GARL-Net: Graph Based Adaptive Regularized Learning Deep Network for Breast Cancer Classification

• Published in: IEEE access 2023-01, Vol.11, p.1-1
• Main Authors: Patel, Vivek, Chaurasia, Vijayshri, Mahadeva, Rajesh, Patole, Shashikant P.
• Format: Article
• Language: English
• Subjects: Breast cancer; Breast Cancer Image Classification; Complement; Complement Cross Entropy; Computer Aided Diagnostic; Computer networks; Convolutional neural networks; Datasets; Deep Learning; Diagnostic systems; Entropy; Feature extraction; Graph Laplacian Basis Regularization; Histopathology; Image classification; Learning; Medical imaging; Regularization; Support vector machines; Training; Transfer Learning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3239671

Across the globe, women suffer from breast cancer fatal disease. It is arising surprisingly due to a lack of awareness among them and the inconvenient reach of diagnostic systems. Many computer-aided diagnostic systems have been developed for the detection of cancer. These systems have quite lower performance, so more accurate diagnosis is the need of the time to save the life of human beings. For large and imbalanced image datasets, efficient learning of the network is very important to detect and classify breast cancer more accurately. In this paper, a graph based adaptive regularized learning of deep network (GARL-Net) is proposed for more accurate breast cancer classification. Transfer learning is used for training the bakebone network DenseNet121. furthermore, fine tuning of bakebone network is followed by the estimated improved loss function. The improved loss function is actually graph based adaptively regularized complement cross entropy loss. The SoftMax cross entropy in itself is not sufficient to classify image samples accurately, complement entropy technique is incorporated to overcome the misclassification issue with the cross-entropy loss. Further, by adaptive scaling of regularization term with spatial graph Laplacian basis used to adaptively penalize the complement cross entropy loss for improving the learning of the network. The performance of the proposed method is evaluated using BreakHis and BACH 2018 histopathology image datasets and outperforms the existing state-of-the-art methods and achieved 99.00% of precision, 99.40% of recall, 99.20 % of F-1score, and 99.49% of accuracy for binary classification of breast cancer image samples of BreakHis dataset.