BCHisto-Net: Breast histopathological image classification by global and local feature aggregation

Rashmi, R and Prasad, Keerthana and Udupa, Chethana Babu K (2021) BCHisto-Net: Breast histopathological image classification by global and local feature aggregation. Artificial Intelligence in Medicine, 121. ISSN 0933-3657

[img] PDF
14181.pdf - Published Version
Restricted to Registered users only

Download (4MB) | Request a copy
Official URL: http://www.elsevier.com/locate/artmed


Breast cancer among women is the second most common cancer worldwide. Non-invasive techniques such as mammograms and ultrasound imaging are used to detect the tumor. However, breast histopathological image analysis is inevitable for the detection of malignancy of the tumor. Manual analysis of breast histopathological images is subjective, tedious, laborious and is prone to human errors. Recent developments in computational power and memory have made automation a popular choice for the analysis of these images. One of the key challenges of breast histopathological image classification at 100× magnification is to extract the features of the potential regions of interest to decide on the malignancy of the tumor. The current state-of-the-art CNN based methods for breast histopathological image classification extract features from the entire image (global features) and thus may overlook the features of the potential regions of interest. This can lead to inaccurate diagnosis of breast histopathological images. This research gap has motivated us to propose BCHisto-Net to classify breast histopathological images at 100× magnification. The proposed BCHisto-Net extracts both global and local fea�tures required for the accurate classification of breast histopathological images. The global features extract abstract image features while local features focus on potential regions of interest. Furthermore, a feature ag�gregation branch is proposed to combine these features for the classification of 100× images. The proposed method is quantitatively evaluated on red a private dataset and publicly available BreakHis dataset. An extensive evaluation of the proposed model showed the effectiveness of the local and global features for the classification of these images. The proposed method achieved an accuracy of 95% and 89% on KMC and BreakHis datasets respectively, outperforming state-of-the-art classifiers.

Item Type: Article
Uncontrolled Keywords: Deep learning Image classification Convolution neural network Breast cancer Histopathological images Computer - aided diagnosis Image analysis
Subjects: Information Sciences > MCIS Manipal
Depositing User: MIT Library
Date Deposited: 07 Feb 2022 04:53
Last Modified: 07 Feb 2022 04:53
URI: http://eprints.manipal.edu/id/eprint/158026

Actions (login required)

View Item View Item