A Multicentre Comparative Analysis of Radiomics, Deep-learning, and Fusion Models for Predicting Postpartum Hemorrhage.

Authors

Zhang W,Zhao X,Meng L,Lu L,Guo J,Cheng M,Tian H,Ren N,Yin J,Zhang X

Affiliations (6)

  • Department of Radiology, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China (W.Z., X.Z., L.L., M.C., H.T., N.R., X.Z.).
  • Department of Radiology, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China (W.Z., X.Z., L.L., M.C., H.T., N.R., X.Z.); Tianjian Laboratory of Advanced Biomedical Sciences, Institute of Advanced Biomedical Sciences, Zhengzhou University, Zhengzhou, China (X.Z.).
  • Department of Medical Technology, Shangqiu Medical College, Shangqiu, China (L.M.).
  • General Electric (GE) Healthcare, MR Research China, Beijing, China (J.G.).
  • Department of Neonatology, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China (J.Y.).
  • Department of Radiology, The Third Affiliated Hospital of Zhengzhou University, Zhengzhou, China (W.Z., X.Z., L.L., M.C., H.T., N.R., X.Z.). Electronic address: [email protected].

Abstract

This study compared the capabilities of two-dimensional (2D) and three-dimensional (3D) deep learning (DL), radiomics, and fusion models to predict postpartum hemorrhage (PPH), using sagittal T2-weighted MRI images. This retrospective study successively included 581 pregnant women suspected of placenta accreta spectrum (PAS) disorders who underwent placental MRI assessment between May 2018 and June 2024 in two hospitals. Clinical information was collected, and MRI images were analyzed by two experienced radiologists. The study cohort was divided into training (hospital 1, n=470) and validation (hospital 2, n=160) sets. Radiomics features were extracted after image segmentation to develop the radiomics model, 2D and 3D DL models were developed, and two fusion strategies (early and late fusion) were used to construct the fusion models. ROC curves, AUC, sensitivity, specificity, calibration curves, and decision curve analysis were used to evaluate the models' performance. The late-fusion model (DLRad_LF) yielded the highest performance, with AUCs of 0.955 (95% CI: 0.935-0.974) and 0.898 (95% CI: 0.848-0.949) in the training and validation sets, respectively. In the validation set, the AUC of the 3D DL model was significantly larger than those of the radiomics (AUC=0.676, P<0.001) and 2D DL (AUC=0.752, P<0.001) models. Subgroup analysis found that placenta previa and PAS did not impact the models' performance significantly. The DLRad_LF model could predict PPH reasonably accurately based on sagittal T2-weighted MRI images.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.