文献速递炎症性肠病消化内镜消化道肿瘤与早癌

人工智能在克罗恩病CT小肠造影中量化累积小肠疾病严重程度

Artificial Intelligence for Quantifying Cumulative Small Bowel Disease Severity on CT-Enterography in Crohn's Disease.
PubMed 文献 · Am J Gastroenterol · 2024-04-25

本研究在三级医疗中心接受生物制剂治疗的成人回肠克罗恩病患者中,开发机器学习方法自动评估CT小肠造影上的累积回肠损伤,并与传统肠道指标比较预测未来小肠手术的能力。机器学习与放射科医生评分一致性高(κ=0.80),累积空间指标模型预测未来手术的AUC为0.76,优于传统指标模型(AUC=0.62)。

要点

  • 机器学习与放射科医生对回肠损伤评分的一致性高(κ=0.80),与放射科医生间一致性(κ=0.87)相似。
  • 未来手术患者的累积损伤评分(46.6 vs 30.4,P=0.0007)和平均累积损伤等级(1.80 vs 1.42,P<0.0001)均高于未手术者。
  • 累积空间指标模型预测未来手术的AUC为0.76,优于传统肠道指标、实验室值和病史模型(AUC=0.62)。

核心结论

  • 自动累积回肠损伤评分在改善小肠克罗恩病结局预测方面显示出潜力。
  • 空间小肠造影分析可超越复制专家判断,增强克罗恩病肠道评估的个性化。

研究设计与样本

  • 研究纳入 tertiary care center 接受生物制剂治疗的成人回肠克罗恩病患者,对CT小肠造影(CTE)扫描进行机器学习分析。
  • 两名经过专科培训的放射科医生沿回肠以1 cm为空间增量(称为 mini-segments)对肠道损伤严重程度进行评分。
  • 机器学习分割方法基于放射科医生评分训练,预测严重程度并空间映射至回肠。
  • 累积损伤计算为沿回肠严重程度等级的总和(S-CIDSS)和平均值。
  • 多变量模型比较未来小肠切除与累积回肠损伤指标及传统肠道指标,并校正CTE时的实验室值、药物和既往手术。

主要发现

  • 共分析229次CTE扫描的8,424个 mini-segments。
  • 机器学习与放射科医生损伤评分一致性强度为κ=0.80(95%CI 0.79-0.81),与放射科医生间一致性κ=0.87(95%CI 0.85-0.88)相似。
  • 未来手术的CD生物制剂使用者中,S-CIDSS较高(46.6 vs 30.4,P=0.0007),平均累积损伤等级评分也较高(1.80 vs 1.42,P<0.0001)。
  • 使用累积空间指标的模型预测生物制剂使用者未来手术的AUC=0.76,优于使用传统肠道指标、实验室值和病史的模型(AUC=0.62)。

关键数值与推荐

  • 机器学习与放射科医生评分一致性κ=0.80(95%CI 0.79-0.81),放射科医生间一致性κ=0.87(95%CI 0.85-0.88)。
  • 未来手术者S-CIDSS为46.6,未手术者为30.4(P=0.0007)。
  • 未来手术者平均累积损伤等级评分为1.80,未手术者为1.42(P<0.0001)。
  • 累积空间指标模型预测未来手术的AUC=0.76,传统指标模型AUC=0.62。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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)。

原文

INTRODUCTION: Assessing the cumulative degree of bowel injury in ileal Crohn's disease (CD) is difficult. We aimed to develop machine learning (ML) methodologies for automated estimation of cumulative ileal injury on computed tomography-enterography (CTE) to help predict future bowel surgery. METHODS: Adults with ileal CD using biologic therapy at a tertiary care center underwent ML analysis of CTE scans. Two fellowship-trained radiologists graded bowel injury severity at granular spatial increments along the ileum (1 cm), called mini-segments. ML segmentation methods were trained on radiologist grading with predicted severity and then spatially mapped to the ileum. Cumulative injury was calculated as the sum (S-CIDSS) and mean of severity grades along the ileum. Multivariate models of future small bowel resection were compared with cumulative ileum injury metrics and traditional bowel measures, adjusting for laboratory values, medications, and prior surgery at the time of CTE. RESULTS: In 229 CTE scans, 8,424 mini-segments underwent analysis. Agreement between ML and radiologists injury grading was strong (κ = 0.80, 95% confidence interval 0.79-0.81) and similar to inter-radiologist agreement (κ = 0.87, 95% confidence interval 0.85-0.88). S-CIDSS (46.6 vs 30.4, P = 0.0007) and mean cumulative injury grade scores (1.80 vs 1.42, P < 0.0001) were greater in CD biologic users that went to future surgery. Models using cumulative spatial metrics (area under the curve = 0.76) outperformed models using conventional bowel measures, laboratory values, and medical history (area under the curve = 0.62) for predicting future surgery in biologic users. DISCUSSION: Automated cumulative ileal injury scores show promise for improving prediction of outcomes in small bowel CD. Beyond replicating expert judgment, spatial enterography analysis can augment the personalization of bowel assessment in CD.

来源:Am J Gastroenterol,查看原文。版权归原作者所有。

引用

  1. Stidham RW, Enchakalody B, Wang SC, et al. Artificial Intelligence for Quantifying Cumulative Small Bowel Disease Severity on CT-Enterography in Crohn's Disease. Am J Gastroenterol. 2024. PMID: 38661148. doi:10.14309/ajg.0000000000002828

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。