An Enhanced UNet++ with InceptionNeXt Blocks and Feature-Scale Channel Attention for Ischemic Stroke Lesion Segmentation
DOI:
https://doi.org/10.62411/jcta.16410Keywords:
Computer-Aided Diagnosis, Deep Learning, Feature-Scale Channel Attention, InceptionNeXt, Ischemic Stroke, Medical Image Segmentation, Multi-Sequence MRI, UNetAbstract
Ischemic stroke lesion segmentation from Magnetic Resonance Imaging (MRI) remains a challenging task due to the small lesion size, irregular morphology, low contrast with surrounding tissue, and severe class imbalance. To address these challenges, this study proposes an enhanced UNet++ architecture that integrates Modified InceptionNeXt Blocks and Feature-Scale Channel Attention (FSCA) to improve multi-scale feature extraction and adaptive feature fusion. Hyperparameter tuning was performed by optimizing the number of initial filters, network depth, and loss function, followed by an ablation study to evaluate the contribution of each architectural component. The proposed model was implemented using the TensorFlow framework and evaluated on the ISLES 2022 dataset. To enhance lesion visibility, Diffusion-Weighted Imaging (DWI) was processed using Contrast Limited Adaptive Histogram Equalization (CLAHE) to generate enhanced DWI (eDWI). Three input configurations, namely DWI, DWI+ADC, and DWI+ADC+eDWI, were investigated through channel concatenation. Performance was assessed using Dice Score, Intersection over Union (IoU), Precision, and Recall. Experimental results demonstrate that the proposed UNet++ model with Modified InceptionNeXt Blocks and FSCA achieves the best performance using the DWI+ADC+eDWI configuration, obtaining a Dice Score of 0.8742, IoU of 0.8464, Precision of 0.9440, and Recall of 0.8906. Furthermore, the segmentation results exhibit high agreement with the ground truth, indicating that the proposed architecture effectively improves ischemic stroke lesion segmentation while maintaining computational efficiency.References
W. J. Powers et al., “Guidelines for the Early Management of Patients With Acute Ischemic Stroke: 2019 Update to the 2018 Guidelines for the Early Management of Acute Ischemic Stroke: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke ,” Stroke, vol. 50, no. 12, Dec. 2019, doi: 10.1161/STR.0000000000000211.
S. S. Virani et al., “Heart Disease and Stroke Statistics—2020 Update: A Report From the American Heart Association,” Circulation, vol. 141, no. 9, Mar. 2020, doi: 10.1161/CIR.0000000000000757.
J. B. Fiebach et al., “CT and Diffusion-Weighted MR Imaging in Randomized Order,” Stroke, vol. 33, no. 9, pp. 2206–2210, Sep. 2002, doi: 10.1161/01.STR.0000026864.20339.CB.
G. W. Albers et al., “Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging,” N. Engl. J. Med., vol. 378, no. 8, pp. 708–718, Feb. 2018, doi: 10.1056/NEJMoa1713973.
O. Maier et al., “ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI,” Med. Image Anal., vol. 35, pp. 250–269, Jan. 2017, doi: 10.1016/j.media.2016.07.009.
M. R. Hernandez Petzsche et al., “ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset,” Sci. Data, vol. 9, no. 1, p. 762, Dec. 2022, doi: 10.1038/s41597-022-01875-5.
Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018, pp. 3–11. doi: 10.1007/978-3-030-00889-5_1.
F. Isensee, P. F. Jaeger, S. A. A. Kohl, J. Petersen, and K. H. Maier-Hein, “nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation,” Nat. Methods, vol. 18, no. 2, pp. 203–211, Feb. 2021, doi: 10.1038/s41592-020-01008-z.
M. A. Hambali and P. A. Agwu, “Adversarial Convolutional Neural Network for Predicting Blood Clot Ischemic Stroke,” J. Comput. Theor. Appl., vol. 2, no. 1, pp. 51–64, Jun. 2024, doi: 10.62411/jcta.10516.
W. Jiangtao, N. I. R. Ruhaiyem, and F. Panpan, “A Comprehensive Review of U‐Net and Its Variants: Advances and Applications in Medical Image Segmentation,” IET Image Process., vol. 19, no. 1, Jan. 2025, doi: 10.1049/ipr2.70019.
S. Zuo, Y. Xiao, X. Chang, and X. Wang, “Vision transformers for dense prediction: A survey,” Knowledge-Based Syst., vol. 253, p. 109552, Oct. 2022, doi: 10.1016/j.knosys.2022.109552.
C. Asuai et al., “Transformer-Augmented Deep Learning Ensemble for Multi-Modal Neuroimaging-Based Diagnosis of Amyotrophic Lateral Sclerosis,” J. Comput. Theor. Appl., vol. 3, no. 2, pp. 190–205, Oct. 2025, doi: 10.62411/jcta.14661.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Lecture Notes in Computer Science, Springer, 2015, pp. 234–241. doi: 10.1007/978-3-319-24574-4_28.
J. Tagnamas, H. Ramadan, A. Yahyaouy, and H. Tairi, “SCA-InceptionUNeXt: A lightweight Spatial-Channel-Attention-based network for efficient medical image segmentation,” Knowledge-Based Syst., vol. 311, p. 113166, Feb. 2025, doi: 10.1016/j.knosys.2025.113166.
C. Szegedy et al., “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2015, pp. 1–9. doi: 10.1109/CVPR.2015.7298594.
A. Rahman et al., “Deep learning-driven segmentation of ischemic stroke lesions using multi-channel MRI,” Biomed. Signal Process. Control, vol. 105, p. 107676, Jul. 2025, doi: 10.1016/j.bspc.2025.107676.
S. M. Pizer, R. E. Johnston, J. P. Ericksen, B. C. Yankaskas, and K. E. Muller, “Contrast-limited adaptive histogram equalization: speed and effectiveness,” in [1990] Proceedings of the First Conference on Visualization in Biomedical Computing, pp. 337–345. doi: 10.1109/VBC.1990.109340.
S. S. M. Salehi, D. Erdogmus, and A. Gholipour, “Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks,” in Lecture Notes in Computer Science, 2017, pp. 379–387. doi: 10.1007/978-3-319-67389-9_44.
C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. Jorge Cardoso, “Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations,” in Lecture Notes in Computer Science, 2017, pp. 240–248. doi: 10.1007/978-3-319-67558-9_28.
G. Kaur and J. Chhaterji, “A Survey on Medical Image Segmentation,” Int. J. Sci. Res., vol. 6, no. 5, pp. 1305–1311, 2017, [Online]. Available: https://www.ijsr.net/archive/v6i5/ART20173326.pdf
Y. Zhang, J. M. Gorriz, and Z. Dong, “Deep Learning in Medical Image Analysis,” J. Imaging, vol. 7, no. 4, p. 74, Apr. 2021, doi: 10.3390/jimaging7040074.
S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional Block Attention Module,” in Lecture Notes in Computer Science, 2018, pp. 3–19. doi: 10.1007/978-3-030-01234-2_1.
Y. Ye et al., “Image segmentation using improved U-Net model and convolutional block attention module based on cardiac magnetic resonance imaging,” J. Radiat. Res. Appl. Sci., vol. 17, no. 1, p. 100816, Mar. 2024, doi: 10.1016/j.jrras.2023.100816.
W. Yu, P. Zhou, S. Yan, and X. Wang, “InceptionNeXt: When Inception Meets ConvNeXt,” ArXiv. Apr. 05, 2025. [Online]. Available: http://arxiv.org/abs/2303.16900
Y. Gao, Y. Jiang, Y. Peng, F. Yuan, X. Zhang, and J. Wang, “Medical Image Segmentation: A Comprehensive Review of Deep Learning-Based Methods,” Tomography, vol. 11, no. 5, p. 52, Apr. 2025, doi: 10.3390/tomography11050052.
Y. Liu, Z. Zhang, J. Yue, and W. Guo, “SCANeXt: Enhancing 3D medical image segmentation with dual attention network and depth-wise convolution,” Heliyon, vol. 10, no. 5, p. e26775, Mar. 2024, doi: 10.1016/j.heliyon.2024.e26775.
T. Li et al., “SrSNet: Accurate segmentation of stroke lesions by a two-stage segmentation framework with asymmetry information,” Expert Syst. Appl., vol. 254, p. 124329, Nov. 2024, doi: 10.1016/j.eswa.2024.124329.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv. Jan. 30, 2017. [Online]. Available: http://arxiv.org/abs/1412.6980
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Hilmy Naufal, Wiharto Wiharto, Herdito Ibnu Dewangkoro
This work is licensed under a Creative Commons Attribution 4.0 International License.
