Domain transformation using semi-supervised CycleGAN for improving performance of classifying thyroid tissue images

Yoshihito Ichiuji; Shingo Mabu; Satomi Hatta; Kunihiro Inai; Shohei Higuchi; Shoji Kido

doi:10.1007/s11548-024-03061-x

Domain transformation using semi-supervised CycleGAN for improving performance of classifying thyroid tissue images

Int J Comput Assist Radiol Surg. 2024 Jan 18. doi: 10.1007/s11548-024-03061-x. Online ahead of print.

Authors

Yoshihito Ichiuji¹, Shingo Mabu², Satomi Hatta^{3

4}, Kunihiro Inai³, Shohei Higuchi^{3

5}, Shoji Kido⁶

Affiliations

¹ Graduate School of Sciences and Technology for Innovation, Yamaguchi University, 2-16-1, Tokiwadai, Ube, Yamaguchi, 755-8611, Japan.
² Graduate School of Sciences and Technology for Innovation, Yamaguchi University, 2-16-1, Tokiwadai, Ube, Yamaguchi, 755-8611, Japan. mabu@yamaguchi-u.ac.jp.
³ Division of Molecular Pathology, Department of Pathological Sciences, University of Fukui, 23-3, Matsuoka-shimoaizuki, Eiheiji-cho, Yoshida-gun, Fukui, 910-1193, Japan.
⁴ Division of Diagnostic/Surgical Pathology, University of Fukui Hospital, 23-3, Matsuoka-shimoaizuki, Eiheiji-cho, Yoshida-gun, Fukui, 910-1193, Japan.
⁵ Department of Pathological Diagnosis, Fukui Prefectural Hospital, 2-8-1, Yotsui, Fukui, Fukui, 910-0846, Japan.
⁶ Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, 2-2, Yamadaoka, Suita, Osaka, 565-0871, Japan.

PMID: 38238492
DOI: 10.1007/s11548-024-03061-x

Abstract

Purpose: A large number of research has been conducted on the classification of medical images using deep learning. The thyroid tissue images can be also classified by cancer types. Deep learning requires a large amount of data, but every medical institution cannot collect sufficient number of data for deep learning. In that case, we can consider a case where a classifier trained at a certain medical institution that has a sufficient number of data is reused at other institutions. However, when using data from multiple institutions, it is necessary to unify the feature distribution because the feature of the data differs due to differences in data acquisition conditions.

Methods: To unify the feature distribution, the data from Institution T are transformed to have the closer distribution to that from Institution S by applying a domain transformation using semi-supervised CycleGAN. The proposed method enhances CycleGAN considering the feature distribution of classes for making appropriate domain transformation for classification. In addition, to address the problem of imbalanced data with different numbers of data for each cancer type, several methods dealing with imbalanced data are applied to semi-supervised CycleGAN.

Results: The experimental results showed that the classification performance was enhanced when the dataset from Institution S was used as training data and the testing dataset from Institution T was classified after applying domain transformation. In addition, focal loss contributed to improving the mean F1 score the best as a method that addresses the class imbalance.

Conclusion: The proposed method achieved the domain transformation of thyroid tissue images between two domains, where it retained the important features related to the classes across domains and showed the best F1 score with significant differences compared with other methods. In addition, the proposed method was further enhanced by addressing the class imbalance of the dataset.

Keywords: Classification; CycleGAN; Domain transformation; Semi-supervised learning; Thyroid tissue images.

Abstract

Grants and funding