Open Access

ARTICLE

Mixed Re-Sampled Class-Imbalanced Semi-Supervised Learning for Skin Lesion Classification

Ye Tian¹, Liguo Zhang^1,2, Linshan Shen^1,*, Guisheng Yin¹, Lei Chen³

1 Harbin Engineering University, College of Computer Science and Technology, Harbin, 150001, China
2 Heilongjiang Hengxun Technology Co., Ltd., Harbin, 150001, China
3 College of Engineering and Information Technology, Georgia Southern University, Statesboro, GA, 30458, USA

* Corresponding Author: Linshan Shen. Email:

Intelligent Automation & Soft Computing 2021, 28(1), 195-211. https://doi.org/10.32604/iasc.2021.016314

Received 21 December 2020; Accepted 29 January 2021; Issue published 17 March 2021

Abstract

Skin cancer is one of the most common types of cancer in the world, melanoma is considered to be the deadliest type among other skin cancers. Quite recently, automated skin lesion classification in dermoscopy images has become a hot and challenging research topic due to its essential way to improve diagnostic performance, thus reducing melanoma deaths. Convolution Neural Networks (CNNs) are at the heart of this promising performance among a variety of supervised classification techniques. However, these successes rely heavily on large amounts of class-balanced clearly labeled samples, which are expensive to obtain for skin lesion classification in the real world. To address this issue, we propose a mixed re-sampled (MRS) class-imbalanced semi-supervised learning method for skin lesion classification, which consists of two phases, re-sampling, and multiple mixing methods. To counter class imbalance problems, a re-sampling method for semi-supervised learning is proposed, and focal loss is introduced to the semi-supervised learning to improve the classification performance. To make full use of unlabeled data to improve classification performance, Fmix and Mixup are used to mix labeled data with the pseudo-labeled unlabeled data. Experiments are conducted to demonstrate the effectiveness of the proposed method on class-imbalanced datasets, the results show the effectiveness of our method as compared with other state-of-the-art semi-supervised methods.

---

Keywords

---

Citations