TY - JOUR
T1 - Classification of breast cancer lesions in ultrasound images by using attention layer and loss ensemble in deep convolutional neural networks
AU - Kalafi, Elham Yousef
AU - Jodeiri, Ata
AU - Setarehdan, Seyed Kamaledin
AU - Lin, Ng Wei
AU - Rahmat, Kartini
AU - Taib, Nur Aishah
AU - Ganggayah, Mogana Darshini
AU - Dhillon, Sarinder Kaur
N1 - Funding Information:
This project was supported by the University of Malaya Research Grant (PRGS) Program Based Grant (PRGS 2017-1) and FRGS /1/2019 SKK03/UM/01/1 (MOHE Malaysia) awarded to the corresponding authors. Acknowledgments: We would like to thank the University Malaya Medical Center (UMMC) for providing the data to conduct this study.
Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/10
Y1 - 2021/10
N2 - The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.
AB - The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.
KW - Breast cancer
KW - Classification
KW - Deep learning
KW - Diagnostic imaging
KW - Ultrasound
UR - http://www.scopus.com/inward/record.url?scp=85117398469&partnerID=8YFLogxK
U2 - 10.3390/diagnostics11101859
DO - 10.3390/diagnostics11101859
M3 - Article
C2 - 34679557
AN - SCOPUS:85117398469
SN - 2075-4418
VL - 11
JO - Diagnostics
JF - Diagnostics
IS - 10
M1 - 1859
ER -