Breast cancer histopathological image classification using convolutional neural networks with small SE-ResNet module

• Published in: PloS one 2019-03, Vol.14 (3), p.e0214587-e0214587
• Main Authors: Jiang, Yun, Chen, Li, Zhang, Hai, Xiao, Xiao
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Biology and Life Sciences; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Care and treatment; Computer and Information Sciences; Diagnosis; Humans; Image processing; Image Processing, Computer-Assisted - methods; Medicine and Health Sciences; Methods; Molecular Imaging; Neural Networks, Computer; Novels; Physicians; Research and Analysis Methods; Technology; Tumors
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0214587

Although successful detection of malignant tumors from histopathological images largely depends on the long-term experience of radiologists, experts sometimes disagree with their decisions. Computer-aided diagnosis provides a second option for image diagnosis, which can improve the reliability of experts' decision-making. Automatic and precision classification for breast cancer histopathological image is of great importance in clinical application for identifying malignant tumors from histopathological images. Advanced convolution neural network technology has achieved great success in natural image classification, and it has been used widely in biomedical image processing. In this paper, we design a novel convolutional neural network, which includes a convolutional layer, small SE-ResNet module, and fully connected layer. We propose a small SE-ResNet module which is an improvement on the combination of residual module and Squeeze-and-Excitation block, and achieves the similar performance with fewer parameters. In addition, we propose a new learning rate scheduler which can get excellent performance without complicatedly fine-tuning the learning rate. We use our model for the automatic classification of breast cancer histology images (BreakHis dataset) into benign and malignant and eight subtypes. The results show that our model achieves the accuracy between 98.87% and 99.34% for the binary classification and achieve the accuracy between 90.66% and 93.81% for the multi-class classification.