2018/11/10 by Md Zahangir Alom, Alom, Md Zahangir, Chris Yakopcic +5
Computer Science · Medicine · Neuroscience · #AI in cancer detection #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Radiomics and Machine Learning in Medical Imaging
paper · pdf · doi:10.48550/arxiv.1811.04241
openalex publication_date 2018/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The Deep Convolutional Neural Network (DCNN) is one of the most powerful and\nsuccessful deep learning approaches. DCNNs have already provided superior\nperformance in different modalities of medical imaging including breast cancer\nclassification, segmentation, and detection. Breast cancer is one of the most\ncommon and dangerous cancers impacting women worldwide. In this paper, we have\nproposed a method for breast cancer classification with the Inception Recurrent\nResidual Convolutional Neural Network (IRRCNN) model. The IRRCNN is a powerful\nDCNN model that combines the strength of the Inception Network (Inception-v4),\nthe Residual Network (ResNet), and the Recurrent Convolutional Neural Network\n(RCNN). The IRRCNN shows superior performance against equivalent Inception\nNetworks, Residual Networks, and RCNNs for object recognition tasks. In this\npaper, the IRRCNN approach is applied for breast cancer classification on two\npublicly available datasets including BreakHis and Breast Cancer Classification\nChallenge 2015. The experimental results are compared against the existing\nmachine learning and deep learning-based approaches with respect to\nimage-based, patch-based, image-level, and patient-level classification. The\nIRRCNN model provides superior classification performance in terms of\nsensitivity, Area Under the Curve (AUC), the ROC curve, and global accuracy\ncompared to existing approaches for both datasets.\n