MedCAGD-Dataset-Collection - Medical Image Segmentation Datasets
This repo contains multiple publicly available medical image segmentation (Semantic Segmentation) datasets used for training and evaluation of the segmentation models. Each subfolder corresponds to a specific dataset and follows its original structure or a standardized format used in this project. These datasets are used for benchmarking segmentation performance across multiple medical imaging modalities including CT, MRI, dermoscopy, endoscopy, ultrasound, fundus imaging, and microscopy.
If you use this, please cite the following paper (MCADS-Decoder) *:
bibtex
@inproceedings{wazir2025rethinking,
title={Rethinking decoder design: Improving biomarker segmentation using depth-to-space restoration and residual linear attention},
author={Wazir, Saad and Kim, Daeyoung},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={30861--30871},
year={2025},
doi = {10.48550/arXiv.2506.18335},
url = {https://doi.org/10.48550/arXiv.2506.18335}
}
MCADS-Decoder - Rethinking decoder design: Improving biomarker segmentation using depth-to-space restoration and residual linear attentionImproving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention - CVPR 2025
This dataset collection provides early access to the datasets used for benchmarking segmentation models across multiple medical imaging datasets. The segmentation benchmarks associated with this dataset collection are part of ongoing research related to the MCADS decoder and the upcoming MedCAGD framework. The full benchmark results and evaluation protocols will appear in the MedCAGD paper, which is currently under review, and additional results will be released after the review process.