Introduction: Heterogeneous MRI manifestations restrict the efficiency and consistency of neuroradiologists in diagnosing hypoxic-ischemic encephalopathy (HIE) due to complex injury patterns. This study aimed to develop and validate an intelligent HIE identification model (termed as DLCRN, deep learning clinical-radiomics nomogram) based on conventional structural MRI and clinical characteristics.
Methods: In this retrospective case-control study, full-term neonates with HIE and healthy controls were collected in two different medical centers from January 2015 to December 2020. Multivariable logistic regression analysis was implemented to establish the DLCRN model based on conventional MRI sequences and clinical characteristics. Discrimination, calibration, and clinical applicability were used to evaluate the model in the training and validation cohorts. Grad-class activation map algorithm was implemented to visualize the DLCRN.
Results: 186 HIE patients and 219 healthy controls were assigned to the training, internal validation, and independent validation cohorts. Birthweight was incorporated with deep radiomics signatures to create the final DLCRN model. The DLCRN model achieved better discriminatory power than simple radiomics models, with an area under the curve (AUC) of 0.868, 0.813, and 0.798 in the training, internal validation, and independent validation cohorts, respectively. The DLCRN model was well calibrated and has clinical potential. Visualization of the DLCRN highlighted the lesion areas that conformed to radiological identification.
Conclusion: Visualized DLCRN may be a useful tool in the objective and quantitative identification of HIE. Scientific application of the optimized DLCRN model may save time for screening early mild HIE, improve the consistency of HIE diagnosis, and guide timely clinical management.
Keywords: Deep learning; Neonate hypoxic-ischemic encephalopathy; Neuroimage.
© 2023 S. Karger AG, Basel.