An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images.
Authors
Affiliations (7)
Affiliations (7)
- Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, 47040, Pakistan.
- Department of AI, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, Al-Khobar, Saudi Arabia. [email protected].
- Department of AI, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, Al-Khobar, Saudi Arabia.
- School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, 965-8580, Japan.
- College of Computer Science, King Khalid University, Abha, 61413, Saudi Arabia.
- Hanynag University, Seoul, South Korea.
- Hanynag University, Seoul, South Korea. [email protected].
Abstract
Convolutional Neural Networks (CNNs), a sophisticated deep learning technique, have proven highly effective in identifying and classifying abnormalities related to various diseases. The manual classification of these is a hectic and time-consuming process; therefore, it is essential to develop a computerized technique. Most existing methods are designed to address a single specific problem, limiting their adaptability. In this work, we proposed a novel adaptive deep-learning framework for simultaneously classifying breast cancer and maternal-fetal ultrasound datasets. Data augmentation was applied in the preprocessing phase to address the data imbalance problem. After, two novel architectures are proposed: InBnFUS and CNNDen-GRU. The InBnFUS network combines 5-Blocks inception-based architecture (Model 1) and 5-Blocks inverted bottleneck-based architecture (Model 2) through a depth-wise concatenation layer, while CNNDen-GRU incorporates 5-Blocks dense architecture with an integrated GRU layer. Post-training features were extracted from the global average pooling and GRU layer and classified using neural network classifiers. The experimental evaluation achieved enhanced accuracy rates of 99.0% for breast cancer, 96.6% for maternal-fetal (common planes), and 94.6% for maternal-fetal (brain) datasets. Additionally, the models consistently achieve high precision, recall, and F1 scores across both datasets. A comprehensive ablation study has been performed, and the results show the superior performance of the proposed models.