ashynf/OpenPros

--- license: cc-by-nc-sa-4.0 size_categories: - n>1T --- **OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography** Prostate cancer is one of the most common and lethal cancers among men, making its early detection critically important. Although ultrasound imaging offers greater accessibility and cost-effectiveness compared to MRI, traditional transrectal ultrasound (TRUS) methods suffer from low sensitivity, especially in detecting anteriorly located tumors. Ultrasound computed tomography (USCT) provides quantitative tissue characterization, but its clinical implementation faces significant challenges, particularly under anatomically constrained limited-angle acquisition conditions specific to prostate imaging. To address these unmet needs, we introduce OPENPROS, a large-scale benchmark dataset explicitly developed for limited-view prostate USCT. Our dataset includes over 280,000 paired samples of realistic 2D speed-of-sound (SOS) phantoms and corresponding ultrasound full-waveform data, generated from anatomically accurate 3D digital prostate models derived from real clinical MRI/CT scans and ex vivo ultrasound measurements, annotated by medical experts. Simulations are conducted under clinically realistic configurations using advanced finite-difference time-domain (FDTD) and Runge-Kutta acoustic wave solvers, both provided as open-source components. Through comprehensive baseline experiments, we demonstrate that state-of-the-art deep learning methods surpass traditional physics-based approaches in both inference efficiency and reconstruction accuracy. Nevertheless, current deep learning models still fall short of delivering clinically acceptable high-resolution images with sufficient accuracy. By publicly releasing OPENPROS, we aim to encourage the development of advanced machine learning algorithms capable of bridging this performance gap and producing clinically usable, high-resolution, and highly accurate prostate ultrasound images. **Resources** [Website](https://open-pros.github.io/OpenPros/) - Explore more resources on the official website of OpenPros. **Labels of tissue/organ** 0 - muscle; 1 - fat; 2 - bone; 3 - prostate; 4 - anal canal; 5 - rectum; 6 - urinary bladder; 7 - neurovascular bundles; 8 - penile bulb; 9 - seminal vesicles; -1 - unknown **License** This dataset is licensed under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/) (CC BY-NC-SA 4.0). **Citation** If you find the data useful, please cite: ```bibtex @misc{wang2025openproslargescaledatasetlimited, title={OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography}, author={Hanchen Wang and Yixuan Wu and Yinan Feng and Peng Jin and Shihang Feng and Yiming Mao and James Wiskin and Baris Turkbey and Peter A. Pinto and Bradford J. Wood and Songting Luo and Yinpeng Chen and Emad Boctor and Youzuo Lin}, year={2025}, eprint={2505.12261}, archivePrefix={arXiv}, primaryClass={physics.med-ph}, url={https://arxiv.org/abs/2505.12261}, } ```许可证：CC BY-NC-SA 4.0 规模类别：数据量大于1TB **OpenPros：面向有限视角前列腺超声计算机断层扫描的大规模基准数据集** 前列腺癌是男性最常见且致死率最高的癌症之一，因此其早期检测至关重要。尽管超声成像相较于磁共振成像（MRI）具备更高的可及性与成本效益，但传统经直肠超声（TRUS）方法灵敏度较低，尤其在检测位于前部的肿瘤时问题更为突出。超声计算机断层扫描（USCT）可实现定量的组织特征表征，但其临床应用仍面临诸多重大挑战，尤其是在前列腺成像特有的解剖约束性有限角度采集场景下。为解决这些未被满足的临床需求，我们推出了OPENPROS——一款专为有限视角前列腺USCT开发的大规模基准数据集。 本数据集包含超过28万个成对样本，均由基于真实临床MRI/CT扫描及离体超声测量所得的解剖学精准3D数字化前列腺模型生成，涵盖逼真的二维声速（SOS）体模与对应的超声全波形数据，并经医学专家标注。我们采用先进的时域有限差分（FDTD）与龙格-库塔声波求解器，在符合临床实际的配置下完成仿真，上述两类求解器均已作为开源组件发布。 通过全面的基准实验，我们证明了当前主流深度学习方法在推理效率与重建精度上均优于传统的基于物理的方法。然而，现有的深度学习模型仍无法生成临床可接受的高分辨率图像，且精度不足。我们公开发布OPENPROS数据集，旨在推动先进机器学习算法的研发，以缩小这一性能差距，最终生成具备临床实用性的高分辨率、高精度前列腺超声图像。 **资源** [官方网站](https://open-pros.github.io/OpenPros/) —— 访问OpenPros官方网站获取更多相关资源。 **组织/器官标签** 0 - 肌肉；1 - 脂肪；2 - 骨骼；3 - 前列腺；4 - 肛管；5 - 直肠；6 - 膀胱；7 - 神经血管束；8 - 阴茎球；9 - 精囊；-1 - 未知 **授权协议** 本数据集采用[知识共享署名-非商业性使用-相同方式共享4.0国际许可协议](https://creativecommons.org/licenses/by-nc-sa/4.0/)（CC BY-NC-SA 4.0）进行授权。 **引用方式** 若您认为本数据集对您的研究有所帮助，请引用如下文献： bibtex @misc{wang2025openproslargescaledatasetlimited, title={OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography}, author={Hanchen Wang and Yixuan Wu and Yinan Feng and Peng Jin and Shihang Feng and Yiming Mao and James Wiskin and Baris Turkbey and Peter A. Pinto and Bradford J. Wood and Songting Luo and Yinpeng Chen and Emad Boctor and Youzuo Lin}, year={2025}, eprint={2505.12261}, archivePrefix={arXiv}, primaryClass={physics.med-ph}, url={https://arxiv.org/abs/2505.12261}, }