Enhanced Breast Cancer Diagnosis Using Modified InceptionNet-V3: A Deep Learning Approach for Ultrasound Image Classification

Rana Alnashwan^1*Abduljabbar S. Ba Mahel²Samia Chelloug¹Ahsan Rafiq³Mohammed Muthanna⁴Ahmed Aziz^5,6

• ¹Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Saudi Arabia, Riyadh, Riyadh, Saudi Arabia
• ²School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China
• ³School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, Chongqing, China
• ⁴Department of international business Management, Tashkent state university of Economics, Tashkent, Uzbekistan, Tashkent, Uzbekistan
• ⁵Department of Computer Science, Faculty of Computer and Artificial Intelligence, Benha University, Benha, Egypt
• ⁶Engineering school, Central Asian University, Tashkent, Uzbekistan

Breast cancer (BC) is a malignant neoplasm that originates in the mammary gland's cellular structures and remains one of the most prevalent cancers among women, ranking second in cancer-related mortality after lung cancer. Early and accurate diagnosis is crucial due to the heterogeneous nature of breast cancer and its rapid progression. However, manual detection and classification are often time-consuming and prone to errors, necessitating the development of automated and reliable diagnostic approaches. Recent advancements in deep learning have significantly improved medical image analysis, demonstrating superior predictive performance in breast cancer detection using ultrasound images. Despite these advancements, training deep learning models from scratch can be computationally expensive and dataintensive. Transfer learning, leveraging pre-trained models on large-scale datasets, offers an effective solution to mitigate these challenges. In this study, we investigate and compare multiple deep-learning models for breast cancer classification using transfer learning. The evaluated architectures include modified InceptionV3, GoogLeNet, ShuffleNet, AlexNet, VGG-16, and SqueezeNet. Additionally, we propose a deep neural network model that integrates features from modified InceptionV3 to further enhance classification performance. The experimental results demonstrate that the modified InceptionV3 model achieves the highest classification accuracy of 99.10%, with a recall of 98.90%, precision of 99.00%, and an F1-score of 98.80%, outperforming all other evaluated models on the given datasets. These findings underscore the potential of the proposed approach in enhancing diagnostic precision.