کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Improved Attention U-Net combined with Conditional Random Field for Ischemic Lesion Segmentation from Magnetic Resonance Images

نویسندگان :

Ali Rezaei¹ Asieh Khosravanian² Habibollah Danyali³ Kamran Kazemi⁴ Ardalan Aarabi⁵

1- دانشگاه صنعتی شیراز 2- دانشگاه صنعتی شیراز 3- دانشگاه صنعتی شیراز 4- دانشگاه صنعتی شیراز 5- University of Picardy Jules Verne

کلمات کلیدی :

Ischemic Stroke،Segmentation،Deep Learning،U-Net،Conditional Random Field

چکیده :

Stroke Lesion segmentation from magnetic resonance images is of great research interest due to its capability in providing appropriate clinical information for effective treatment of stroke. Deep learning methods have demonstrated promising results in medical image segmentation and U-Net is one of the most effective models. Nevertheless, these algorithms in the area of ischemic stroke lesion segmentation are in first stages of development and they lack performance compared to other problems for instance brain tumor segmentation. In this paper, we improved U-Net algorithm by applying blocks consist of depth-wise separable convolutions with skip connections instead of normal convolution layers and new attention blocks. Based on these improvements, the new architecture has better performance and accuracy with fewer parameter which would need simpler equipment for implementation. We utilized 3D fully connected Conditional Random Field (CRF) as post processing to improve the model prediction. Experimental results showed that the proposed end-to-end deep encoder-decoder model has a significant improvement compared to existing deep learning methods on the publicly available Anatomical Tracings of Lesion After Stroke (ATLAS) dataset.