Self-Supervised Transfer Learning Based on Domain Adaptation for Benign-Malignant Lung Nodule Classification on Thoracic CT
Authors:
- 3 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (8) , 3860-3871
Abstract
The spatial heterogeneity is an important indicator of the malignancy of lung nodules in lung cancer diagnosis. Compared with 2D nodule CT images, the 3D volumes with entire nodule objects hold richer discriminative information. However, for deep learning methods driven by massive data, effectively capturing the 3D discriminative features of nodules in limited labeled samples is a challenging task. Different from previous models that proposed transfer learning models in a 2D pattern or learning from scratch 3D models, we develop a self-supervised transfer learning based on domain adaptation (SSTL-DA) 3D CNN framework for benign-malignant lung nodule classification. At first, a data pre-processing strategy termed adaptive slice selection (ASS) is developed to eliminate the redundant noise of the input samples with lung nodules. Then, the self-supervised learning network is constructed to learn robust image representations from CT images. Finally, a transfer learning method based on domain adaptation is designed to obtain discriminant features for classification. The proposed SSTL-DA method has been assessed on the LIDC-IDRI benchmark dataset, and it obtains an accuracy of 91.07% and an AUC of 95.84%. These results demonstrate that the SSTL-DA model achieves quite a competitive classification performance compared with some state-of-the-art approachesKeywords
Funding Information
- National Natural Science Foundation of China (42071302)
- Graduate Research and Innovation Foundation of Chongqing (CYB21060)
- Fundamental Research Funds for the Central Universities (2019CDYGYB008)
- Innovation Program for Chongqing Overseas Returnees (cx2019144)
- Visiting Scholar Foundation of Key Laboratory of Optoelectronic Technology and Systems
- Nvidia
This publication has 53 references indexed in Scilit:
- Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classificationPattern Recognition, 2017
- An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image ClassificationIEEE Journal of Biomedical and Health Informatics, 2016
- Correlation coefficient based supervised locally linear embedding for pulmonary nodule recognitionComputer Methods and Programs in Biomedicine, 2016
- Improved pulmonary nodule classification utilizing quantitative lung parenchyma featuresJournal of Medical Imaging, 2015
- Computer-aided classification of lung nodules on computed tomography images via deep learning techniqueOncoTargets and Therapy, 2015
- Lung Nodule Classification Using Deep Features in CT Images2015
- Bag-of-Frequencies: A Descriptor of Pulmonary Nodules in Computed Tomography ImagesIEEE Transactions on Medical Imaging, 2014
- Texture Feature Analysis for Computer-Aided Diagnosis on Pulmonary NodulesJournal of Digital Imaging, 2014
- The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT ScansMedical Physics, 2011
- Thematic Map ComparisonPhotogrammetric Engineering & Remote Sensing, 2004