Intelligent Computer-Aided Model for Efficient Diagnosis of Digital Breast Tomosynthesis 3D Imaging Using Deep Learning

Abstract: Digital Breast Tomosynthesis (DBT) is a highly promising 3D imaging modality for breast diagnosis. Tissue overlapping is a challenge with traditional 2D mammograms, however since digital breast tomosynthesis can obtain three-dimensional images, tissue overlapping is reduced, making it easier for radiologists to detect abnormalities and resulting in improved and more accurate diagnosis. In this study, a new computer-aided multi-class diagnosis system is proposed that integrates DBT augmentation and colour feature map with a modified deep learn-ing architecture (Mod_AlexNet). In addition, an optimization layer is added with multiple opti-mizers for effective classification of multiple breast classes, including benign, normal, and ma-lignant. The proposed system comprises several techniques, including data augmentation, col-our feature mapping, optimization, and classification. Two experimental scenarios are applied, the first scenario proposed a computer-aided diagnosis (CAD) model that integrated DBT aug-mentation, image enhancement techniques and colour feature mapping with six deep learning models for feature extraction, including ResNet-18, AlexNet, GoogleNet, MobileNetV2, VGG-16 and DenseNet-201, to efficiently classify DBT slices. The second scenario compared the perfor-mance of the newly proposed Mod_AlexNet architecture and traditional AlexNet, using several optimization techniques and different evaluation performance metrics were computed. The op-timization techniques included Adaptive Moment Estimation (Adam), Root Mean Squared Prop-agation (RMSProp), and Stochastic Gradient Descent with Momentum (SGDM), for different batch sizes, including 32, 64 and 512. Experiments have been conducted on a large benchmark da-taset of breast tomography scans. The performance of the first scenario was compared in terms of accuracy, precision, sensitivity, specificity, runtime, and f1-score. While in the second scenar-io, performance was compared in terms of training accuracy, training loss, and test accuracy. In the first scenario, results demonstrated that AlexNet reported improvement rates of 1.69%, 5.13%, 6.13%, 4.79% and 1.6%, compared to ResNet-18, MobileNetV2, GoogleNet, DenseNet-201 and VGG16, respectively. Experimental analysis with different optimization techniques and batch sizes demonstrated that the proposed Mod_AlexNet architecture outperformed AlexNet in terms of test accuracy with an average improvement rate of 2.01%, 1.17% and 0.96% when com-pared using SGDM, Adam, and RMSProp optimizers, respectively.