U-Net-based architecture with attention mechanisms and Bayesian Optimization for brain tumor segmentation using MR images

• Published in: Computers in biology and medicine Vol. 195; p. 110677
• Main Authors: Ramalakshmi, K., Krishna Kumari, L.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2025
• Subjects: Algorithms; Attention mechanisms; Bayes Theorem; Bayesian optimization; Brain Neoplasms - diagnostic imaging; Brain tumor segmentation; Deep Learning; Humans; Image Interpretation, Computer-Assisted - methods; Internal Medicine; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Other; Region-adaptive thresholding; U-Net architecture; Attention mechanisms; Brain tumor segmentation; Magnetic resonance imaging; Bayesian optimization; Region-adaptive thresholding; U-Net architecture
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2025.110677

As technological innovation in computers has advanced, radiologists may now diagnose brain tumors (BT) with the use of artificial intelligence (AI). In the medical field, early disease identification enables further therapies, where the use of AI systems is essential for time and money savings. The difficulties presented by various forms of Magnetic Resonance (MR) imaging for BT detection are frequently not addressed by conventional techniques. To get around frequent problems with traditional tumor detection approaches, deep learning techniques have been expanded. Thus, for BT segmentation utilizing MR images, a U-Net-based architecture combined with Attention Mechanisms has been developed in this work. Moreover, by fine-tuning essential variables, Hyperparameter Optimization (HPO) is used using the Bayesian Optimization Algorithm to strengthen the segmentation model's performance. Tumor regions are pinpointed for segmentation using Region-Adaptive Thresholding technique, and the segmentation results are validated against ground truth annotated images to assess the performance of the suggested model. Experiments are conducted using the LGG, Healthcare, and BraTS 2021 MRI brain tumor datasets. Lastly, the importance of the suggested model has been demonstrated through comparing several metrics, such as IoU, accuracy, and DICE Score, with current state-of-the-art methods. The U-Net-based method gained a higher DICE score of 0.89687 in the segmentation of MRI-BT. •U-Net with Attention Mechanisms is used for brain tumor segmentation in MRI images.•Bayesian Optimization performs hyperparameter tuning to improve model performance.•Region-Adaptive Thresholding is applied to segment tumor regions precisely in MRI images.•The model's segmentation results are validated using IoU, accuracy, and DICE score metrics.•The proposed method achieves 99.78 % accuracy and a DICE score of 0.89687, outperforming existing techniques.