Semi-HIC: A novel semi-supervised deep learning method for histopathological image classification

• Published in: Computers in biology and medicine Vol. 137; p. 104788
• Main Authors: Su, Lei, Liu, Yu, Wang, Minghui, Li, Ao
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01-10-2021; Elsevier Limited
• Subjects: Annotations; Classification; Computer architecture; Datasets; Deep learning; Design; Heterogeneity; Histopathological image classification; Image classification; Machine learning; Medical imaging; Object recognition; Semantics; Semi-supervised learning; Similarity; Teaching methods; Deep learning; Histopathological image classification; Semi-supervised learning
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104788

Histopathological images provide a gold standard for cancer recognition and diagnosis. Existing approaches for histopathological image classification are supervised learning methods that demand a large amount of labeled data to obtain satisfying performance, which have to face the challenge of limited data annotation due to prohibitive time cost. To circumvent this shortage, a promising strategy is to design semi-supervised learning methods. Recently, a novel semi-supervised approach called Learning by Association (LA) is proposed, which achieves promising performance in nature image classification. However, there are still great challenges in its application to histopathological image classification due to the wide inter-class similarity and intra-class heterogeneity in histopathological images. To address these issues, we propose a novel semi-supervised deep learning method called Semi-HIC for histopathological image classification. Particularly, we introduce a new semi-supervised loss function combining an association cycle consistency (ACC) loss and a maximal conditional association (MCA) loss, which can take advantage of a large number of unlabeled patches and address the problems of inter-class similarity and intra-class variation in histopathological images, and thereby remarkably improve classification performance for histopathological images. Besides, we employ an efficient network architecture with cascaded Inception blocks (CIBs) to learn rich and discriminative embeddings from patches. Experimental results on both the Bioimaging 2015 challenge dataset and the BACH dataset demonstrate our Semi-HIC method compares favorably with existing deep learning methods for histopathological image classification and consistently outperforms the semi-supervised LA method.
•We propose a novel semi-supervised method Semi-HIC for histopathological image classification with limited labeled data.•Both ACC and MCA loss are introduced to solve the problems of intra-class heterogeneity and inter-class similarity.•The proposed Cascaded Inception blocks helps to extract discriminant representations from both labeled and unlabeled patches.