MMCAF-Net, a CNN-KAN multimodal fusion network with 3D multi-scale attention and cross-attention fusion, reports improved lung cancer subtype classification on Lung-PET-CT-Dx, but the gains are not statistically supported by the small single-split evaluation.
In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small Lesions-aware Bidirectional Multimodal Multiscale Fusion Network for Lung Disease Classification
MMCAF-Net, a CNN-KAN multimodal fusion network with 3D multi-scale attention and cross-attention fusion, reports improved lung cancer subtype classification on Lung-PET-CT-Dx, but the gains are not statistically supported by the small single-split evaluation.