Department of Radiology, Cincinnati Children's Hospital Medical Center, University of Cincinnati College of Medicine, 3333 Burnet Ave, Cincinnati, OH 45229.
Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH.
AJR Am J Roentgenol. 2024 Jan;222(1):e2329812. doi: 10.2214/AJR.23.29812. Epub 2023 Aug 2.
Radiologists have variable diagnostic performance and considerable interreader variability when interpreting MR enterography (MRE) examinations for suspected Crohn disease (CD). The purposes of this study were to develop a machine learning method for predicting ileal CD by use of radiomic features of ileal wall and mesenteric fat from noncontrast T2-weighted MRI and to compare the performance of the method with that of expert radiologists. This single-institution study included retrospectively identified patients who underwent MRE for suspected ileal CD from January 1, 2020, to January 31, 2021, and prospectively enrolled participants (patients with newly diagnosed ileal CD or healthy control participants) from December 2018 to October 2021. Using axial T2-weighted SSFSE images, a radiologist selected two slices showing greatest terminal ileal wall thickening. Four ROIs were segmented, and radiomic features were extracted from each ROI. After feature selection, support-vector machine models were trained to classify the presence of ileal CD. Three fellowship-trained pediatric abdominal radiologists independently classified the presence of ileal CD on SSFSE images. The reference standard was clinical diagnosis of ileal CD based on endoscopy and biopsy results. Radiomic-only, clinical-only, and radiomic-clinical ensemble models were trained and evaluated by nested cross-validation. The study included 135 participants (67 female, 68 male; mean age, 15.2 ± 3.2 years); 70 were diagnosed with ileal CD. The three radiologists had accuracies of 83.7% (113/135), 88.1% (119/135), and 86.7% (117/135) for diagnosing CD; consensus accuracy was 88.1%. Interradiologist agreement was substantial (κ = 0.78). The best-performing ROI was bowel core (AUC, 0.95; accuracy, 89.6%); other ROIs had worse performance (whole-bowel AUC, 0.86; fat-core AUC, 0.70; whole-fat AUC, 0.73). For the clinical-only model, AUC was 0.85 and accuracy was 80.0%. The ensemble model combining bowel-core radiomic and clinical models had AUC of 0.98 and accuracy of 93.5%. The bowel-core radiomic-only model had significantly greater accuracy than radiologist 1 ( = .009) and radiologist 2 ( = .02) but not radiologist 3 ( > .99) or the radiologists in consensus ( = .05). The ensemble model had greater accuracy than the radiologists in consensus ( = .02). A radiomic machine learning model predicted CD diagnosis with better performance than two of three expert radiologists. Model performance improved when radiomic data were ensembled with clinical data. Deployment of a radiomic-based model including T2-weighted MRI data could decrease interradiologist variability and increase diagnostic accuracy for pediatric CD.
放射科医生在解释疑似克罗恩病（CD）的磁共振肠造影（MRE）检查时，诊断性能存在差异，且存在相当大的读者间差异。本研究旨在开发一种机器学习方法，通过使用非对比 T2 加权 MRI 获得回肠壁和肠系膜脂肪的放射组学特征来预测回肠 CD，并比较该方法与专家放射科医生的表现。这项单中心研究回顾性纳入了 2020 年 1 月 1 日至 2021 年 1 月 31 日期间因疑似回肠 CD 而行 MRE 的患者，并前瞻性纳入了 2018 年 12 月至 2021 年 10 月期间新诊断为回肠 CD 的患者或健康对照参与者。使用轴向 T2 加权 SSFSE 图像，放射科医生选择了两个显示最大末端回肠壁增厚的切片。对四个 ROI 进行了分割，并从每个 ROI 提取了放射组学特征。在特征选择后，支持向量机模型被训练以分类回肠 CD 的存在。三位经过专业培训的儿科腹部放射科医生独立对 SSFSE 图像上回肠 CD 的存在进行分类。参考标准是基于内镜和活检结果的临床诊断回肠 CD。仅放射组学、仅临床和放射组学-临床联合模型通过嵌套交叉验证进行训练和评估。该研究纳入了 135 名参与者（67 名女性，68 名男性；平均年龄 15.2±3.2 岁）；70 名被诊断为回肠 CD。这 3 位放射科医生诊断 CD 的准确率分别为 83.7%（113/135）、88.1%（119/135）和 86.7%（117/135）；共识准确率为 88.1%。放射科医生间的一致性较高（κ=0.78）。表现最好的 ROI 是肠核（AUC：0.95；准确率：89.6%）；其他 ROI 的表现较差（全肠 AUC：0.86；脂肪核 AUC：0.70；全脂肪 AUC：0.73）。对于仅临床模型，AUC 为 0.85，准确率为 80.0%。结合肠核放射组学和临床模型的联合模型 AUC 为 0.98，准确率为 93.5%。仅肠核放射组学模型的准确率明显高于放射科医生 1（=0.009）和放射科医生 2（=0.02），但与放射科医生 3（>0.99）或共识放射科医生（=0.05）无差异。联合模型的准确率高于共识放射科医生（=0.02）。放射组学机器学习模型在预测 CD 诊断方面的表现优于 3 位专家放射科医生中的 2 位。当放射组学数据与临床数据联合使用时，模型性能会提高。部署基于放射组学的模型，包括 T2 加权 MRI 数据，可能会降低放射科医生间的差异，提高儿科 CD 的诊断准确性。
