From the Department of Radiology, Kangdong Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Republic of Korea (J.H.H.); Department of Radiology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 222 Banpo-daero, Seocho-gu, Seoul 06591, Republic of Korea (J.Y.J., A.J., S.Y.L., H.P., S.E.L., S.K.); Division of Biomedical Engineering, Hankuk University of Foreign Studies, Gyeonggi-do, Republic of Korea (Y.N.); and Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Republic of Korea (S.P.).
Radiology. 2021 Jun;299(3):626-632. doi: 10.1148/radiol.2021203783. Epub 2021 Mar 30.
Background It is important to diagnose sclerotic bone lesions in order to determine treatment strategy. Purpose To evaluate the diagnostic performance of a CT radiomics-based machine learning model for differentiating bone islands and osteoblastic bone metastases. Materials and Methods In this retrospective study, patients who underwent contrast-enhanced abdominal CT and were diagnosed with a bone island or osteoblastic metastasis between 2015 to 2019 at either of two different institutions were included: institution 1 for the training set and institution 2 for the external test set. Radiomics features were extracted. The random forest (RF) model was built using 10 selected features, and subsequent 10-fold cross-validation was performed. In the test phase, the RF model was tested with an external test set. Three radiologists reviewed the CT images for the test set. The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated for the models and each of the three radiologists. The AUCs of the radiomics model and radiologists were compared. Results A total of 177 patients (89 with a bone island and 88 with metastasis; mean age, 66 years ± 12 [standard deviation]; 111 men) were in the training set, and 64 (23 with a bone island and 41 with metastasis; mean age, 69 years ± 14; 59 men) were in the test set. Radiomics features ( = 1218) were extracted. The average AUC of the RF model from 10-fold cross-validation was 0.89 (sensitivity, 85% [75 of 88 patients]; specificity, 82% [73 of 89 patients]; and accuracy, 84% [148 of 177 patients]). In the test set, the AUC of the trained RF model was 0.96 (sensitivity, 80% [33 of 41 patients]; specificity, 96% [22 of 23 patients]; and accuracy, 86% [55 of 64 patients]). The AUCs for the three readers were 0.95 (95% CI: 0.90, 1.00), 0.96 (95% CI: 0.90, 1.00), and 0.88 (95% CI: 0.80, 0.96). The AUC of radiomics model was higher than that of only reader 3 (0.96 vs 0.88, respectively; = .03). Conclusion A CT radiomics-based random forest model was proven useful for differentiating bone islands from osteoblastic metastases and showed better diagnostic performance compared with an inexperienced radiologist. © RSNA, 2021 See also the editorial by Vannier in this issue.
背景 为了确定治疗策略，对硬化性骨病变进行诊断非常重要。目的 评估基于 CT 放射组学的机器学习模型对鉴别骨岛和成骨转移瘤的诊断性能。材料与方法 本回顾性研究纳入了 2015 年至 2019 年间在两家不同机构（机构 1 用于训练集，机构 2 用于外部测试集）诊断为骨岛或成骨转移瘤的接受增强腹部 CT 检查的患者：机构 1 用于训练集，机构 2 用于外部测试集。提取放射组学特征。使用 10 个选定的特征构建随机森林（RF）模型，然后进行 10 折交叉验证。在测试阶段，使用外部测试集对 RF 模型进行测试。三位放射科医生对测试集的 CT 图像进行了审查。为模型和三位放射科医生中的每一位计算了敏感性、特异性、准确性和受试者工作特征曲线（ROC）下的面积（AUC）。比较了放射组学模型和放射科医生的 AUC。结果 在训练集中共有 177 例患者（骨岛 89 例，转移瘤 88 例；平均年龄 66 岁±12[标准差]；111 例男性），64 例（骨岛 23 例，转移瘤 41 例；平均年龄 69 岁±14；59 例男性）在测试集中。提取了 1218 个放射组学特征。来自 10 折交叉验证的 RF 模型的平均 AUC 为 0.89（敏感性 85%[88 例患者中的 75 例]；特异性 82%[89 例患者中的 73 例]；准确性 84%[177 例患者中的 148 例]）。在测试集中，训练后的 RF 模型的 AUC 为 0.96（敏感性 80%[41 例患者中的 33 例]；特异性 96%[23 例患者中的 22 例]；准确性 86%[64 例患者中的 55 例]）。三位读者的 AUC 分别为 0.95（95%CI：0.90，1.00）、0.96（95%CI：0.90，1.00）和 0.88（95%CI：0.80，0.96）。放射组学模型的 AUC 高于仅读者 3（0.96 与 0.88，分别； =.03）。结论 CT 放射组学随机森林模型有助于鉴别骨岛和成骨转移瘤，与经验不足的放射科医生相比，其诊断性能更好。©RSNA，2021 请参见本期杂志中 Vannier 的评论。
