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

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

doi:10.3389/fnins.2024.1363930

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

Front Neurosci. 2024 Apr 12:18:1363930. doi: 10.3389/fnins.2024.1363930. eCollection 2024.

Authors

Asim Zaman^{1

2

3

4}, Haseeb Hassan², Xueqiang Zeng^{2

3}, Rashid Khan^{3

4

5}, Jiaxi Lu^{2

3}, Huihui Yang^{2

3}, Xiaoqiang Miao^{2

6}, Anbo Cao^{2

3}, Yingjian Yang⁷, Bingding Huang⁵, Yingwei Guo^{2

8}, Yan Kang^{1

2

3

4

6}

Affiliations

¹ School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China.
² College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen, China.
³ School of Applied Technology, Shenzhen University, Shenzhen, China.
⁴ Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen, China.
⁵ College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China.
⁶ College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
⁷ Shenzhen Lanmage Medical Technology Co., Ltd, Shenzhen, China.
⁸ School of Electrical and Information Engineering, Northeast Petroleum University, Daqing, China.

Abstract

Introduction: In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to 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.

Methods: We introduce 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.

Results: AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.

Discussion: The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.

Keywords: adaptive feature extraction; attention mechanism; brain lesion segmentation; computer-aided diagnosis; deep learning; encoder-decoder architecture; medical image analysis; neurological diagnostics.

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The National Key Research and Development Program of China, Grant Nos. 2022YFF0710800 and 2022YFF0710802; the National Natural Science Foundation of China, Grant Number 62071311; the Special Program for Key Fields of Colleges and Universities in Guangdong Province (Biomedicine and Health) of China, Grant Number 2021ZDZX2008; and the Stable Support Plan for Colleges and Universities in Shenzhen of China, Grant Number SZWD2021010.