An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness

Nan, Jiaofen; Fan, Gaodeng; Zhang, Kaifan; Zhai, Shuyao; Jin, Xueqi; Li, Duan; Yu, Chunlai

doi:10.3390/electronics14183631

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness

by

Jiaofen Nan

¹,

Gaodeng Fan

¹,

Kaifan Zhang

¹,

Shuyao Zhai

¹,

Xueqi Jin

¹,

Duan Li

^1,*

and

Chunlai Yu

²

¹

School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450001, China

²

Engineering Division, Huanghe University of Science and Technology, Zhengzhou 450061, China

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(18), 3631; https://doi.org/10.3390/electronics14183631 (registering DOI)

Submission received: 28 July 2025 / Revised: 2 September 2025 / Accepted: 11 September 2025 / Published: 13 September 2025

Download Versions Notes

Abstract

To address the limitations in the accuracy of current cerebral cortex structure segmentation methods, this study proposes an automatic segmentation network based on dynamic recalibration and region awareness. The network is an improved version of the classic U-shaped architecture, incorporating a Dynamic Recalibration Block (DRB) and a Region-Aware Block (RAB). The DRB enhances important feature channels by extracting global feature information across channels, computing the significance weights via a two-layer fully connected network, and applying these weights to the original feature maps for dynamic feature reweighting. Meanwhile, the RAB integrates spatial positional information and captures both global and local context across multiple dimensions. It recalibrates features using dimension-specific weights, enabling region-aware feature association and complementing the DRB’s function. Together, these components enable efficient and accurate segmentation of brain structures. The proposed DRA-Net model effectively overcomes the accuracy–efficiency trade-off in cortical segmentation through multi-scale feature fusion, dual attention mechanisms, and deep feature extraction strategies. Experimental results demonstrate that DRA-Net achieves an average Dice score of 91.35% across multiple datasets, outperforming segmentation atlases based on methods such as U-Net, QuickNAT, and FastSurfer.

Keywords: region awareness; cerebral cortex; dynamic recalibration

Share and Cite

MDPI and ACS Style

Nan, J.; Fan, G.; Zhang, K.; Zhai, S.; Jin, X.; Li, D.; Yu, C. An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness. Electronics 2025, 14, 3631. https://doi.org/10.3390/electronics14183631

AMA Style

Nan J, Fan G, Zhang K, Zhai S, Jin X, Li D, Yu C. An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness. Electronics. 2025; 14(18):3631. https://doi.org/10.3390/electronics14183631

Chicago/Turabian Style

Nan, Jiaofen, Gaodeng Fan, Kaifan Zhang, Shuyao Zhai, Xueqi Jin, Duan Li, and Chunlai Yu. 2025. "An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness" Electronics 14, no. 18: 3631. https://doi.org/10.3390/electronics14183631

APA Style

Nan, J., Fan, G., Zhang, K., Zhai, S., Jin, X., Li, D., & Yu, C. (2025). An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness. Electronics, 14(18), 3631. https://doi.org/10.3390/electronics14183631

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

An Automatic Brain Cortex Segmentation Technique Based on Dynamic Recalibration and Region Awareness

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI