What question did this study set out to answer?

The study aims to improve medical image segmentation performance by addressing limitations in existing CNN and Transformer models.

March 17, 2026Scientific ReportsOpen Access

A parallel UNet integrating KAN and mamba for medical image segmentation

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates improved image segmentation in medical contexts using an advanced deep learning framework, suggesting enhanced efficiency.

The study aims to improve medical image segmentation performance by addressing limitations in existing CNN and Transformer models.
Proposed KMP-UNet framework combining Mamba-based and KAN branches.
Implemented task-oriented fusion block and skip refinement module.
Evaluated on four public datasets using standard segmentation metrics.
Achieved 0.9038 Dice Similarity Coefficient (DSC) on ISIC2018, indicating excellent performance.
Demonstrated compact model size with approximately 1.0M parameters.
Conducted extensive comparisons to analyze the contributions of model components.

Liu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

March 17, 2026Scientific ReportsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates improved image segmentation in medical contexts using an advanced deep learning framework, suggesting enhanced efficiency.

The study aims to improve medical image segmentation performance by addressing limitations in existing CNN and Transformer models.
Proposed KMP-UNet framework combining Mamba-based and KAN branches.
Implemented task-oriented fusion block and skip refinement module.
Evaluated on four public datasets using standard segmentation metrics.
Achieved 0.9038 Dice Similarity Coefficient (DSC) on ISIC2018, indicating excellent performance.
Demonstrated compact model size with approximately 1.0M parameters.
Conducted extensive comparisons to analyze the contributions of model components.

Liu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark