and diseases. Therefore, many techniques that effectively train deep neural networks have been proposed, and one of the techniques is transfer learning. This paper focuses on transfer learning and especially conducts a case study on ROI-based opacity classification of diffuse lung diseases in chest CT images. The aim of this paper is to clarify what characteristics of the datasets for pre-training and what kinds of structures of deep neural networks for fine-tuning contribute to enhance the effectiveness of transfer learning. In addition, the numbers of training data are set at various values and the effectiveness of transfer learning is evaluated. In the experiments, nine conditions of transfer learning and a method without transfer learning are compared to analyze the appropriate conditions. From the experimental results, it is clarified that the pre-training dataset with more (various) classes and the compact structure for fine-tuning show the best accuracy in this work.