Yang Huancheng, Wu Xiang, Liu Weihao, Yuan Yangguang, Zeng Haoyang, Li Junkai, Ye Baiwei, Wang Lei, Luo Shimei, Li Zhe, Liu Hanlin
Department of Luohu Clinical Institute, Shantou University, Shantou, China.
Department of Medical College, Shantou University, Shantou, China.
Quant Imaging Med Surg. 2023 Oct 1;13(10):7105-7116. doi: 10.21037/qims-23-142. Epub 2023 Aug 21.
Placenta accreta spectrum (PAS) is a significant contributor to maternal morbidity and mortality. Our objective was to develop a quantitative analysis framework utilizing magnetic resonance imaging (MRI)-anatomical-clinical features to predict 3 clinically significant parameters in patients with PAS: placenta subtype (invasive . non-invasive placenta), intraoperative bleeding (≥1,500 . <1,500 mL), and hysterectomy risk (hysterectomy . non-hysterectomy).
A total of 125 pregnant women with PAS from 2 medical centers were enrolled into an internal training set and an external testing set. Some 21 MRI-anatomical-clinical features were integrated as input into the framework. The proposed quantitative analytic framework contains mainly 3 classifiers built by extreme gradient boosting (XGBoost) and their testing in external datasets. We also further compared the accuracy of placenta subtype prediction between the proposed model and 4 radiologists. A quantitative model interpretation method called SHapley Additive exPlanations (SHAP) was conducted to explore the contribution of each feature.
The placenta subtype (invasive . non-invasive), intraoperative bleeding (≥1,500 . <1,500 mL), and hysterectomy risk (hysterectomy . non-hysterectomy) demonstrated impressive area under the receiver operating characteristic curve (AUROC) values of 0.93, 0.88, and 0.90, respectively, in the internal validation set. Even in the external testing set, these metrics maintained their strength, achieving AUROC values of 0.91, 0.82, and 0.82, respectively. Comparing our proposed framework to the 4 radiologists, our model exhibited superior accuracy, specificity, and sensitivity in predicting placental subtypes within the external testing cohort. The features associated with intraplacental dark T2 bands played a crucial role in the decision-making process of all 3 prediction models.
The quantitative analysis framework can provide a robust method for classification of placenta subtype (invasive . non-invasive placenta), intraoperative bleeding (≥1,500 . <1,500 mL), and hysterectomy risk (hysterectomy . non-hysterectomy) based on MRI-anatomical-clinical features in PAS.
胎盘植入谱系疾病（PAS）是导致孕产妇发病和死亡的重要原因。我们的目标是开发一种利用磁共振成像（MRI）解剖学 - 临床特征的定量分析框架，以预测PAS患者的3个临床重要参数：胎盘亚型（侵入性. 非侵入性胎盘）、术中出血量（≥1500. <1500 mL）和子宫切除风险（子宫切除. 非子宫切除）。
来自2个医疗中心的125例患有PAS的孕妇被纳入内部训练集和外部测试集。约21个MRI解剖学 - 临床特征被整合作为框架的输入。所提出的定量分析框架主要包含由极端梯度提升（XGBoost）构建的3个分类器及其在外部数据集中的测试。我们还进一步比较了所提出模型与4名放射科医生在胎盘亚型预测方面的准确性。采用一种称为SHapley Additive exPlanations（SHAP）的定量模型解释方法来探索每个特征的贡献。
在内部验证集中，胎盘亚型（侵入性. 非侵入性）、术中出血量（≥1500. <1500 mL）和子宫切除风险（子宫切除. 非子宫切除）的受试者工作特征曲线下面积（AUROC）值分别令人印象深刻，为0.93、0.88和0.90。即使在外部测试集中，这些指标也保持了其优势，AUROC值分别为0.91、0.82和0.82。将我们提出的框架与4名放射科医生进行比较，我们的模型在外部测试队列中预测胎盘亚型时表现出更高的准确性、特异性和敏感性。与胎盘内暗T2带相关的特征在所有3个预测模型的决策过程中都起着关键作用。
该定量分析框架可以提供一种基于PAS的MRI解剖学 - 临床特征对胎盘亚型（侵入性. 非侵入性胎盘）、术中出血量（≥1500. <1500 mL）和子宫切除风险（子宫切除. 非子宫切除）进行分类的可靠方法。
