PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for 3D Brain Tumor Segmentation
Brain Sciences · 29.05.2026 · 16 (6) · 588
DOI: 10.3390/brainsci16060588 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 29.05.2026. Verfasst von Haokun Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Accurate automatic segmentation of multimodal magnetic resonance imaging (MRI) is essential for neurosurgical planning and image-guided procedures. However, existing three-dimensional segmentation models often struggle with low lesion-to-tissue contrast, ambiguous tumor boundaries, small enhancing tumor regions, and performance degradation caused by missing imaging modalities. This study aimed to develop a robust segmentation framework that improves cross-modal representation learning, boundary recovery, and segmentation performance under incomplete-input conditions.
Methods
We propose PF-CMNet, a Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for three-dimensional brain tumor segmentation. The network introduces a Cross-Modal Selective Frequency Attention module in the early encoder stage to model modality-specific frequency responses and spatially adaptive cross-modal correlations. A Progressive Cross-Scale Detail Fusion decoder is further employed to aggregate multilevel semantic features and refine high-resolution boundary details. To enhance robustness under missing-modality conditions, a teacher–student distillation strategy transfers full-modality predictions and shallow feature knowledge to a student network trained with random modality dropout.
Results
On the MSD Task01_BrainTumour dataset, PF-CMNet achieved an average Dice score of 84.3%, with Dice scores of 79.6%, 82.8%, and 90.4% for enhancing tumor, tumor core, and whole tumor, respectively. On the BraTS2021 dataset, the model achieved an average Dice score of 88.2% and the lowest average 95th percentile Hausdorff distance among the compared methods. In predefined complete-modality absence stress tests, where unavailable MRI sequences were zero-masked to model the absence of input modalities rather than partial image degradation, the distilled model maintained average Dice scores of 78.64%, 82.58%, 58.39%, 82.03%, and 79.29% when FLAIR, T1, T1ce, T2, and T1 + T2 were unavailable, respectively.
Conclusions
PF-CMNet provides a unified framework for multimodal brain tumor segmentation, improving full-modality segmentation accuracy, boundary consistency, and robustness to incomplete MRI inputs while maintaining a favorable accuracy–efficiency trade-off.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
Zitieren
APA
Wang, H., Wang, S., Li, Y., Miao, X., & Cao, C. (2026). PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for 3D Brain Tumor Segmentation. Brain Sciences, 16(6), 588. https://doi.org/10.3390/brainsci16060588
Vancouver
Wang H, Wang S, Li Y, Miao X, Cao C. PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for 3D Brain Tumor Segmentation. Brain Sciences. 2026;16(6):588. doi:10.3390/brainsci16060588
BibTeX
@article{Wang2026,
author = {Wang, Haokun and Wang, Shuyi and Li, Yuqi and Miao, Xinrong and Cao, Chenyi},
title = {PF-CMNet: Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for 3D Brain Tumor Segmentation},
journal = {Brain Sciences},
year = {2026},
volume = {16},
number = {6},
pages = {588},
doi = {10.3390/brainsci16060588}
}
EUVIMED