人工智能通过胸部X光检测脂肪肝疾病-动脉网

AI Detects Fatty Liver Disease from Chest X-Rays

HospiMedica 等信源发布 2025-07-01 08:05



可切换为仅中文







Fatty liver disease, which results from excess fat accumulation in the liver, is believed to impact approximately one in four individuals globally. If not addressed in time, it can progress to severe conditions such as cirrhosis and liver cancer, underscoring the importance of early detection and treatment.

脂肪肝病是由肝脏中脂肪过度积累引起的，据信全球大约每四个人中就有一人受到影响。如果不及时处理，它可能发展为肝硬化和肝癌等严重状况，突显了早期检测和治疗的重要性。

The current standard diagnostic tools for fatty liver disease include ultrasounds, CT scans, and MRIs, all of which require expensive, specialized equipment and dedicated facilities. .

目前脂肪肝病的标准诊断工具包括超声波、CT扫描和核磁共振成像，所有这些都需要昂贵的专业设备和专用设施。

By contrast, chest X-rays are more commonly used, cost-effective, and involve minimal radiation. Although primarily employed to assess the lungs and heart, chest X-rays also partially image the liver, making it possible to identify signs of fatty liver disease. Despite this potential, the link between chest X-rays and the condition has rarely been studied in depth.

相比之下，胸部X光更常用、成本效益高且涉及的辐射最少。虽然主要用于评估肺部和心脏，但胸部X光也能部分成像肝脏，从而可以识别脂肪肝疾病的迹象。尽管有这种潜力，但胸部X光与该疾病之间的联系却很少被深入研究。

Now, researchers have created an AI model capable of identifying fatty liver disease using chest X-ray images..

现在，研究人员已经创建了一种人工智能模型，能够使用胸部X光片识别脂肪肝疾病。

In a retrospective study, a research team from Osaka Metropolitan University (Osaka, Japan) used 6,599 chest X-ray images from 4,414 patients to develop their AI model based on controlled attenuation parameter (CAP) scores. Their results, published in

在一项回顾性研究中，大阪都市大学（日本大阪）的一个研究团队使用了来自4,414名患者的6,599张胸部X光片，基于受控衰减参数（CAP）评分开发了他们的AI模型。他们的研究结果发表在

Radiology Cardiothoracic Imaging

放射学心血管影像

, demonstrated that the AI model achieved high accuracy, with the area under the receiver operating characteristic curve (AUC) ranging from 0.82 to 0.83.

，表明人工智能模型达到了较高的准确率，接收者操作特征曲线下的面积（AUC）在 0.82 到 0.83 之间。

“The development of diagnostic methods using easily obtainable and inexpensive chest X-rays has the potential to improve fatty liver detection. We hope it can be put into practical use in the future,” said Associate Professor Sawako Uchida-Kobayashi who led the research.

“使用易于获取且成本低廉的胸部X光片开发诊断方法，有望提高脂肪肝的检测水平。我们希望它未来能够投入实际应用，”领导该研究的副教授内田小奈子表示。