Attention-Based Ensemble Network for Effective Breast Cancer Classification over Benchmarks

Abstract

Globally, breast cancer (BC) is considered a major cause of death among women. Therefore, researchers have used various machine and deep learning-based methods for its early and accurate detection using X-ray, MRI, and mammography image modalities. However, the machine learning model requires domain experts to select an optimal feature, obtains a limited accuracy, and has a high false positive rate due to handcrafting features extraction. The deep learning model overcomes these limitations, but these models require large amounts of training data and computation resources, and further improvement in the model performance is needed. To do this, we employ a novel framework called the Ensemble-based Channel and Spatial Attention Network (ECS-A-Net) to automatically classify infected regions within BC images. The proposed framework consists of two phases: in the first phase, we apply different augmentation techniques to enhance the size of the input data, while the second phase includes an ensemble technique that parallelly leverages modified SE-ResNet50 and InceptionV3 as a backbone for feature extraction, followed by Channel Attention (CA) and Spatial Attention (SA) modules in a series manner for more dominant feature selection. To further validate the ECS-A-Net, we conducted extensive experiments between several competitive state-of-the-art (SOTA) techniques over two benchmarks, including DDSM and MIAS, where the proposed model achieved 96.50% accuracy for the DDSM and 95.33% accuracy for the MIAS datasets. Additionally, the experimental results demonstrated that our network achieved a better performance using various evaluation indicators, including accuracy, sensitivity, and specificity among other methods.

Efficient Machine Learning and Deep Learning Techniques for Detection of Breast Cancer Tumor

“…The ECS-A-Net model conducted thorough trials comparing several stateof-the-art methodologies on two benchmarks, DDSM and MIAS. The model obtained an accuracy of 96.50% on the DDSM dataset and 95.33% on the MIAS dataset 34 .…”

“…The second phase involves an ensemble technique that simultaneously utilizes modified SE-ResNet50 and InceptionV3 as a backbone for feature extraction. This is followed by the sequential application of Channel Attention (CA) and Spatial Attention (SA) modules to select more prominent features 34 . Humayun et al propose a deep learning algorithm to largely predict breast cancer risk based on this foundation.…”