1.School of Information Engineering, Ningxia University, Yinchuan 750021, China
2.Department of Pathology, General Hospital of Ningxia Medical University, Yinchuan 750021, China
3.Department of Pathology, Second Affiliated Hospital of Hainan Medical University, Haikou 570000, China
4.Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West, Yinchuan 750021, China
5.Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-founded by Ningxia Municipality and Ministry of Education, Yinchuan 750021, China
Objective To construct a high-value region-guided dual-network semi-supervised segmentation method (HVASS) under extremely low labeling rates for addressing the challenges of heterogeneity and blurred boundaries in MRI tumor subregions and improving the accuracy and reliability of complex boundary segmentation for the heart and glioma. Methods HVASS employs a dual-network collaborative learning architecture that leverages prediction inconsistency to automatically identify two clinically significant high-risk regions: the high-confidence ambiguity zones, where predictions between the two networks diverge despite at least one network exhibiting high confidence; and the low-confidence stable zones, where predictions agree but with consistently low confidence across both networks. To refine pseudo-label quality, an adaptive dual-teacher mutual distillation mechanism was introduced for dynamically leveraging complementary knowledge from both networks. A high-value region-aware convolutional module was integrated to strengthen feature representation at the tumor margins and the heterogeneous areas, while a wavelet-based frequency-domain refinement module was incorporated to preserve the fine-grained edge details. The framework was evaluated on two publicly available datasets: BraTS2019 for brain glioma MRI and ACDC for cardiac MRI. Results On the ACDC dataset, HVASS achieved a mean Dice score of 90.34% and a 95th percentile Hausdorff Distance (95HD) of 2.46 mm, representing a 3.24% improvement in Dice and a 2.68 mm reduction in 95HD compared to the state-of-the-art model. On BraTS2019, the model attained a Dice score of 85.07% and a 95HD of 7.68 mm, with a 3.8% increase in Dice for enhancing tumor sub-region and a substantial reduction of boundary localization error. Conclusion HVASS demonstrates superior segmentation performance under minimal annotation settings and allows effective capture of fuzzy boundaries and heterogeneous tumor regions in MRI. The method shows particular strength in segmenting small lesions and ill-defined edges and thus lessens the annotation burden of the radiologists.
为在空间-频域联合建模框架中进一步提升高价值区域(高置信歧义区Ω₂ 与低置信稳定区 Ω₃)的特征判别性与扰动一致性,本节提出小波频域特征精炼模块(WFFR),将其作为高价值区域感知卷积模块(HVAC)的前置频域增强单元。该模块采用单层 Haar 离散小波变换(DWT)对解码器中间层特征进行分解,得到低频平滑分量与高频细节分量,进而与HVAC中的通道-空间双注意力机制及原型一致性学习相结合,实现端到端协同优化,形成“频域分解→注意力门控→原型精炼→一致性加权”的完整闭环(图8)。
ChenXK, YuanYH, ZengG, et al. Semi-supervised semantic segmentation with cross pseudo supervision[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 20-25, 2021. Nashville, TN, USA. IEEE, 2021: 2613-22. doi:10.1109/cvpr46437.2021.00264
[10]
WuYC, XuMF, GeZY, et al. Semi-supervised left atrium segmentation with mutual ConsistencyTraining[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2021. Cham: Springer, 2021: 297-306. doi:10.1007/978-3-030-87196-3_28
[11]
AdigaV S, DolzJ, LombaertH. Anatomically-aware uncertainty for semi-supervised image segmentation[J]. Med Image Anal, 2024, 91: 103011. doi:10.1016/j.media.2023.103011
[12]
BernardO, LalandeA, ZottiC, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?[J]. IEEE Trans Med Imaging, 2018, 37(11): 2514-25. doi:10.1109/tmi.2018.2837502
[13]
BakasS, AkbariH, SotirasA, et al. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features[J]. Sci Data, 2017, 4: 170117. doi:10.1038/sdata.2017.117
ZhouZW, Rahman SiddiqueeMM, TajbakhshN, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer, 2018: 3-11. doi:10.1007/978-3-030-00889-5_1
[16]
ZhaoCJ, XiangS, WangYQ, et al. Context-aware network fusing transformer and V-Net for semi-supervised segmentation of 3D left atrium[J]. Expert Syst Appl, 2023, 214: 119105. doi:10.1016/j.eswa.2022.119105
[17]
TopolEJ. High-performance medicine: the convergence of human and artificial intelligence[J]. Nat Med, 2019, 25(1): 44-56. doi:10.1038/s41591-018-0300-7
[18]
TarvainenA, ValpolaH. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results[C]//Neural Information Processing Systems., 2017
[19]
XuZ, WangYX, LuDH, et al. Ambiguity-selective consistency regularization for mean-teacher semi-supervised medical image segmentation[J]. Med Image Anal, 2023, 88: 102880. doi:10.1016/j.media.2023.102880
[20]
ZhangYC, JiaoRS, LiaoQC, et al. Uncertainty-guided mutual consistency learning for semi-supervised medical image segmentation[J]. Artif Intell Med, 2023, 138: 102476. doi:10.1016/j.artmed.2022.102476
[21]
WangYC, XiaoB, BiXL, et al. MCF: mutual correction framework for semi-supervised medical image segmentation[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 17-24, 2023, Vancouver, BC, Canada. IEEE, 2023: 15651-60. doi:10.1109/cvpr52729.2023.01502
[22]
ChenYY, YangZY, ShenCY, et al. Evidence-based uncertainty-aware semi-supervised medical image segmentation[J]. Comput Biol Med, 2024, 170: 108004. doi:10.1016/j.compbiomed.2024.108004
MenzeBH, JakabA, BauerS, et al. The multimodal brain tumor image segmentation benchmark (BRATS)[J]. IEEE Trans Med Imaging, 2015, 34(10): 1993-2024.
[25]
BauerS, WiestR, NolteLP, et al. A survey of MRI-based medical image analysis for brain tumor studies[J]. Phys Med Biol, 2013, 58(13): R97-R129. doi:10.1088/0031-9155/58/13/r97
[26]
SalvadorA, BellverM, CamposV, et al. Recurrent neural networks for semantic instance segmentation[J]. arXiv preprint arXiv:2017.
[27]
TahaAA, HanburyA. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool[J]. BMC Med Imaging, 2015, 15: 29. doi:10.1186/s12880-015-0068-x
[28]
PetitjeanC, DacherJN. A review of segmentation methods in short axis cardiac MR images[J]. Med Image Anal, 2011, 15(2): 169-84. doi:10.1016/j.media.2010.12.004
[29]
ZhuangXH, ShenJ. Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI[J]. Med Image Anal, 2016, 31: 77-87. doi:10.1016/j.media.2016.02.006
[30]
IsenseeF, JaegerPF, KohlSAA, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nat Methods, 2021, 18(2): 203-11. doi:10.1038/s41592-020-01008-z
[31]
EstevaA, RobicquetA, RamsundarB, et al. A guide to deep learning in healthcare[J]. Nat Med, 2019, 25(1): 24-9. doi:10.1038/s41591-018-0316-z