.png){kind=icon}
Return
Spectral attribute reasoning for interpretable multi-modal pathological segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compmedimag.2026.102707.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Enhances segmentation accuracy with pathology-informed spectral reasoning. • Improves interpretability by linking predictions to spectral similarity. • Captures discriminative features via adaptive frequency-domain decomposition. • Reduces computational cost through efficient multi-modal feature integration. • Outperforms state-of-the-art methods on three public pathological datasets.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
Cited Papers
ShareSaveAligning knowledge concepts to whole slide images for precise histopathology image analysis.png)
NPJ DIGITAL MEDICINE
OAAI
NPJ DIGITAL MEDICINEIF15.1
OAAIShareSaveShareSaveShareSaveCSWin-UNet: Transformer UNet with cross-shaped windows for medical image segmentationINFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAIShareSaveTransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformersMEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAIShareSave
View more