可解释的机器学习模型使用双能CT用于预测胃癌的不良组织病理状态:一个多中心研究
Yiyang Liu1, Shuai Zhao2, Diansen Chen3
1Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, China; Henan International Joint Laboratory of Medical Imaging, Zhengzhou, China; Henan Key Laboratory of Imaging Diagnosis and Treatment for Digestive System Tumor, Zhengzhou, China; Henan Key Laboratory of CT Imaging, Zhengzhou, China; Department of Medical Imaging, Zhengzhou University People's Hospital and Henan Provincial People's Hospital, Zhengzhou, China.
使用双能CT (DECT) 定量参数的机器学习模型可以预测不利的胃癌 (GC) 组织病理学. 这些模型还与患者无进展生存相关,提供非侵入性见解.
科学领域:
- 放射学 放射学是一门学科.
- 在瘤学瘤学.
- 医疗成像医学成像
背景情况:
- 胃癌 (GC) 的诊断和分期通常依赖于侵入性手术.
- 需要准确的非侵入性方法来评估GC组织病理学和预测患者的结果.
研究的目的:
- 调查机器学习 (ML) 算法的实用性,集成多个双能CT (DECT) 定量参数,用于非侵入性解码GC中的不良基因病理状态.
- 评估这些ML模型与患者无进展生存率的相关性.
主要方法:
- 一项观察性研究涉及手术切除GC的患者,他们在六个医疗中心接受了DECT.
- 开发和验证五个ML模型,使用14个定量DECT参数来预测T3/T4阶段,淋巴结转移 (LNM) 和淋巴血管/周围神经侵入 (LVI/PNI).
- 使用考克斯回归和卡普兰-梅尔方法进行生存分析;用于模型解释性的SHapley添加式扩展 (SHAP).
主要成果:
- ML模型实现了高预测性能,AUC从0.825到0.907 (训练) 和0.774到0.848 (测试) 之间.
- 随机森林模型显示出有利的性能. 关键预测因素包括140 keV单能衰减和正常化的度.
- 所有模型都显示了对外部验证队列的概括性 (AUC > 0.70) 并与改善无进展生存率 (p < 0.05) 相联系.
结论:
- 整合多个DECT定量参数的ML模型可以有效地解码GC中的不良基因病理特征.
- 这些基于DECT的非侵入性ML模型显示出预后价值,与患者无进展生存率相关.
相关概念视频
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Imaging Studies I: CT and MRI
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Imaging Studies for Cardiovascular System V: CT
Simplified Synchronous Machine Model
In this model, each generator is connected to a...
Wind Turbine Machine Models
Induction machines interact through the rotating magnetic field generated by the stator and the rotor. The key parameter is slip, which is the difference between synchronous speed and rotor speed relative to synchronous speed. Slip is...
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT


