A white matter hyperintensity segmentation model combining 2.5-dimensional spatial context and frequency-domain prior information_Journal of Biomedical Engineering

Authors：

BAI Peirui ¹ , WANG Yuemin ¹ , LIU Qingyi ¹ , CHEN Xue ² ,  REN Yande ³

1. College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590, P. R. China;
2. Institute for Digital Medicine and Computer-assisted Surgery, Qingdao University, Qingdao, Shandong 266071, P. R. China;
3. Department of Radiology, Affiliated Hospital of Qingdao University, Qingdao, Shandong 265000, P. R. China;

Corresponding?author：

REN Yande, Email: 8198458ryd@qdu.edu.cn

Keywords：

White matter hyperintensities; Magnetic resonance imaging; Image segmentation; Transformer; U-Net; Frequency-domain priors; 2.5-dimensional segmentation

DOI：

10.7507/1001-5515.202606023

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Imaging studies indicate that white matter hyperintensities (WMHs) are closely associated with various cerebrovascular and neurodegenerative diseases, and their accurate segmentation is of great significance for the clinical diagnosis and treatment of related brain diseases. However, affected by factors such as insufficient inter-slice resolution caused by magnetic resonance imaging (MRI) voxel anisotropy, blurred boundaries of tiny lesions, and multi-center data heterogeneity, the performance of existing methods still needs to be improved. Targeting 2.5-dimensional (2.5D) MRI slice sequence data, this paper proposes an automatic segmentation network integrating slice context and frequency-domain prior information. First, a inter-slice context Transformer (ISCT) module is designed to extract Z-axis long-range dependencies, in order to reduce inter-slice information loss. Second, a frequency-domain encoder based on learnable discrete wavelet transform (LDWT) is constructed to decouple high- and low-frequency features, and combined with a detail gating module (DGM) to suppress background noise. Finally, a weighted focal Tversky loss function is introduced to enhance the detection robustness for tiny lesions. Experimental results show that the proposed model achieves Dice similarity coefficients (DSC) of 0.800 8 ± 0.077 3 and 0.763 6 ± 0.180 2, and recall of 0.831 1 ± 0.081 8 and 0.852 0 ± 0.204 5 on public and in-house datasets, respectively, and its generalization ability outperforms existing mainstream methods. This model effectively mitigates problems such as lesion omission and cross-domain performance degradation, providing an accurate and robust evaluation tool for the clinical diagnosis and treatment of related diseases.

Citation： BAI Peirui, WANG Yuemin, LIU Qingyi, CHEN Xue, REN Yande. A white matter hyperintensity segmentation model combining 2.5-dimensional spatial context and frequency-domain prior information. Journal of Biomedical Engineering, 2026, 43(5): 1001-1009. doi: 10.7507/1001-5515.202606023 Copy

1.	中華醫學會神經病學分會, 中華醫學會神經病學分會腦血管病學組. 中國腦小血管病診治指南2020[J]. 中華神經科雜志, 2022, 55(8): 807-818.
2.	Debette S, Beiser A, Decarli C, et al. Association of MRI markers of vascular brain injury with incident stroke, mild cognitive impairment, dementia, and mortality: the Framingham Offspring Study[J]. Stroke, 2010, 41(4): 600-606.
3.	Wardlaw J M, Smith E E, Biessels G J, et al. Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration[J]. Lancet Neurol, 2013, 12(8): 822-838.
4.	Rahmani M, Dierker D, Yaeger L, et al. Evolution of white matter hyperintensity segmentation methods and implementation over the past two decades; an incomplete shift towards deep learning[J]. Brain Imaging Behav, 2024, 18(5): 1310-1322.
5.	趙建國, 李文斌. 醫學圖像分析方法研究進展[J]. 生物醫學工程學雜志, 2019, 36(2): 247-254.
6.	Schmidt P, Gaser C, Arsic M, et al. An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis[J]. Neuroimage, 2012, 59(4): 3774-3783.
7.	Griffanti L, Zamboni G, Khan A, et al. BIANCA (Brain Intensity AbNormality Classification Algorithm): a new tool for automated segmentation of white matter hyperintensities[J]. Neuroimage, 2016, 141: 191-205.
8.	白培瑞, 李崢, 劉慶一, 等. 基于三維模糊連接脈沖耦合神經網絡的腎臟CT圖像自動分割算法[J]. 電子與信息學報, 2023, 45(6): 2264-2272.
9.	張華海, 白培瑞, 郭子楊, 等. 一種融合表面波變換與脈沖耦合神經網絡的三維肺實質分割算法[J]. 生物醫學工程學雜志, 2020, 37(4): 630-640.
10.	Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, Munich: Springer, 2015: 234-241.
11.	Li H, Jiang G, Zhang J, et al. Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images[J]. Neuroimage, 2018, 183: 650-665.
12.	He H, Jiang J, Peng S, et al. A robust automated segmentation method for white matter hyperintensity of vascular-origin[J]. Neuroimage, 2025, 315: 121279.
13.	張新峰, 梁玉清, 李相生, 等. 基于SE-UNet的腦白質高信號分割方法[J]. 北京生物醫學工程, 2025, 44(4): 365-372.
14.	Panduri B, Rao O S. Deep optimization-guided hybrid neural network for accurate detection and segmentation of white matter hyperintensities in clinical MRI images[J]. Sci Rep, 2026, 16(1): 16211.
15.	Sundaresan V, Zamboni G, Rothwell P M, et al. Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images[J]. Med Image Anal, 2021, 73: 102184.
16.	Duarte K T, Gobbi D G, Sidhu A S, et al. Segmenting white matter hyperintensities in brain magnetic resonance images using convolution neural networks[J]. Pattern Recognit Lett, 2023, 175: 90-94.
17.	Huang L, Sun Y, Zhao Z, et al. 2.5D ASF-UNet: adjacent slice spatial feature fusion model for WMH segmentation from 3D MR brain image[C]//2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon: IEEE, 2024: 2054-2059.
18.	Zhang L, Niu K, Sun Y, et al. White matter hyperintensity segmentation of multiple sclerosis and neuromyelitis optical spectrum disorders using 2.5D FrC-ResUnet[J]. Quant Imaging Med Surg, 2025, 15(11): 11066-11082.
19.	Hou Y, Chen N, Huo T, et al. MemSAM-2.5D: overcoming volumetric discontinuity and boundary ambiguity for 3D liver tumor segmentation[J]. Front Oncol, 2026, 16: 1850004.
20.	Wu H, Chen J, Lv C, et al. Adjacent slices disentangled 2.5D network for spinal segmentation on multi-view MR images[J]. Biomed Signal Process Control, 2025, 107: 107809.
21.	Park G, Hong J, Duffy B A, et al. White matter hyperintensities segmentation using the ensemble U-Net with multi-scale highlighting foregrounds[J]. Neuroimage, 2021, 237: 118140.
22.	Duarte K T N, de Barros M C, Sidhu A S, et al. Attention blocks improve white matter hyperintensity semantic segmentation using U-nets[J]. IEEE Lat Am Trans, 2025, 23(8): 646-661.
23.	Chen Y T, Huang Y C, Chen H L, et al. Automatic segmentation of white matter lesions on multi-parametric MRI: convolutional neural network versus vision transformer[J]. BMC Neurol, 2025, 25(1): 5.
24.	Farkhani S, Demnitz N, Boraxbekk C J, et al. End-to-end volumetric segmentation of white matter hyperintensities using deep learning[J]. Comput Methods Programs Biomed, 2024, 245: 108008.
25.	Cao H, Wang Y, Chen J, et al. Swin-Unet: U-Net-like pure transformer for medical image segmentation[C]//Computer Vision - ECCV 2022 Workshops, Tel Aviv: Springer, 2022: 205-218.
26.	Ma J, Li F, Wang B. U-Mamba: enhancing long-range dependency for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2024, Marrakesh: Springer, 2024: 29-39.
27.	Wu J, Brown J D, Hu R, et al. Benchmark white matter hyperintensity segmentation methods fail on heterogeneous clinical MRI: a new dataset and deep learning-based solutions[J]. J Imaging Inform Med, 2026: 1-9.
28.	Karimzadeh M, Seyedarabi H, Jodeiri A, et al. Enhanced brain stroke lesion segmentation in MRI using a 2.5D transformer backbone U-Net model[J]. Brain Sci, 2025, 15(8): 778.
29.	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, Long Beach: Curran Associates, 2017: 5998-6008.
30.	Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City: IEEE, 2018: 7132-7141.
31.	Liu P, Zhang H, Zhang K, et al. Multi-level wavelet-CNN for image restoration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City: IEEE, 2018: 773-782.
32.	Qin Z, Zhang P, Wu F, et al. FCANet: frequency channel attention networks[J]. IEEE Trans Pattern Anal Mach Intell, 2024, 46(1): 405-418.
33.	Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks[C]//International Workshop on Machine Learning in Medical Imaging, Quebec City: Springer, 2017: 379-387.
34.	Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, Venice: IEEE, 2017: 2980-2988.
35.	Kuijf H J, Biesbroek J M, de Bresser J, et al. Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge[J]. IEEE Trans Med Imaging, 2019, 38(11): 2556-2568.
36.	Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. UNet++: redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Trans Med Imaging, 2020, 39(6): 1856-1867.
37.	Schlemper J, Oktay O, Schaap M, et al. Attention gated networks: learning to leverage salient regions in medical images[J]. Med Image Anal, 2019, 53: 197-207.
38.	Zhang Z, Liu Q, Wang Y. Road extraction by deep residual U-Net[J]. IEEE Geosci Remote Sens Lett, 2018, 15(5): 749-753.
39.	Chen J, Mei J, Li X, et al. TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers[J]. Med Image Anal, 2024, 97: 103280.
40.	Isensee F, Jaeger P F, Kohl S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nat Methods, 2021, 18(2): 203-211.

1. 中華醫學會神經病學分會, 中華醫學會神經病學分會腦血管病學組. 中國腦小血管病診治指南2020[J]. 中華神經科雜志, 2022, 55(8): 807-818.
2. Debette S, Beiser A, Decarli C, et al. Association of MRI markers of vascular brain injury with incident stroke, mild cognitive impairment, dementia, and mortality: the Framingham Offspring Study[J]. Stroke, 2010, 41(4): 600-606.
3. Wardlaw J M, Smith E E, Biessels G J, et al. Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration[J]. Lancet Neurol, 2013, 12(8): 822-838.
4. Rahmani M, Dierker D, Yaeger L, et al. Evolution of white matter hyperintensity segmentation methods and implementation over the past two decades; an incomplete shift towards deep learning[J]. Brain Imaging Behav, 2024, 18(5): 1310-1322.
5. 趙建國, 李文斌. 醫學圖像分析方法研究進展[J]. 生物醫學工程學雜志, 2019, 36(2): 247-254.
6. Schmidt P, Gaser C, Arsic M, et al. An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis[J]. Neuroimage, 2012, 59(4): 3774-3783.
7. Griffanti L, Zamboni G, Khan A, et al. BIANCA (Brain Intensity AbNormality Classification Algorithm): a new tool for automated segmentation of white matter hyperintensities[J]. Neuroimage, 2016, 141: 191-205.
8. 白培瑞, 李崢, 劉慶一, 等. 基于三維模糊連接脈沖耦合神經網絡的腎臟CT圖像自動分割算法[J]. 電子與信息學報, 2023, 45(6): 2264-2272.
9. 張華海, 白培瑞, 郭子楊, 等. 一種融合表面波變換與脈沖耦合神經網絡的三維肺實質分割算法[J]. 生物醫學工程學雜志, 2020, 37(4): 630-640.
10. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, Munich: Springer, 2015: 234-241.
11. Li H, Jiang G, Zhang J, et al. Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images[J]. Neuroimage, 2018, 183: 650-665.
12. He H, Jiang J, Peng S, et al. A robust automated segmentation method for white matter hyperintensity of vascular-origin[J]. Neuroimage, 2025, 315: 121279.
13. 張新峰, 梁玉清, 李相生, 等. 基于SE-UNet的腦白質高信號分割方法[J]. 北京生物醫學工程, 2025, 44(4): 365-372.
14. Panduri B, Rao O S. Deep optimization-guided hybrid neural network for accurate detection and segmentation of white matter hyperintensities in clinical MRI images[J]. Sci Rep, 2026, 16(1): 16211.
15. Sundaresan V, Zamboni G, Rothwell P M, et al. Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images[J]. Med Image Anal, 2021, 73: 102184.
16. Duarte K T, Gobbi D G, Sidhu A S, et al. Segmenting white matter hyperintensities in brain magnetic resonance images using convolution neural networks[J]. Pattern Recognit Lett, 2023, 175: 90-94.
17. Huang L, Sun Y, Zhao Z, et al. 2.5D ASF-UNet: adjacent slice spatial feature fusion model for WMH segmentation from 3D MR brain image[C]//2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon: IEEE, 2024: 2054-2059.
18. Zhang L, Niu K, Sun Y, et al. White matter hyperintensity segmentation of multiple sclerosis and neuromyelitis optical spectrum disorders using 2.5D FrC-ResUnet[J]. Quant Imaging Med Surg, 2025, 15(11): 11066-11082.
19. Hou Y, Chen N, Huo T, et al. MemSAM-2.5D: overcoming volumetric discontinuity and boundary ambiguity for 3D liver tumor segmentation[J]. Front Oncol, 2026, 16: 1850004.
20. Wu H, Chen J, Lv C, et al. Adjacent slices disentangled 2.5D network for spinal segmentation on multi-view MR images[J]. Biomed Signal Process Control, 2025, 107: 107809.
21. Park G, Hong J, Duffy B A, et al. White matter hyperintensities segmentation using the ensemble U-Net with multi-scale highlighting foregrounds[J]. Neuroimage, 2021, 237: 118140.
22. Duarte K T N, de Barros M C, Sidhu A S, et al. Attention blocks improve white matter hyperintensity semantic segmentation using U-nets[J]. IEEE Lat Am Trans, 2025, 23(8): 646-661.
23. Chen Y T, Huang Y C, Chen H L, et al. Automatic segmentation of white matter lesions on multi-parametric MRI: convolutional neural network versus vision transformer[J]. BMC Neurol, 2025, 25(1): 5.
24. Farkhani S, Demnitz N, Boraxbekk C J, et al. End-to-end volumetric segmentation of white matter hyperintensities using deep learning[J]. Comput Methods Programs Biomed, 2024, 245: 108008.
25. Cao H, Wang Y, Chen J, et al. Swin-Unet: U-Net-like pure transformer for medical image segmentation[C]//Computer Vision - ECCV 2022 Workshops, Tel Aviv: Springer, 2022: 205-218.
26. Ma J, Li F, Wang B. U-Mamba: enhancing long-range dependency for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2024, Marrakesh: Springer, 2024: 29-39.
27. Wu J, Brown J D, Hu R, et al. Benchmark white matter hyperintensity segmentation methods fail on heterogeneous clinical MRI: a new dataset and deep learning-based solutions[J]. J Imaging Inform Med, 2026: 1-9.
28. Karimzadeh M, Seyedarabi H, Jodeiri A, et al. Enhanced brain stroke lesion segmentation in MRI using a 2.5D transformer backbone U-Net model[J]. Brain Sci, 2025, 15(8): 778.
29. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, Long Beach: Curran Associates, 2017: 5998-6008.
30. Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City: IEEE, 2018: 7132-7141.
31. Liu P, Zhang H, Zhang K, et al. Multi-level wavelet-CNN for image restoration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City: IEEE, 2018: 773-782.
32. Qin Z, Zhang P, Wu F, et al. FCANet: frequency channel attention networks[J]. IEEE Trans Pattern Anal Mach Intell, 2024, 46(1): 405-418.
33. Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks[C]//International Workshop on Machine Learning in Medical Imaging, Quebec City: Springer, 2017: 379-387.
34. Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, Venice: IEEE, 2017: 2980-2988.
35. Kuijf H J, Biesbroek J M, de Bresser J, et al. Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge[J]. IEEE Trans Med Imaging, 2019, 38(11): 2556-2568.
36. Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. UNet++: redesigning skip connections to exploit multiscale features in image segmentation[J]. IEEE Trans Med Imaging, 2020, 39(6): 1856-1867.
37. Schlemper J, Oktay O, Schaap M, et al. Attention gated networks: learning to leverage salient regions in medical images[J]. Med Image Anal, 2019, 53: 197-207.
38. Zhang Z, Liu Q, Wang Y. Road extraction by deep residual U-Net[J]. IEEE Geosci Remote Sens Lett, 2018, 15(5): 749-753.
39. Chen J, Mei J, Li X, et al. TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers[J]. Med Image Anal, 2024, 97: 103280.
40. Isensee F, Jaeger P F, Kohl S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nat Methods, 2021, 18(2): 203-211.

Next Article
A multi-scale attention and federated learning-based method for human epidermal growth factor receptor 2 immunohistochemical grading of breast cancer

Journal of Biomedical Engineering

A white matter hyperintensity segmentation model combining 2.5-dimensional spatial context and frequency-domain prior information

Abstract Full text Figures/Tables Video References Cited by

Next Article

Format

Content