OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography

2025-05-18

AI Summary

Early detection of prostate cancer demands high-sensitivity, low-cost imaging, yet conventional transrectal ultrasound exhibits poor sensitivity for anterior tumors, and ultrasound computed tomography (USCT) suffers from limited-angle reconstruction artifacts. To address this, we introduce OpenPros—the first large-scale, open-source benchmark dataset for limited-view prostate USCT. It comprises over 280,000 paired sound-speed distributions and full-waveform simulations, generated from anatomically accurate 3D models derived from clinical MRI/CT and ex vivo ultrasound, with expert annotations and physics-based simulation. We also release open-source finite-difference time-domain (FDTD) and Runge–Kutta wave solvers to support deep learning–based reconstruction methods, including U-Net and diffusion models. Experiments demonstrate that deep learning significantly improves reconstruction speed and accuracy, though spatial resolution remains a bottleneck. OpenPros is publicly available to accelerate USCT algorithm development and clinical translation.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

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 methods suffer from low sensitivity, especially in detecting anteriorly located tumors. Ultrasound computed tomography 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, the first 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 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. The dataset is publicly accessible at https://open-pros.github.io/.

Problem

• Improving early detection of prostate cancer using ultrasound imaging
• Overcoming limited-angle acquisition challenges in prostate USCT
• Enhancing resolution and accuracy of prostate ultrasound images via deep learning

Innovation

• Large-scale dataset for limited-view prostate USCT
• Anatomically accurate 3D digital prostate models
• Open-source advanced acoustic wave solvers