A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 13 Issue 4
Apr.  2026

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 19.2, Top 1 (SCI Q1)
    CiteScore: 28.2, Top 1% (Q1)
    Google Scholar h5-index: 95， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2026  >  13(4): 939-954
R. Cheng, X. Qiu, M. Li, Y. Zhang, F. Yu, and C. Li, “Robust brain tumor segmentation with incomplete MRI modalities using Hölder divergence and mutual information-enhanced knowledge transfer,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 4, pp. 939–954, Apr. 2026. doi: 10.1109/JAS.2025.125609
Citation: R. Cheng, X. Qiu, M. Li, Y. Zhang, F. Yu, and C. Li, “Robust brain tumor segmentation with incomplete MRI modalities using Hölder divergence and mutual information-enhanced knowledge transfer,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 4, pp. 939–954, Apr. 2026. doi: 10.1109/JAS.2025.125609
shu

Robust Brain Tumor Segmentation With Incomplete MRI Modalities Using Hölder Divergence and Mutual Information-Enhanced Knowledge Transfer

doi: 10.1109/JAS.2025.125609
Funds:  This work was supported by the National Key Research and Development Program of China (2025YFE0113400, 2022YFC3310300), Guangdong Basic and Applied Basic Research Foundation (2024A1515011774), the National Natural Science Foundation of China (12171036), Shenzhen Sci-Tech Fund (RCJC20231211090030059), and Beijing Natural Science Foundation (Z210001)
More Information
    Abstract
  • Multimodal MRI (magnetic resonance imaging) provides critical complementary information for accurate brain tumor segmentation. However, conventional methods struggle when certain modalities are missing due to issues like image quality, protocol inconsistencies, patient allergies, or financial constraints. To address this, we propose a robust single-modality parallel processing framework that achieves high segmentation accuracy even with incomplete modalities. Leveraging Hölder divergence and mutual information, our model maintains modality-specific features while dynamically adjusting network parameters based on available inputs. By using these divergence and information-based loss functions, the framework effectively quantifies discrepancies between predictions and ground-truth labels, resulting in consistently accurate segmentation. Extensive evaluations on the BraTS 2018 and BraTS 2020 datasets demonstrate superior performance over existing methods in handling missing modalities, with ablation studies validating each component’s contribution to the framework.

     

    • FullText(HTML)
  • loading
    • Runze Cheng and Xihang Qiu and Ming Li contributed equally to this work.
    References(59)
  • [1]
    Y. Liu, Y. Shi, F. Mu, J. Cheng, and X. Chen, “Glioma segmentation-oriented multi-modal MR image fusion with adversarial learning,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 8, pp. 1528–1531, Aug. 2022. doi: 10.1109/JAS.2022.105770
    [2]
    B. Liu, R. Song, Y. Xiang, J. Du, W. Ruan, and J. Hu, “Self-supervised entity alignment based on multi-modal contrastive learning,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 11, pp. 2031–2033, Nov. 2022. doi: 10.1109/JAS.2022.105962
    [3]
    S. Mei, Y. Ma, X. Mei, J. Huang, and F. Fan, “S2-Net: Self-supervision guided feature representation learning for cross-modality images,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 10, pp. 1883–1885, Oct. 2022. doi: 10.1109/JAS.2022.105884
    [4]
    Y.-P. Huang, K. Bhalla, H.-C. Chu, Y.-C. Lin, H.-C. Kuo, W.-J. Chu, and J.-H. Lee, “Wavelet K-means clustering and fuzzy-based method for segmenting MRI images depicting Parkinson’s disease,” Int. J. Fuzzy Syst., vol. 23, no. 6, pp. 1600–1612, Mar. 2021. doi: 10.1007/s40815-021-01053-6
    [5]
    D. Shah, A. Barve, B. Vala, and J. Gandhi, “A survey on brain tumor segmentation with missing MRI modalities,” in Decision Intelligence: Proceedings of the Meeting Conference on Information Technology, B. K. Murthy, B. V. R. Reddy, N. Hasteer, J.-P. Van Belle, Eds. Singapore, Singapore: Springer, 2023, pp. 299−308.
    [6]
    R. Azad, N. Khosravi, and D. Merhof, “SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities,” in Proc. Int. Conf. Medical Imaging with Deep Learning, Zurich, Switzerland, 2022, pp. 48−62.
    [7]
    S. Wang, Z. Yan, D. Zhang, H. Wei, Z. Li, and R. Li, “Prototype knowledge distillation for medical segmentation with missing modality,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023, pp. 1−5.
    [8]
    S. Karimijafarbigloo, R. Azad, A. Kazerouni, S. Ebadollahi, and D. Merhof, “MMCFormer: Missing modality compensation transformer for brain tumor segmentation,” in Proc. Medical Imaging with Deep Learning, Nashville, USA, 2023, pp. 1144−1162.
    [9]
    Y. Ding, X. Yu, and Y. Yang, “RFNet: Region-aware fusion network for incomplete multi-modal brain tumor segmentation,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Montreal, Canada, 2021, pp. 3955−3964.
    [10]
    H. Ting and M. Liu, “Multimodal transformer of incomplete MRI data for brain tumor segmentation,” IEEE J. Biomed. Health Inf., vol. 28, no. 1, pp. 89–99, Jan. 2024. doi: 10.1109/JBHI.2023.3286689
    [11]
    H. Wang, Y. Chen, C. Ma, J. Avery, L. Hull, and G. Carneiro, “Multi-Modal learning with missing modality via shared-specific feature modelling,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Vancouver, Canada, 2023, pp. 15878−15887.
    [12]
    H. Wang, S. Luo, G. Hu, and J. Zhang, “Gradient-guided modality decoupling for missing-modality robustness,” in Proc. 38th AAAI Conf. Artificial Intelligence, Vancouver, Canada, 2024, pp. 15483−15491.
    [13]
    Y. Qiu, Z. Zhao, H. Yao, D. Chen, and Z. Wang, “Modal-aware visual prompting for incomplete multi-modal brain tumor segmentation,” in Proc. 31st ACM Int. Conf. Multimedia, Ottawa, Canada, 2023, pp. 3228−3239.
    [14]
    D. Chen, Y. Qiu, and Z. Wang, “Query re-training for modality-gnostic incomplete multi-modal brain tumor segmentation,” in Proc. Int. Conf. Medical Image Computing and Computer Assisted Intervention, Vancouver, Canada, 2023, pp. 135−146.
    [15]
    W. Qin and X. Luo, “Asynchronous parallel fuzzy stochastic gradient descent for high-dimensional incomplete data representation,” IEEE Trans. Fuzzy Syst., vol. 32, no. 2, pp. 445–459, Feb. 2024. doi: 10.1109/TFUZZ.2023.3300370
    [16]
    X. Luo, W. Qin, A. Dong, K. Sedraoui, and M. Zhou, “Efficient and high-quality recommendations via momentum-incorporated parallel stochastic gradient descent-based learning,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 402–411, Feb. 2021. doi: 10.1109/JAS.2020.1003396
    [17]
    X. Luo, M. Chen, H. Wu, Z. Liu, H. Yuan, and M. Zhou, “Adjusting learning depth in nonnegative latent factorization of tensors for accurately modeling temporal patterns in dynamic QoS data,” IEEE Trans. Autom. Sci. Eng., vol. 18, no. 4, pp. 2142–2155, Oct. 2021. doi: 10.1109/TASE.2020.3040400
    [18]
    W. Qin, X. Luo, S. Li, and M. Zhou, “Parallel adaptive stochastic gradient descent algorithms for latent factor analysis of high-dimensional and incomplete industrial data,” IEEE Trans. Autom. Sci. Eng., vol. 21, no. 3, pp. 2716–2729, Jul. 2024. doi: 10.1109/TASE.2023.3267609
    [19]
    W.-G. Chang, T. You, S. Seo, S. Kwak, and B. Han, “Domain-specific batch normalization for unsupervised domain adaptation,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 7346−7354.
    [20]
    S. Ahn, S. X. Hu, A. Damianou, N. D. Lawrence, and Z. Dai, “Variational information distillation for knowledge transfer,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, Long Beach, USA, 2019, pp. 9155−9163.
    [21]
    F. Nielsen, K. Sun, and S. Marchand-Maillet, “On hölder projective divergences,” Entropy, vol. 19, no. 3, p. Art. no. 122, Mar. 2017. doi: 10.3390/e19030122
    [22]
    R. Cheng, Z. Sun, Y. Zhang, and C. Li, “Robust divergence learning for missing-modality segmentation,” in Proc. China Automation Congr., Qingdao, China, 2024, pp. 2077−2083.
    [23]
    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
    [24]
    M. Havaei, N. Guizard, N. Chapados, and Y. Bengio, “HeMIS: Hetero-modal image segmentation,” in Proc. 19th Int. Conf. Medical Image Computing and Computer-Assisted Intervention, Athens, Greece, 2016, pp. 469−477.
    [25]
    Y. Wang, Y. Zhang, Y. Liu, Z. Lin, J. Tian, C. Zhong, Z. Shi, J. Fan, and Z. He, “ACN: Adversarial co-training network for brain tumor segmentation with missing modalities,” in Proc. 24th Int. Conf. Medical Image Computing and Computer Assisted Intervention, Strasbourg, France, 2021, pp. 410−420.
    [26]
    Y. Zhang, N. He, J. Yang, Y. Li, D. Wei, Y. Huang, Y. Zhang, Z. He, and Y. Zheng, “mmFormer: Multimodal medical transformer for incomplete multimodal learning of brain tumor segmentation,” in Proc. 25th Int. Conf. Medical Image Computing and Computer Assisted Intervention, Singapore, Singapore, 2022, pp. 107−117.
    [27]
    A. Hatamizadeh, V. Nath, Y. Tang, D. Yang, H. R. Roth, and D. Xu, “Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images,” in Proc. 7th Int. Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 2021, pp. 272−284.
    [28]
    Z. Liu, J. Wei, R. Li, and J. Zhou, “SFusion: Self-attention based N-to-One multimodal fusion block,” in Proc. 26th Int. Conf. Medical Image Computing and Computer Assisted Intervention, Vancouver, Canada, 2023, pp. 159−169.
    [29]
    J. Shi, L. Yu, Q. Cheng, X. Yang, K. Cheng, and Z. Yan, “MFTrans: Modality-masked fusion transformer for incomplete multi-modality brain tumor segmentation,” IEEE J. Biomed. Health Inf., vol. 28, no. 1, pp. 379–390, Jan. 2024. doi: 10.1109/JBHI.2023.3326151
    [30]
    A. Konwer, X. Hu, J. Bae, X. Xu, C. Chen, and P. Prasanna, “Enhancing modality-agnostic representations via meta-learning for brain tumor segmentation,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 21358−21368.
    [31]
    Y. Qiu, D. Chen, H. Yao, Y. Xu, and Z. Wang, “Scratch each other’s back: Incomplete multi-modal brain tumor segmentation via category aware group self-support learning,” in Proc. IEEE/CVF Int. Conf. Computer Vision, Paris, France, 2023, pp. 21260−21269.
    [32]
    H. G. Hoang, B.-N. Vo, B.-T. Vo, and R. Mahler, “The Cauchy-Schwarz divergence for Poisson point processes,” IEEE Trans. Inf. Theory, vol. 61, no. 8, pp. 4475–4485, Aug. 2015. doi: 10.1109/TIT.2015.2441709
    [33]
    F. Nielsen, K. Sun, and S. Marchand-Maillet, “k-Means clustering with Hölder divergences,” in Proc. 3rd Int. Conf. Geometric Science of Information, Paris, France, 2017, pp. 856−863.
    [34]
    G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv: 1503.02531, 2015.
    [35]
    Z. Yin, J. Pu, Y. Zhou, and X. Xue, “Two-stage approach for targeted knowledge transfer in self-knowledge distillation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 11, pp. 2270–2283, Nov. 2024. doi: 10.1109/JAS.2024.124629
    [36]
    Z. Zheng, L. Teng, W. Zhang, N. Wu, and S. Teng, “Knowledge transfer learning via dual density sampling for resource-limited domain adaptation,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 12, pp. 2269–2291, Dec. 2023. doi: 10.1109/JAS.2023.123342
    [37]
    H. Liu, D. Wei, D. Lu, J. Sun, L. Wang, and Y. Zheng, “M.3AE: Multimodal representation learning for brain tumor segmentation with missing modalities,” in Proc. 37th AAAI Conf. Artificial Intelligence, Washington, USA, 2023, Art. no. 184.
    [38]
    D. Barber and F. Agakov, “The IM algorithm: A variational approach to information maximization,” Proc. 17th Int. Conf. Neural Information Processing Systems, Whistler, Canada, 2003, pp. 201−208.
    [39]
    F. Milletari, N. Navab, and S.-A. Ahmadi, “V-Net: Fully convolutional neural networks for volumetric medical image segmentation,” in Proc. 4th Int. Conf. 3D Vision, Stanford, USA, 2016, pp. 565−571.
    [40]
    I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, USA: MIT Press, 2016.
    [41]
    T. M. Cover, Elements of Information Theory. New York, USA: John Wiley & Sons, 1999.
    [42]
    G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, USA, 2017, pp. 2261−2269.
    [43]
    K. C. Tezcan, C. F. Baumgartner, R. Luechinger, K. P. Pruessmann, and E. Konukoglu, “MR image reconstruction using deep density priors,” IEEE Trans. Med. Imaging, vol. 38, no. 7, pp. 1633–1642, Jul. 2019. doi: 10.1109/TMI.2018.2887072
    [44]
    Y. Nesterov, Introductory Lectures on Convex Optimization: A Basic Course. New York, USA: Springer, 2013.
    [45]
    H. Robbins and S. Monro, “A stochastic approximation method,” Ann. Math. Statist., vol. 22, no. 3, pp. 400–407, Sep. 1951.
    [46]
    R. D. Hjelm, A. Fedorov, S. Lavoie-Marchildon, K. Grewal, P. Bachman, A. Trischler, and Y. Bengio, “Learning deep representations by mutual information estimation and maximization,” in Proc. 7th Int. Conf. Learning Representations, New Orleans, USA, 2019.
    [47]
    B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al, “The multimodal brain tumor image segmentation benchmark (BRATS),” IEEE Trans. Med. Imaging, vol. 34, no. 10, pp. 1993–2024, Oct. 2015. doi: 10.1109/TMI.2014.2377694
    [48]
    Q. Yang, X. Guo, Z. Chen, P. Y. Woo, and Y. Yuan, “D.2-Net: Dual disentanglement network for brain tumor segmentation with missing modalities,” IEEE Trans. Med. Imaging, vol. 41, no. 10, pp. 2953–2964, Oct. 2022. doi: 10.1109/TMI.2022.3175478
    [49]
    R. Dorent, S. Joutard, M. Modat, S. Ourselin, and T. Vercauteren, “Hetero-modal variational encoder-decoder for joint modality completion and segmentation,” in Proc. 22nd Int. Conf. Medical Image Computing and Computer Assisted Intervention, Shenzhen, China, 2019, pp. 74−82.
    [50]
    A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, et al., “PyTorch: An imperative style, high-performance deep learning library,” in Proc. 33rd Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2019, Art. no. 721.
    [51]
    J. Chen and A. L. Martel, “Head and neck tumor segmentation with 3D UNet and survival prediction with multiple instance neural network,” in Proc. 3rd Challenge on Head and Neck Tumor Segmentation and Outcome Prediction, Singapore, Singapore, 2022, pp. 221−229.
    [52]
    D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd Int. Conf. Learning Representations, San Diego, USA, 2015.
    [53]
    L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Phys. D: Nonlinear Phenom., vol. 60, no. 1−4, pp. 259–268, Nov. 1992. doi: 10.1016/0167-2789(92)90242-F
    [54]
    V. Kumar, K. Vasan, and S. Kumar, “Exact mean and variance of the squared Hellinger distance for random density matrices,” Phys. Rev. E, vol. 111, no. 5, p. Art. no. 054204, May 2025. doi: 10.1103/physreve.111.054204
    [55]
    S. Kullback and R. A. Leibler, “On information and sufficiency,” Ann. Math. Stat., vol. 22, no. 1, pp. 79–86, Mar. 1951.
    [56]
    F. Nielsen and K. Okamura, “On the f-divergences between densities of a multivariate location or scale family,” Stat. Comput., vol. 34, no. 1, p. Art. no. 60, Jan. 2024. doi: 10.1007/s11222-023-10373-6
    [57]
    F. Nielsen, “On a generalization of the Jensen-Shannon divergence and the Jensen-Shannon centroid,” Entropy, vol. 22, no. 2, p. Art. no. 221, Feb. 2020.
    [58]
    C. F. Gauss, Theoria Motus Corporum Coelestium in Sectionibus Conicis Solem Ambientium. Cambridge, UK: Cambridge University Press, 2012.
    [59]
    C. E. Shannon, “A mathematical theory of communication,” The Bell System Technical Journal, vol. 27, no. 3, pp. 379–423, 1948. doi: 10.1002/j.1538-7305.1948.tb01338.x
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(3)  / Tables(8)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (20) PDF downloads(0) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return