SDA-UNET2.5D: Shallow Dilated with Attention Unet2.5D for Brain Tumor Segmentation

Abstract

Many studies have been carried out to segmentation brain tumors on 3D Magnetic Resonance Imaging (MRI) images with 3D or 2D approaches. The 3D approach pays attention to the interrelationships between slices in a 3D image. However, this requires high resources, while the 2D approach requires lower resources but ignores the voxel relationship in 3D space. The 2.5D approach seeks to combine the lightness of the 2D approach and the voxel interconnection of the 3D approach. This article proposes SDA-UNet2.5D, a shallow UNet 2.5D architecture that pays attention to the interconnectedness of 3D images by involving five slices to get one slice of segmentation prediction results. The architecture is trained using the Brain Tumor Segmentation (BraTS) 2018, 2019, and 2020 datasets. Compared to other architectures, this proposed architecture has a high segmentation speed with 4.05-4.24 seconds to segment one patient data. Online validation resulted in superior average dice

Enhancing Brain Tumor Detection and Classification with Reduced Complexity Spatial Fusion Convolutional Neural Networks

“…The SDA-UNET2.5D, a shallow dilated with attention UNet2.5D architecture for brain tumour segmentation, was presented by the authors, Agus Subhan Akbar et al [27]. This method provides a promising balance between depth and receptive field size, which may reduce computational requirements.…”

“…Complexity and Computational Efficiency are the limitations Autoencoders [26] While this method effectively performs image classification, it focuses on classification tasks This method may necessitate a large amount of labelled data, which is often difficult to obtain in medical imaging. SDA-UNET2.5D [27] a shallow dilated with attention UNet2.5D architecture for brain tumour segmentation emphasis on 2.5D MRI images and the lack of explicit discussions on computational efficiency. The authors also concentrated solely on dice score, with no comparison to Sensitivity and Specificity.…”

Brain Cancer Object Segmentation Using LPSIT Method and Back Propagation Network

“…This method is not capable to handle the complex MRI images. Akbar et al [33] reported a brain cancer segmentation method using Shallow dilated with attention Unet2,5D that works based on multi slices of MRI. The drawback is the limited dice segmentation performance.…”