AUTHOR=Pawar Shivaji D. , Sharma Kamal K. , Sapate Suhas G. , Yadav Geetanjali Y. , Alroobaea Roobaea , Alzahrani Sabah M. , Hedabou Mustapha 

TITLE=Multichannel DenseNet Architecture for Classification of Mammographic Breast Density for Breast Cancer Detection

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.885212

DOI=10.3389/fpubh.2022.885212

ISSN=2296-2565

ABSTRACT=Percentage Mammographic breast density is one of the most notable biomarkers, and it is assessed visually with the support of radiologists with four qualitative BIRADS categories. It is difficult for radiologists to differentiate between the two variably allotted BIRADS classes, "BIRADS C and BIRADS D." Recently, convolution neural networks have been found superior in classification tasks due to their ability to extract local features with shared weight architecture and space invariance characteristics. The proposed research intends to examine an AI-based MBD classifier towards developing a latent computer-assisted tool for radiologists to distinguish the BIRADS class in modern clinical progress. This article proposes a Multi-channel Dense-Net architecture for MBD classification. The proposed architecture consists of four-channel Dense-Net transfer learning architecture to extract significant features from a single patient's two MLO and two CC view mammograms. The performance of the proposed classifier is evaluated using 200 cases consisting of 800 digital mammograms of different BIRADS density classes with validated density ground truth. The classifier's performance is evaluated with quantitative metrics like precision, responsiveness, specificity, and AUC. The concluding preliminary outcomes reveal that this intended multi-channel model has delivered good performance with an accuracy of 96.67% during training and 90.06% during testing and an average AUC of 0.9625. Obtained results are also validated qualitatively with the help of a radiologist expert in the field of MBD. Proposed architecture achieved state-of-art results with a fewer number of images and with less computation power.