人工智能在常规腹部CT上评估身体成分并预测胰腺癌患者死亡率:本地化应用方案
本研究开发了一种全自动神经网络,在L3椎体层面从常规腹部CT量化脂肪和肌肉质量,并在136例胰腺癌队列中验证。算法与参考标准一致性良好(ICC>0.8),肌肉减少症与死亡率显著相关(调整HR 1.58,95%CI 1.03-3.33),而内脏脂肪与死亡率无关。作者公开了代码、训练数据和工作流程以促进本地应用。
要点
- AI可在1秒左右自动完成L3层面身体成分分析,ICC>0.8,适合嵌入常规报告流程。
- 肌肉减少症(按公认SMI切点)与胰腺癌患者死亡率独立相关,调整HR 1.58。
- 内脏脂肪中位值分类与死亡率无关,阅片时不应将其作为预后指标单独解读。
关键影像表现/征象
- 在L3椎体层面自动分割并量化肌肉和脂肪质量,算法基于常规腹部CT图像。
- 肌肉减少症定义为低于公认的骨骼肌指数切点,内脏脂肪按其中位值分类。
- 胰腺癌队列中15%存在肌肉减少症,平均内脏脂肪142 cm2。
诊断标准与关键数值
- 肌肉减少症采用公认的骨骼肌指数(SMI)切点定义,具体数值原文未报告。
- 内脏脂肪以其中位值作为分类阈值,具体数值原文未报告。
- 算法在LiTS数据训练后应用于本地队列,ICC>0.8;两数据集联合训练后ICC>0.9。
- 肌肉减少症与死亡率关联:平均生存15±12 vs 22±12(p<0.05),调整HR 1.58(95%CI 1.03-3.33)。
临床应用与阅片要点
- 可将AI身体成分分析整合到常规腹部CT报告流程,自动提供L3层面肌肉和脂肪定量。
- 对胰腺癌患者,关注肌肉减少症提示预后不良,但内脏脂肪不宜单独作为预后判断依据。
- 算法检测分析耗时约1±0.5秒,适合临床工作流。
局限性
- 胰腺癌队列样本量有限(136例),单中心数据,外部泛化性需进一步验证。
- 肌肉减少症和内脏脂肪分类阈值依赖特定切点或中位值,可能受人群差异影响。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Body composition is associated with mortality; however its routine assessment is too time-consuming.
PURPOSE: To demonstrate the value of artificial intelligence (AI) to extract body composition measures from routine studies, we aimed to develop a fully automated AI approach to measure fat and muscles masses, to validate its clinical discriminatory value, and to provide the code, training data and workflow solutions to facilitate its integration into local practice.
METHODS: We developed a neural network that quantified the tissue components at the L3 vertebral body level using data from the Liver Tumor Challenge (LiTS) and a pancreatic cancer cohort. We classified sarcopenia using accepted skeletal muscle index cut-offs and visceral fat based its median value. We used Kaplan Meier curves and Cox regression analysis to assess the association between these measures and mortality.
RESULTS: Applying the algorithm trained on LiTS data to the local cohort yielded good agreement [>0.8 intraclass correlation (ICC)]; when trained on both datasets, it had excellent agreement (>0.9 ICC). The pancreatic cancer cohort had 136 patients (mean age: 67 ± 11 years; 54% women); 15% had sarcopenia; mean visceral fat was 142 cm2. Concurrent with prior research, we found a significant association between sarcopenia and mortality [mean survival of 15 ± 12 vs. 22 ± 12 (p < 0.05), adjusted HR of 1.58 (95% CI: 1.03-3.33)] but no association between visceral fat and mortality. The detector analysis took 1 ± 0.5 s.
CONCLUSIONS: AI body composition analysis can provide meaningful imaging biomarkers from routine exams demonstrating AI's ability to further enhance the clinical value of radiology reports.
引用
- Hsu TH, Schawkat K, Berkowitz SJ, et al. Artificial intelligence to assess body composition on routine abdominal CT scans and predict mortality in pancreatic cancer- A recipe for your local application. Eur J Radiol. 2021. PMID: 34252866. doi:10.1016/j.ejrad.2021.109834
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。