Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 22, 2025

Abstract Accurate brain tumor segmentation is critical for clinical diagnosis and treatment planning. This study proposes an advanced framework that combines Multiscale Attention U-Net with the EfficientNetB4 encoder to enhance performance. Unlike conventional U-Net-based architectures, proposed model leverages EfficientNetB4’s compound scaling optimize feature extraction at multiple resolutions while maintaining low computational overhead. Additionally, Multi-Scale Mechanism (utilizing $$1\times 1, 3\times 3$$ , $$5\times 5$$ kernels) enhances representation by capturing boundaries across different scales, addressing limitations of existing CNN-based methods. Our approach effectively suppresses irrelevant regions localization through attention-enhanced skip connections residual attention blocks. Extensive experiments were conducted on publicly available Figshare dataset, comparing EfficientNet variants determine optimal architecture. demonstrated superior performance, achieving Accuracy 99.79%, MCR 0.21%, Dice Coefficient 0.9339, Intersection over Union (IoU) 0.8795, outperforming other in accuracy efficiency. The training process was analyzed using key metrics, including Coefficient, dice loss, precision, recall, specificity, IoU, showing stable convergence generalization. method evaluated against state-of-the-art approaches, surpassing them all accuracy, mean IoU. demonstrates effectiveness robust efficient tumors, positioning it as a valuable tool research applications.

Язык: Английский

MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3791 - 3791

Опубликована: Март 30, 2025

Brain tumors are a type of disease that affects people’s health and have received extensive attention. Accurate segmentation Magnetic Resonance Imaging (MRI) images for brain is essential effective treatment strategies. However, there scope enhancing the accuracy established deep learning approaches, such as 3D U-Net. In pursuit improved precision tumor MRI images, we propose MEASegNet, which incorporates multiple efficient attention mechanisms into U-Net architecture. The encoder employs Parallel Channel Spatial Attention Block (PCSAB), bottleneck layer leverages Reduce Residual Atrous Pyramid Pooling (CRRASPP) attention, decoder Selective Large Receptive Field (SLRFB). Through integration various mechanisms, enhance capacity detailed feature extraction, facilitate interplay among distinct features, ensure retention more comprehensive information. Consequently, this leads to an enhancement in images. conclusion, our experimentation on BraTS2021 dataset yields Dice scores 92.50%, 87.49%, 84.16% Whole Tumor (WT), Core (TC), Enhancing (ET), respectively. These results indicate marked improvement over conventional

Язык: Английский