MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Cheng Xu; Ke Yi; Nan Jiang; Xiong Li; Meiling Zhong; Yuejin Zhang

doi:10.1016/j.compbiomed.2023.107385

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Comput Biol Med. 2023 Oct:165:107385. doi: 10.1016/j.compbiomed.2023.107385. Epub 2023 Aug 16.

Authors

Cheng Xu¹, Ke Yi¹, Nan Jiang¹, Xiong Li², Meiling Zhong³, Yuejin Zhang⁴

Affiliations

¹ School of Information Engineering, East China Jiaotong University, Nanchang, 330013, China.
² School of Software, East China Jiaotong University, Nanchang, 330013, China.
³ School of Materials Science and Engineering, East China Jiaotong University, 330013, Nanchang, China.
⁴ School of Information Engineering, East China Jiaotong University, Nanchang, 330013, China. Electronic address: zyjecjtu@foxmail.com.

PMID: 37633086
DOI: 10.1016/j.compbiomed.2023.107385

Abstract

Breast cancer is a common malignancy and early detection and treatment of it is crucial. Computer-aided diagnosis (CAD) based on deep learning has significantly advanced medical diagnostics, enhancing accuracy and efficiency in recent years. Despite the convenience, this technology also has certain limitations. When the morphological characteristics of the patient's pathological section are not evident or complex, certain small lesions or cells deep within the lesion cannot be recognized, and misdiagnosis is prone to occur. As a result, MDFF-Net, a CNN-based multidimensional feature fusion network, is proposed. The model consists of a one-dimensional feature extraction network, a two-dimensional feature extraction network, and a feature fusion classification network. The basic part of the two-dimensional feature extraction network is stacked by modules integrated with multi-scale channel shuffling networks and channel attention modules. Furthermore, inspired by natural language processing, this model integrates a one-dimensional feature extraction network to extract detailed information in the image to avoid misdiagnosis caused by insufficient information extraction such as cell morphological characteristics and differentiation degree. Finally, the extracted one-dimensional and two-dimensional features are fused in the feature fusion network and employed for the final classification. The effectiveness of MDFF-Net and classical classification models were evaluated on the BreakHis and the BACH datasets. According to experimental results, MDFF-Net achieves an accuracy of 98.86% on the BreakHis and 86.25% on the BACH dataset. Furthermore, to further assess the effectiveness of the model in other classification tasks, the colon cancer and the lung cancer datasets were employed for additional experiments, achieving a classification accuracy of 100% in both cases.

Keywords: Breast cancer; Feature extraction; Histopathology images; Image classification; MDFF-Net.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Breast Neoplasms* / diagnostic imaging
Breast* / diagnostic imaging
Cell Differentiation
Diagnosis, Computer-Assisted
Female
Humans
Image Processing, Computer-Assisted
Information Storage and Retrieval