BackgroundDifferent placenta accreta spectrum (PAS) subtypes pose varying surgical risks to the parturient. Machine learning model has the potential to diagnose PAS disorder.PurposeTo develop a cascaded deep semantic‐radiomic‐clinical (DRC) model for diagnosing PAS and its subtypes based on T2‐weighted MRI.Study TypeRetrospective.Population361 pregnant women (mean age: 33.10 ± 4.37 years), suspected of PAS, divided into segment training cohort (N = 40), internal training cohort (N = 139), internal testing cohort (N = 60), and external testing cohort (N = 122).Field Strength/SequenceCoronal T2‐weighted sequence at 1.5 T and 3.0 T.AssessmentClinical characteristics such as history of uterine surgery and the presence of placenta previa, complete placenta previa and dangerous placenta previa were extracted from clinical records. The DRC model (incorporating radiomics, deep semantic features, and clinical characteristics), a cumulative radiological score method performed by radiologists, and other models (including a radiomics and clinical, the clinical, radiomics and deep learning models) were developed for PAS disorder diagnosing (existence of PAS and its subtypes).Statistical TestsAUC, ACC, Student's t‐test, the Mann–Whitney U test, chi‐squared test, dice coefficient, intraclass correlation coefficients, least absolute shrinkage and selection operator regression, receiver operating characteristic curve, calibration curve with the Hosmer–Lemeshow test, decision curve analysis, DeLong test, and McNemar test. P < 0.05 indicated a significant difference.ResultsIn PAS diagnosis, the DRC‐1 outperformed than other models (AUC = 0.850 and 0.841 in internal and external testing cohorts, respectively). In PAS subtype classification (abnormal adherent placenta and abnormal invasive placenta), DRC‐2 model performed similarly with radiologists (P = 0.773 and 0.579 in the internal testing cohort and P = 0.429 and 0.874 in the external testing cohort, respectively).Data ConclusionThe DRC model offers efficiency and high diagnostic sensitivity in diagnosis, aiding in surgical planning.Level of Evidence3Technical EfficacyStage 2

中文翻译：

---

MRI 深度学习放射组学分析结合临床特征诊断侵入性胎盘谱及其亚型

背景不同的侵入性胎盘谱系 (PAS) 亚型给产妇带来不同的手术风险。机器学习模型具有诊断 PAS 疾病的潜力。目的开发级联深度语义放射学临床 (DRC) 模型，用于基于 T2 加权 MRI 诊断 PAS 及其亚型。研究类型回顾性。人群 361 名孕妇（平均年龄：33.10 ± 4.37岁），疑似PAS，分为分段训练队列（氮= 40), 内部培训队列 (氮= 139），内部测试队列（氮= 60），以及外部测试队列（氮= 122).场强/序列1.5 T和3.0 T的冠状T2加权序列。评估从临床记录中提取临床特征，例如子宫手术史和前置胎盘、完全性前置胎盘和危险性前置胎盘的存在。DRC模型（结合放射组学、深度语义特征和临床特征）、由放射科医生执行的累积放射学评分方法以及其他模型（包括放射组学和临床、临床、放射组学和深度学习模型）被开发用于PAS疾病诊断（PAS 及其亚型的存在）。统计测试AUC、ACC、学生t‐检验、Mann-Whitney U 检验、卡方检验、骰子系数、组内相关系数、最小绝对收缩和选择算子回归、受试者工作特征曲线、Hosmer-Lemeshow 检验校准曲线、决策曲线分析、DeLong 检验，和麦克尼马尔测试。磷< 0.05 表示存在显着差异。结果在 PAS 诊断中，DRC-1 优于其他模型（内部和外部测试队列中的 AUC 分别为 0.850 和 0.841）。在 PAS 亚型分类（异常粘附性胎盘和异常浸润性胎盘）中，DRC-2 模型与放射科医生的表现相似（磷= 内部测试队列中的 0.773 和 0.579磷外部测试队列中分别 = 0.429 和 0.874）。数据结论 DRC 模型在诊断方面提供效率和高诊断灵敏度，有助于手术计划。证据级别 3 技术功效阶段 2