Improve model card: Add metadata, paper link, and citations

This PR improves the model card for the MedFormer segmentation model.

Specifically, it:
* Adds `pipeline_tag: image-segmentation` to the metadata, enhancing discoverability on the Hugging Face Hub.
* Adds `library_name: monai` to the metadata, as evidence from the associated GitHub repository's code paths (e.g., `dataset_abdomenatlas_UFO.py` implying `monai.transforms`) indicates compatibility.
* Updates the main title of the model card to "Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks" and links it prominently to its associated paper on the Hugging Face Hub ([https://huggingface.co/papers/2510.14803](https://huggingface.co/papers/2510.14803)).
* Updates the "Citations" section to include the BibTeX entry for the "Scaling Artificial Intelligence..." paper, ensuring all relevant research is cited.

Please review and merge if these changes are appropriate.

README.md

@@ -1,5 +1,13 @@
-This is a segmentation model (MedFormer architecture) trained for organ and tumor (kidney, liver and pancreas tumors) segmentation in the Beta version of AbdomenAtlas 3.0. 
-Performance improvements are expected for models trained on the released version of AbdomenAtlas 3.0. For the ofifical release of AbdomenAtlas 3.0 (ICCV 2025), please check our GitHub: https://github.com/MrGiovanni/RadGPT.
+---
+pipeline_tag: image-segmentation
+library_name: monai
+---
+
+# Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
+
+This repository contains a segmentation model (MedFormer architecture) which served as a baseline for the paper [Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks](https://huggingface.co/papers/2510.14803).
+
+This model was trained for organ and tumor (kidney, liver and pancreas tumors) segmentation in the Beta version of AbdomenAtlas 3.0. Performance improvements are expected for models trained on the released version of AbdomenAtlas 3.0. For the official release of AbdomenAtlas 3.0 (ICCV 2025), please check our GitHub: https://github.com/MrGiovanni/RadGPT.
 
 This model was only trained with per-voxel segmentation masks. In the MICCAI 2025 paper "Learning Segmentation from Radiology Report", it served as the "segmentation" baseline. 
 
@@ -60,6 +68,11 @@ Training and inference code: https://github.com/MrGiovanni/R-Super
 ---
 # Papers
 
+<b>Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks</b> <br/>
+[Pedro R. A. S. Bassi](https://scholar.google.com/citations?user=NftgL6gAAAAJ&hl=en), [Xinze Zhou](https://scholar.google.com/citations?user=GgL1eWAAAAAJ&hl=en), [Wenxuan Li](https://scholar.google.com/citations?hl=en&user=tpNZM2YAAAAJ), [Szymon Płotka](https://scholar.google.com/citations?user=iT9f9eQAAAAJ&hl=en), [Jieneng Chen](https://scholar.google.com/citations?user=yLYj88sAAAAJ&hl=zh-CN), [Qi Chen](https://scholar.google.com/citations?user=Y7JgY58AAAAJ&hl=en), Zheren Zhu, [Jakub Prządo](https://scholar.google.com/citations?user=_YpS48kAAAAJ&hl=en), Ibrahim E. Hamacı, Sezgin Er, Yuhan Wang, [Ashwin Kumar](https://scholar.google.com/citations?user=l4_3R_cAAAAJ&hl=en), [Bjoern Menze](https://scholar.google.com/citations?user=c_b1RysAAAAJ&hl=en), [Jarosław B. Ćwikła](https://scholar.google.com/citations?user=r2f4LLEAAAAJ&hl=en), [Yuyin Zhou](https://scholar.google.com/citations?user=Q_o_v08AAAAJ&hl=en), [Akshay S. Chaudhari](https://scholar.google.com/citations?user=51jBf1wAAAAJ&hl=en), [Curtis P. Langlotz](https://scholar.google.com/citations?user=53eQv5IAAAAJ&hl=en), [Sergio Decherchi](https://scholar.google.com/citations?user=T09qQ1IAAAAJ&hl=it), [Andrea Cavalli](https://scholar.google.com/citations?user=4xTOvaMAAAAJ&hl=en), [Kang Wang](https://radiology.ucsf.edu/people/kang-wang), [Yang Yang](https://scholar.google.com/citations?hl=en&user=6XsJUBIAAAAJ), [Alan Yuille](https://www.cs.jhu.edu/~ayuille/), [Zongwei Zhou](https://www.zongweiz.com/)* <br/>
+*Johns Hopkins University* <br/>
+<a href='https://huggingface.co/papers/2510.14803'><img src='https://img.shields.io/badge/Paper-PDF-purple'></a>
+
 <b>Learning Segmentation from Radiology Reports</b> <br/>
 [Pedro R. A. S. Bassi](https://scholar.google.com/citations?user=NftgL6gAAAAJ&hl=en), [Wenxuan Li](https://scholar.google.com/citations?hl=en&user=tpNZM2YAAAAJ), [Jieneng Chen](https://scholar.google.com/citations?user=yLYj88sAAAAJ&hl=zh-CN), Zheren Zhu, Tianyu Lin, [Sergio Decherchi](https://scholar.google.com/citations?user=T09qQ1IAAAAJ&hl=it), [Andrea Cavalli](https://scholar.google.com/citations?user=4xTOvaMAAAAJ&hl=en), [Kang Wang](https://radiology.ucsf.edu/people/kang-wang), [Yang Yang](https://scholar.google.com/citations?hl=en&user=6XsJUBIAAAAJ), [Alan Yuille](https://www.cs.jhu.edu/~ayuille/), [Zongwei Zhou](https://www.zongweiz.com/)* <br/>
 *Johns Hopkins University* <br/>
@@ -92,6 +105,15 @@ If you use this data, please cite the 3 paper below:
   year={2025}
 }
 
+@misc{bassi2025scaling,
+      title={Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks}, 
+      author={Pedro R. A. S. Bassi and Xinze Zhou and Wenxuan Li and Szymon Płotka and Jieneng Chen and Qi Chen and Zheren Zhu and Jakub Prządo and Ibrahim E. Hamacı and Sezgin Er and Yuhan Wang and Ashwin Kumar and Bjoern Menze and Jarosław B. Ćwikła and Yuyin Zhou and Akshay S. Chaudhari and Curtis P. Langlotz and Sergio Decherchi and Andrea Cavalli and Kang Wang and Yang Yang and Alan L. Yuille and Zongwei Zhou},
+      year={2025},
+      eprint={2510.14803},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2510.14803}, 
+}
 ```
 
 ## Acknowledgement