SEARCH-IHI/TIDE-II

--- license: cc-by-nc-4.0 language: - en tags: - synthetic-image-dataset - wireless-capsule-endoscopy - gastrointestinal-endoscopy - clinical-evaluation pretty_name: TIDE-II - Synthetic Wireless Capsule Endoscopy (WCE) Dataset --- # **Clinical Evaluation of Medical Image Synthesis: A Case Study in Wireless Capsule Endoscopy** This repository provides the **synthetic Wireless Capsule Endoscopy (WCE)** dataset used for the evaluation of **TIDE-II (This Intestine Does not Exist II)** synthetic image generation model, using the **CEMIS (Clinical Evaluation of Medical Image Synthesis)** protocol, published in Gatoula et al., 2025 (see reference below). It supports research on the clinical assessment of synthetic medical images in gastrointestinal endoscopy. [**Paper link**](https://www.nature.com/articles/s41598-025-14359-4) ## 🔍 Overview The synthetic images have been generated by training the **TIDE-II** model on publicly available WCE datasets: - *KID-2* - *Kvasir Capsule* The dataset provides images showcasing: - *Normal endoscopic tissue* - *Inflammatory Bowel Disease (IBD) conditions* ## 📂 Dataset Structure ``` /tideii_dataset/ │ ├── kid2/ │ ├── abnormal_img_0.png │ ├── abnormal_img_1.png │ ├── ... │ ├── normal_img_0.png │ ├── normal_img_1.png │ └── ... │ ├── kvasir-capsule/ │ ├── abnormal_img_0.png │ ├── abnormal_img_1.png │ ├── ... │ ├── normal_img_0.png │ ├── normal_img_1.png │ └── ... ``` ## 📄 Paper Abstract Synthetic Data Generation (SDG) based on Artificial Intelligence (AI) can transform the way clinical medicine is delivered by overcoming privacy barriers that currently render clinical data sharing difficult. This is the key to accelerating the development of digital tools contributing to enhanced patient safety. Such tools include robust data-driven clinical decision support systems, and example-based digital training tools that will enable healthcare professionals to improve their diagnostic performance for enhanced patient safety. This study focuses on the clinical evaluation of medical SDG, with a proof-of-concept investigation on diagnosing Inflammatory Bowel Disease (IBD) using Wireless Capsule Endoscopy (WCE) images. Its scientific contributions include a) a novel protocol for the systematic Clinical Evaluation of Medical Image Synthesis (CEMIS); b) a novel variational autoencoder-based model, named TIDE-II, which enhances its predecessor model, TIDE (This Intestine Does not Exist), for the generation of high-resolution synthetic WCE images; and c) a comprehensive evaluation of the synthetic images using the CEMIS protocol by 10 international WCE specialists, in terms of image quality, diversity, and realism, as well as their utility for clinical decision-making. The results show that TIDE-II generates clinically plausible, very realistic WCE images, of improved quality compared to relevant state-of-the-art generative models. Concludingly, CEMIS can serve as a reference for future research on medical image-generation techniques, while the adaptation/extension of the architecture of TIDE-II to other imaging domains can be promising. ## ⌨️ Code Implementation The official **TensorFlow** implementation of *"Clinical Evaluation of Medical Image Synthesis: A Case Study in Wireless Capsule Endoscopy"* is available at [TIDE-II GitHub](https://github.com/innoisys/TIDE-II) ## 📚 Citation If you find this synthetic image dataset useful for your research please cite our paper: ```bibtex @article{Gatoula2025, author = {Panagiota Gatoula and Dimitrios E. Diamantis and Anastasios Koulaouzidis and Cristina Carretero and Stefania Chetcuti-Zammit and Pablo Cortegoso Valdivia and Bego{\~n}a Gonz{\'a}lez-Su{\'a}rez and Alessandro Mussetto and John Plevris and Alexander Robertson and Bruno Rosa and Ervin Toth and Dimitris K. Iakovidis}, title = {Clinical evaluation of medical image synthesis: a case study in wireless capsule endoscopy}, journal = {Scientific Reports}, year = {2025}, volume = {15}, number = {1}, pages = {35068}, doi = {10.1038/s41598-025-14359-4}, url = {https://doi.org/10.1038/s41598-025-14359-4}, issn = {2045-2322}, month = {Oct}, day = {08} } ``` ## ⚖️ License This dataset is released under the **Creative Commons Attribution–NonCommercial 4.0 International (CC BY-NC 4.0)** [license](https://creativecommons.org/licenses/by-nc/4.0/) . ## 📧 Contact Prof. Dimitris Iakovidis Director of Biomedical Imaging Lab University of Thessaly [e-mail] ## 🧬 Disclaimer All images in this dataset are **synthetic** and generated by **TIDE-II (This Intestine Does not Exist II)** model.license: CC BY-NC 4.0（知识共享署名-非商业性使用4.0国际许可协议） language: - en - 英语 tags: - synthetic-image-dataset - 合成图像数据集 - wireless-capsule-endoscopy - 无线胶囊内镜（Wireless Capsule Endoscopy, WCE） - gastrointestinal-endoscopy - 胃肠道内镜检查 - clinical-evaluation - 临床评估 pretty_name: TIDE-II - 合成无线胶囊内镜（Wireless Capsule Endoscopy, WCE）数据集 # **医学图像合成的临床评估：以无线胶囊内镜为例** 本仓库提供了用于评估**TIDE-II（本肠非实有II，This Intestine Does not Exist II）**合成图像生成模型的**合成无线胶囊内镜（Wireless Capsule Endoscopy, WCE）**数据集，该数据集采用**CEMIS（医学图像合成临床评估，Clinical Evaluation of Medical Image Synthesis）**协议构建，相关成果发表于Gatoula等人2025年的研究（详见下文参考文献）。本数据集可为胃肠道内镜领域合成医学图像的临床评估研究提供支撑。 [**论文链接**](https://www.nature.com/articles/s41598-025-14359-4) ## 🔍 数据集概览 合成图像通过在公开可用的WCE数据集上训练**TIDE-II**模型生成： - *KID-2* - *Kvasir Capsule* 本数据集包含以下场景的图像： - 正常内镜下组织 - 炎症性肠病（Inflammatory Bowel Disease, IBD）病变 ## 📂 数据集结构 /tideii_dataset/ │ ├── kid2/ │ ├── abnormal_img_0.png │ ├── abnormal_img_1.png │ ├── ... │ ├── normal_img_0.png │ ├── normal_img_1.png │ └── ... │ ├── kvasir-capsule/ │ ├── abnormal_img_0.png │ ├── abnormal_img_1.png │ ├── ... │ ├── normal_img_0.png │ ├── normal_img_1.png │ └── ... ## 📄 论文摘要 基于人工智能（Artificial Intelligence, AI）的合成数据生成（Synthetic Data Generation, SDG）可突破当前阻碍临床数据共享的隐私壁垒，从而重塑临床医疗服务模式，这也是加速开发可提升患者安全的数字工具的核心关键。此类工具包括可靠的数据驱动型临床决策支持系统，以及基于示例的数字化培训工具，能够帮助医疗从业者提升诊断能力，进而强化患者安全。本研究聚焦于医学合成数据生成的临床评估，以无线胶囊内镜（Wireless Capsule Endoscopy, WCE）图像辅助诊断炎症性肠病（Inflammatory Bowel Disease, IBD）为概念验证研究方向。本研究的科学贡献包括：a) 一套面向医学图像合成的系统化临床评估（Clinical Evaluation of Medical Image Synthesis, CEMIS）全新协议；b) 一款基于变分自编码器的新型模型TIDE-II，该模型对其前身模型TIDE（本肠非实有，This Intestine Does not Exist）进行了优化，可生成高分辨率合成WCE图像；c) 联合10名国际WCE专家，采用CEMIS协议对合成图像开展全面评估，评估维度涵盖图像质量、多样性、真实性，以及其在临床决策中的应用价值。研究结果表明，TIDE-II生成的WCE图像符合临床场景且极具真实感，相较于当前主流生成模型，其图像质量得到显著提升。综上，CEMIS可作为未来医学图像生成技术研究的参考框架，而将TIDE-II的架构适配或拓展至其他成像领域亦具备广阔应用前景。 ## ⌨️ 代码实现 本研究论文《医学图像合成的临床评估：以无线胶囊内镜为例》的官方**TensorFlow**实现代码可于[TIDE-II GitHub仓库](https://github.com/innoisys/TIDE-II)获取。 ## 📚 引用规范 若本合成图像数据集对您的研究有所助益，请引用如下论文： bibtex @article{Gatoula2025, author = {Panagiota Gatoula and Dimitrios E. Diamantis and Anastasios Koulaouzidis and Cristina Carretero and Stefania Chetcuti-Zammit and Pablo Cortegoso Valdivia and Begoña González-Suárez and Alessandro Mussetto and John Plevris and Alexander Robertson and Bruno Rosa and Ervin Toth and Dimitris K. Iakovidis}, title = {Clinical evaluation of medical image synthesis: a case study in wireless capsule endoscopy}, journal = {Scientific Reports}, year = {2025}, volume = {15}, number = {1}, pages = {35068}, doi = {10.1038/s41598-025-14359-4}, url = {https://doi.org/10.1038/s41598-025-14359-4}, issn = {2045-2322}, month = {Oct}, day = {08} } ## ⚖️ 许可协议 本数据集采用**知识共享署名-非商业性使用4.0国际许可协议（CC BY-NC 4.0）**[发布](https://creativecommons.org/licenses/by-nc/4.0/)。 ## 📧 联系方式 Dimitris Iakovidis 教授 生物医学影像实验室主任 色萨利大学 [e-mail] ## 🧬 免责声明 本数据集内所有图像均为**合成图像**，由**TIDE-II（本肠非实有II，This Intestine Does not Exist II）**模型生成。