AUTHOR=Zaman Asim , Hassan Haseeb , Zeng Xueqiang , Khan Rashid , Lu Jiaxi , Yang Huihui , Miao Xiaoqiang , Cao Anbo , Yang Yingjian , Huang Bingding , Guo Yingwei , Kang Yan 

TITLE=Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1363930

DOI=10.3389/fnins.2024.1363930

ISSN=1662-453X

ABSTRACT=In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic. To tackle this issue, we present a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability. AFMS-Net both variants are designed to construct a lightweight architecture, handle more complex segmentation problems with precision, and exhibit exceptional performance on notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022.