Optimizing breast cancer diagnosis with convolutional autoencoders: Enhanced performance through modified loss functions
ArunaDevi Karuppasamy, Hamza M. Zidoum, Majda Said Sultan Al-Rashdi, Maiya Al-Bahri · Intelligence-Based Medicine · 2025
The Deep Learning (DL) has demonstrated a significant impact on a various pattern recognition applications, resulting in significant advancements in areas such as visual recognition, autonomous cars, language processing, and healthcare. Nowadays, deep learning was widely applied on the medical images to identify the diseases efficiently. Still, the use of applications in clinical settings is now limited to a small number. The main factors to this might be due to an inadequate annotated data, noises in the images and challenges related to collecting data. Our research proposed a convolutional autoencoder to classify the breast cancer tumors, using the Sultan Qaboos University Hospital(SQUH) and BreakHis datasets. The proposed model named Convolutional AutoEncoder with modified Loss Function (CAE-LF) achieved a good performance, by attaining a F1-score of 0.90, recall of 0.89, and accuracy of 91%. The results obtained are comparable to those obtained in earlier researches. Additional analyses conducted on the SQUH dataset demonstrate that it yields a good performance with an F1-score of 0.91, 0.93, 0.92, and 0.93 for 4x, 10x, 20x, and 40x magnifications, respectively. Our study highlights the potential of deep learning in analyzing medical images to classify breast tumors. • Developed a Convolutional AutoEncoder with a modified loss function (CAE-LF) for efficient and accurate classification of breast cancer tumors. • The model demonstrated excellent performance with an accuracy of 91%, and F1-scores ranging up to 0.93 across different image magnifications (4x, 10x, 20x, 40x). • Explored potential barriers to clinical implementation, including issues with data quality and availability, and provided insights into adapting deep learning tools for real-world medical applications.