Automated Breast Mass Classification System Using Deep Learning and Ensemble Learning in Digital Mammogram

Abstract

In recent years, deep learning techniques are employed in the mammography processing field to reduce radiologists' costs. Existing breast mass classification systems are implemented using deep learning technologies such as a Convolutional Neural Network (CNN). CNN based systems have attained higher performance than the machine learning-based systems in the classification task of mammography images, but a few issues still exist. Some of these issues are; ignorance of semantic features, analysis limitation to the current patch of images, lost patches in less contrast mammography images, and ambiguity in segmentation. These issues lead to increased false information about patches of mammography image, computational cost, decisions based on current patches, and not recovering the variance of patches intensity. In turn, breast mass classification systems based on convolutional neural networks produced unsatisfactory classification accuracy. To resolve these issues and improve the accuracy of classification on low contrast images, we propose a novel Breast Mass Classification system named BMC. It has improved architecture based on a combination of k-mean clustering, Long Short-Term Memory network of Recurrent Neural Network (RNN), CNN, random forest, boosting techniques to classify the breast mass into benign, malignant, and normal. Further, the proposed BMC system is compared with existing classification systems using two publicly available datasets of mammographic images. Proposed BMC system achieves the sensitivity, specificity, F-measure, and accuracy for the DDSM dataset is 0.97%, 0.98%,0.97%, 0.96% and for the MIAS dataset is 0.97%, 0.97%,0.98%, and 0.95% respectively. Further Area Under Curve (AUC) rate of the proposed BMC system lies between 0.94% -0.97% for DDSM and 0.94%-0.98% for the MIAS dataset. The BMC method worked comparably better than other mammography classification schemes that have previously been invented. Moreover, the Confidence interval statistical test is also employed to determine the classification accuracy of the BMC system using different configurations and neural network parameters.INDEX TERMS Deep learning, convolutional neural network, random forest, breast mass classification, recurrent neural network, boosting, machine learning, mammograms, medical image processing.

Breast cancer detection using machine learning approaches: a comparative study

“…In the stacking approach, the outputs from different classification models are to be aggregated into a new dataset [40]. Readers interested for more information are referred to [41]- [46].…”

Simply Fine-Tuned Deep Learning-Based Classification for Breast Cancer with Mammograms

“…Another study reported the use of combined k-mean clustering, long short-term memory (LSTM) network of recurrent neural network (RNN), CNN, random forest, and boosting methods to classify breast masses into three categories: normal, benign, and malignant by Malebary and Hashmi in 2021 [36]. In addition, they compared their invented models with other models utilizing DDSM and MIAS datasets.…”

“…Moreover, the AUC was 0.9970−1.0000, sensitivity was 0.9799−1.0000, precision was 0.9758−0.9992, F1-score was 0.9779−0.9996, specificity was 0.9797−0.9993, and kappa was 0.9595−0.9992. Compared to [36], in terms of sensitivity, specificity, F1-score, accuracy, and AUC, as shown in Tab. 1, our results showed 2%−6% enhancements.…”

Breast cancer detection: Shallow convolutional neural network against deep convolutional neural networks based approach

“…Lotter et al’s annotation-efficient deep learning strategy for mammograms and digital breast tomosynthesis image-based breast cancer diagnosis has been proposed by Lotter et al (2021) . Malebary and Hashmi. (2021) suggested an ensemble-based technique for classifying breast masses.…”