EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CMYD-SurfaceNet: Scale-Aware Cascaded Multimodal MRI Segmentation via Representation-Level Structural Decoupling and Boundary-Constrained Learning

Chaymae El Mechal, Mostefa Mesbah, Loubna Mazgouti, Fatima Zahra Ammor, Najiba El Amrani El Idrissi

Digital · 16.06.2026 · 6 (2) · 49

DOI: 10.3390/digital6020049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digital, online erschienen am 16.06.2026. Verfasst von Chaymae El Mechal und 4 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable delineation of brain tumor boundaries in multimodal magnetic resonance imaging (MRI) remains challenging despite substantial advances in deep learning–based segmentation. Although modern encoder–decoder architectures achieve strong volumetric overlap, precise geometric alignment of tumor contours remains inconsistent, particularly for small lesions and heterogeneous clinical cases. In neuro-oncology, even minor boundary deviations may influence surgical planning, radiotherapy targeting, and longitudinal treatment assessment. These limitations suggest that segmentation performance is not determined solely by network depth or loss design, but also by how multimodal information is structured prior to learning. We introduce CMYD-SurfaceNet, a scale-aware cascaded framework that restructures multimodal MRI inputs at the representation level to enhance boundary-sensitive segmentation. Rather than treating modalities as independently concatenated channels, selected sequences are first organized into a task-guided pseudo-RGB projection. This intermediate representation is subsequently transformed into the CMYK color space to disentangle shared luminance structure from modality-specific contrast dominance. To further encode geometric priors, a gradient-derived boundary density channel is incorporated to explicitly emphasize spatial discontinuities corresponding to tumor margins. The resulting CMYD representation is integrated within a two-stage nnU-Net cascade, where global tumor localization is followed by high-resolution region-of-interest refinement with auxiliary contour supervision. This scale-aware design improves sensitivity to small tumor components while stabilizing contour delineation. Extensive evaluation on the BraTS benchmark demonstrates consistent improvements in boundary-sensitive metrics. Compared with baseline nnU-Net, the proposed framework reduces HD95 from 3.6 mm to 2.4 mm and increases Surface Dice at 1 mm tolerance from 0.82 to 0.89, while maintaining competitive Dice performance. These findings suggest that representation-level structural decoupling, when combined with scale-aware refinement, may provide clinically relevant boundary-aware multimodal MRI segmentation support without increasing architectural complexity.

Zitieren

APA

Mechal, C. E., Mesbah, M., Mazgouti, L., Ammor, F. Z., & Idrissi, N. E. A. E. (2026). CMYD-SurfaceNet: Scale-Aware Cascaded Multimodal MRI Segmentation via Representation-Level Structural Decoupling and Boundary-Constrained Learning. Digital, 6(2), 49. https://doi.org/10.3390/digital6020049

Vancouver

Mechal CE, Mesbah M, Mazgouti L, Ammor FZ, Idrissi NEAE. CMYD-SurfaceNet: Scale-Aware Cascaded Multimodal MRI Segmentation via Representation-Level Structural Decoupling and Boundary-Constrained Learning. Digital. 2026;6(2):49. doi:10.3390/digital6020049

BibTeX
@article{Mechal2026,
  author = {Mechal, Chaymae El and Mesbah, Mostefa and Mazgouti, Loubna and Ammor, Fatima Zahra and Idrissi, Najiba El Amrani El},
  title = {CMYD-SurfaceNet: Scale-Aware Cascaded Multimodal MRI Segmentation via Representation-Level Structural Decoupling and Boundary-Constrained Learning},
  journal = {Digital},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {49},
  doi = {10.3390/digital6020049}
}
Kostenlos starten →