|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- stable-diffusion-v1-5/stable-diffusion-v1-5 |
|
|
pipeline_tag: image-to-image |
|
|
--- |
|
|
<div align="center"> |
|
|
<img src="document/Twitter.png" alt="SMILE" width=100%> |
|
|
</div> |
|
|
|
|
|
<h1 align="center" style="font-size: 60px; margin-bottom: 4px">😊 SMILE: Anatomy-Aware Contrast Enhancement</h1> |
|
|
|
|
|
<div align="center"> |
|
|
|
|
|
|
|
|
[](https://github.com/MrGiovanni/SMILE?tab=readme-ov-file#ctverse-dataset) |
|
|
[](https://github.com/MrGiovanni/SMILE?tab=readme-ov-file#smile-benchmark) |
|
|
[](https://huggingface.co/MitakaKuma/SMILE) |
|
|
[](https://github.com/MrGiovanni/SMILE/stargazers) |
|
|
<a href="https://twitter.com/bodymaps317"> |
|
|
<img src="https://img.shields.io/twitter/follow/BodyMaps?style=social" alt="Follow on Twitter" /> |
|
|
</a><br/> |
|
|
|
|
|
</div> |
|
|
|
|
|
|
|
|
We present **SMILE** (Super Modality Image Learning and Enhancement), an anatomy-aware diffusion model for clinically reliable CT contrast enhancement. |
|
|
|
|
|
SMILE achieves significant improvements: **+14.2% SSIM**, **+20.6% PSNR**, **+50% FID**, and enables cancer detection from non-contrast CT scans with **+10% F1 score** improvement. |
|
|
|
|
|
<div align="center"> |
|
|
<img src="document/pdac_example.png" alt="SMILE" width=100%> |
|
|
</div> |
|
|
|
|
|
<a id="smile-paper"></a> |
|
|
# Paper |
|
|
<b>See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement</b> <br/> |
|
|
[Junqi Liu](https://scholar.google.com/citations?hl=en&authuser=1&user=4Xpspl0AAAAJ), [Zejun Wu](), [Pedro R. A. S. Bassi](), [Xinze Zhou](), [Wenxuan Li](), [Ibrahim E. Hamamci](), [Sezgin Er](), [Tianyu Lin](), [Yi Luo](), [Szymon Płotka](https://scholar.google.com/citations?hl=en&authuser=1&user=g9sWRN0AAAAJ), [Bjoern Menze](https://scholar.google.com/citations?hl=en&authuser=1&user=Kv2QrQgAAAAJ), [Daguang Xu](https://scholar.google.com/citations?hl=en&authuser=1&user=r_VHYHAAAAAJ), [Kai Ding](https://scholar.google.com/citations?hl=en&authuser=1&user=OvpsAYgAAAAJ), [Kang Wang](https://radiology.ucsf.edu/people/kang-wang), [Yang Yang](https://scholar.google.com/citations?hl=en&authuser=1&user=6XsJUBIAAAAJ), [Yucheng Tang](https://scholar.google.com/citations?hl=en&authuser=1&user=0xheliUAAAAJ), [Alan Yuille](https://www.cs.jhu.edu/~ayuille/), [Zongwei Zhou](https://www.zongweiz.com/)<sup>★</sup> <br/> |
|
|
Johns Hopkins University, University of Copenhagen, University of Virginia, University of Bologna, and others |
|
|
|
|
|
<a href='https://www.zongweiz.com/dataset'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://www.cs.jhu.edu/~zongwei/preprint/liu2025see.pdf'><img src='https://img.shields.io/badge/Paper-PDF-purple'></a> |
|
|
|
|
|
# Citation |
|
|
|
|
|
``` |
|
|
@article{liu2025see, |
|
|
title={See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement}, |
|
|
author={Liu, Junqi and Wu, Zejun and Bassi, Pedro RAS and Zhou, Xinze and Li, Wenxuan and Hamamci, Ibrahim E and Er, Sezgin and Lin, Tianyu and Luo, Yi and Płotka, Szymon and others}, |
|
|
journal={arXiv preprint arXiv:https://www.arxiv.org/abs/2512.07251}, |
|
|
year={2025}, |
|
|
url={https://github.com/MrGiovanni/SMILE} |
|
|
} |
|
|
``` |
|
|
|
|
|
# Acknowledgement |
|
|
|
|
|
This work was supported by the Lustgarten Foundation for Pancreatic Cancer Research, the Patrick J. McGovern Foundation Award, and the National Institutes of Health (NIH) under Award Number R01EB037669. We would like to thank the Johns Hopkins Research IT team in [IT@JH](https://researchit.jhu.edu/) for their support and infrastructure resources where some of these analyses were conducted; especially [DISCOVERY HPC](https://researchit.jhu.edu/research-hpc/). Paper content is covered by patents pending. |
