SSCD-Net: Semi-supervised Skin Cancer Diagnostical Network Combined with Curriculum Learning, Disease Relation and Clinical Information

• Published in: 2024 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8
• Main Authors: Wang, Wei, Cao, CaoYunjian, Wu, Shaozhi, Liu, Xingang, Su, Han, Tian, Dan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 30.06.2024
• Subjects: Clinical diagnosis; Convolutional neural networks; curriculum learning; Data models; Feature extraction; Pipelines; Semantics; semi-supervised learning; skin cancer classification; Training
• ISSN: 2161-4407
• DOI: 10.1109/IJCNN60899.2024.10650310

Skin cancer is one of the most prevalent cancer types. Training a convolutional neural network (CNN) for skin cancer diagnosis usually requires a large amount of labeled data to yield good performance. However, obtaining high-quality labels is laborious and expensive, as accurately annotating medical images demands expertise knowledge of the clinicians. In this paper, we present a novel semi-supervised framework for skin cancer diagnosis, SSCD-Net combines curriculum learning strategy, disease relation and the guidance of clinical information. Curriculum learning (CL) strategy is designed to help train from easy instances and then gradually handles harder ones to improve the generalization capacity and convergence rate. The whole training set is split into a number of subsets ranked from an easy one to a more complex one, in an unsupervised manner. The SSCD-Net is driven by disease relation apart from conventional individual consistency, which explicitly enforces the consistency of disease relation among different samples under perturbations, encouraging the model to explore extra semantic information from unlabeled data. At the end of the classification pipeline, a multimodal information fusion (MIF) module is designed to fuse the image features and clinical features, further introducing the guidance of clinical information. Comprehensive experiments are conducted on four publicly accessible dataset, i.e., PADUEFC-20, ISIC 2018, ISIC 2019 and ISIC-Archive. Simulations show that the SSCD-Net has better or comparable performance against that of the other state-of-the-art semi-supervised models.