Department of Radiology, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510000, People's Republic of China.
Guangzhou Institute of Obstetrics and Gynecology, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510000, People's Republic of China.
J Magn Reson Imaging. 2024 Feb;59(2):496-509. doi: 10.1002/jmri.28787. Epub 2023 May 24.
Diagnostic performance of placenta accreta spectrum (PAS) by prenatal MRI is unsatisfactory. Deep learning radiomics (DLR) has the potential to quantify the MRI features of PAS.
To explore whether DLR from MRI can be used to identify pregnancies with PAS.
Retrospective.
324 pregnant women (mean age, 33.3 years) suspected PAS (170 training and 72 validation from institution 1, 82 external validation from institution 2) with clinicopathologically proved PAS (206 PAS, 118 non-PAS).
FIELD STRENGTH/SEQUENCE: 3-T, turbo spin-echo T2-weighted images.
The DLR features were extracted using the MedicalNet. An MRI-based DLR model incorporating DLR signature, clinical model (different clinical characteristics between PAS and non-PAS groups), and MRI morphologic model (radiologists' binary assessment for the PAS diagnosis) was developed. These models were constructed in the training dataset and then validated in the validation datasets.
The Student t-test or Mann-Whitney U, χ or Fisher exact test, Kappa, dice similarity coefficient, intraclass correlation coefficients, least absolute shrinkage and selection operator logistic regression, multivariate logistic regression, receiver operating characteristic (ROC) curve, DeLong test, net reclassification improvement (NRI) and integrated discrimination improvement (IDI), calibration curve with Hosmer-Lemeshow test, decision curve analysis (DCA). P < 0.05 indicated a significant difference.
The MRI-based DLR model had a higher area under the curve than the clinical model in three datasets (0.880 vs. 0.741, 0.861 vs. 0.772, 0.852 vs. 0.675, respectively) or MRI morphologic model in training and independent validation datasets (0.880 vs. 0.760, 0.861, vs. 0.781, respectively). The NRI and IDI were 0.123 and 0.104, respectively. The Hosmer-Lemeshow test had nonsignificant statistics (P = 0.296 to 0.590). The DCA offered a net benefit at any threshold probability.
An MRI-based DLR model may show better performance in diagnosing PAS than a clinical or MRI morphologic model.
3 TECHNICAL EFFICACY STAGE: 2.
产前磁共振成像（MRI）对胎盘植入谱系疾病（PAS）的诊断性能并不令人满意。深度学习放射组学（DLR）具有定量 PAS MRI 特征的潜力。
探讨 MRI 衍生的 DLR 是否可用于识别 PAS 孕妇。
回顾性。
324 名疑似 PAS 的孕妇（平均年龄 33.3 岁）（机构 1 的 170 名训练和 72 名验证，机构 2 的 82 名外部验证），经临床病理证实 PAS（206 例 PAS，118 例非 PAS）。
磁场强度/序列：3-T，涡轮自旋回波 T2 加权图像。
使用 MedicalNet 提取 DLR 特征。建立了一种基于 MRI 的 DLR 模型，该模型包含 DLR 特征、临床模型（PAS 组和非 PAS 组之间的不同临床特征）和 MRI 形态学模型（放射科医生对 PAS 诊断的二进制评估）。这些模型在训练数据集中构建，然后在验证数据集中进行验证。
采用 Student t 检验或 Mann-Whitney U 检验、χ 检验或 Fisher 确切检验、Kappa 检验、Dice 相似系数、组内相关系数、最小绝对收缩和选择算子逻辑回归、多变量逻辑回归、受试者工作特征（ROC）曲线、DeLong 检验、净重新分类改善（NRI）和综合判别改善（IDI）、校准曲线与 Hosmer-Lemeshow 检验、决策曲线分析（DCA）。P＜0.05 表示差异有统计学意义。
在三个数据集（0.880 vs. 0.741、0.861 vs. 0.772、0.852 vs. 0.675）或训练和独立验证数据集中的 MRI 形态学模型中（0.880 vs. 0.760、0.861 vs. 0.781），基于 MRI 的 DLR 模型的曲线下面积均高于临床模型。NRI 和 IDI 分别为 0.123 和 0.104。Hosmer-Lemeshow 检验的统计学结果无显著性差异（P=0.296 至 0.590）。DCA 在任何阈值概率下都提供了净效益。
基于 MRI 的 DLR 模型在诊断 PAS 方面可能优于临床或 MRI 形态学模型。
3 技术功效分级：2。
Zotero 插件