Multi-Classification of Breast Cancer Lesions in Histopathological Images Using DEEP_Pachi: Multiple Self-Attention Head

Chiagoziem C Ukwuoma; Md Altab Hossain; Jehoiada K Jackson; Grace U Nneji; Happy N Monday; Zhiguang Qin

doi:10.3390/diagnostics12051152

Multi-Classification of Breast Cancer Lesions in Histopathological Images Using DEEP_Pachi: Multiple Self-Attention Head

Diagnostics (Basel). 2022 May 5;12(5):1152. doi: 10.3390/diagnostics12051152.

Authors

Chiagoziem C Ukwuoma¹, Md Altab Hossain², Jehoiada K Jackson¹, Grace U Nneji¹, Happy N Monday³, Zhiguang Qin¹

Affiliations

¹ School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.
² School of Management and Economics, University of Electronic Science and Technology of China, Chengdu 610054, China.
³ School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China.

Abstract

Introduction and background: Despite fast developments in the medical field, histological diagnosis is still regarded as the benchmark in cancer diagnosis. However, the input image feature extraction that is used to determine the severity of cancer at various magnifications is harrowing since manual procedures are biased, time consuming, labor intensive, and error-prone. Current state-of-the-art deep learning approaches for breast histopathology image classification take features from entire images (generic features). Thus, they are likely to overlook the essential image features for the unnecessary features, resulting in an incorrect diagnosis of breast histopathology imaging and leading to mortality.

Methods: This discrepancy prompted us to develop DEEP_Pachi for classifying breast histopathology images at various magnifications. The suggested DEEP_Pachi collects global and regional features that are essential for effective breast histopathology image classification. The proposed model backbone is an ensemble of DenseNet201 and VGG16 architecture. The ensemble model extracts global features (generic image information), whereas DEEP_Pachi extracts spatial information (regions of interest). Statistically, the evaluation of the proposed model was performed on publicly available dataset: BreakHis and ICIAR 2018 Challenge datasets.

Results: A detailed evaluation of the proposed model's accuracy, sensitivity, precision, specificity, and f1-score metrics revealed the usefulness of the backbone model and the DEEP_Pachi model for image classifying. The suggested technique outperformed state-of-the-art classifiers, achieving an accuracy of 1.0 for the benign class and 0.99 for the malignant class in all magnifications of BreakHis datasets and an accuracy of 1.0 on the ICIAR 2018 Challenge dataset.

Conclusions: The acquired findings were significantly resilient and proved helpful for the suggested system to assist experts at big medical institutions, resulting in early breast cancer diagnosis and a reduction in the death rate.

Keywords: breast cancer; histopathological images; image classification; medical images; multi-head self-attention; transfer learning.

Grants and funding

This research was partially supported by the National Science Foundation of China (NSFC) under the project “Development of fetal heart-oriented heart sound echocardiography multimodal auxiliary diagnostic equipment” (62027827).