Cahan Noa, Klang Eyal, Aviram Galit, Barash Yiftach, Konen Eli, Giryes Raja, Greenspan Hayit
Faculty of Engineering, Tel Aviv University, Tel-Aviv, Israel.
Division of Data-Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
NPJ Digit Med. 2025 Jul 14;8(1):439. doi: 10.1038/s41746-025-01857-y.
Chest X-rays or chest radiography (CXR), commonly used for medical diagnostics, typically enables limited imaging compared to computed tomography (CT) scans, which offer more detailed and accurate three-dimensional data, particularly contrast-enhanced scans like CT Pulmonary Angiography (CTPA). However, CT scans entail higher costs, greater radiation exposure, and are less accessible than CXRs. In this work, we explore cross-modal translation from a 2D low contrast-resolution X-ray input to a 3D high contrast and spatial-resolution CTPA scan. Driven by recent advances in generative AI, we introduce a novel diffusion-based approach to this task. We employ the synthesized 3D images in a classification framework and show improved AUC in a Pulmonary Embolism (PE) categorization task, using the initial CXR input. Furthermore, we evaluate the model's performance using quantitative metrics, ensuring diagnostic relevance of the generated images. The proposed method is generalizable and capable of performing additional cross-modality translations in medical imaging. It may pave the way for more accessible and cost-effective advanced diagnostic tools. The code for this project is available: https://github.com/NoaCahan/X-ray2CTPA .
胸部X光或胸部放射成像（CXR），常用于医学诊断，与计算机断层扫描（CT）相比，其成像能力通常有限。CT扫描能提供更详细、准确的三维数据，尤其是像CT肺血管造影（CTPA）这样的增强扫描。然而，CT扫描成本更高，辐射暴露更大，且不如CXR容易获得。在这项工作中，我们探索从二维低对比度分辨率的X光输入到三维高对比度和空间分辨率的CTPA扫描的跨模态转换。受生成式人工智能最新进展的推动，我们为这项任务引入了一种基于扩散的新方法。我们在分类框架中使用合成的三维图像，并在使用初始CXR输入的肺栓塞（PE）分类任务中展示了改进的曲线下面积（AUC）。此外，我们使用定量指标评估模型的性能，确保生成图像的诊断相关性。所提出的方法具有通用性，能够在医学成像中执行额外的跨模态转换。它可能为更易获得且具成本效益的先进诊断工具铺平道路。该项目的代码可在以下网址获取：https://github.com/NoaCahan/X-ray2CTPA 。
