High-level feature-guided attention optimized neural network for neonatal lateral ventricular dilatation prediction.

Background: Periventricular-intraventricular hemorrhage can lead to posthemorrhagic ventricular dilatation or even posthemorrhagic hydrocephalus if not detected promptly. Sequential cranial ultrasound scans are typically used for their diagnoses. Nonetheless, manual image audit has numerous disadvantages.

Purpose: This study aimed to develop a predictive model utilizing modified inception (MI) and high-level feature-guided attention (HFA) modules for predicting neonatal lateral ventricular dilation via ultrasound images.

Methods: The MI modules reduced input data sizes and dimensions, while the HFA modules effectively delved into semantic information through supervision from high-level feature images to low-level feature images. The process facilitated the accurate identification of dilated lateral ventricles. A total of 710 neonates, corresponding to 1420 lateral ventricles, were recruited in this study. Each lateral ventricle was captured in two images, one on the parasagittal plane and the other on the coronal plane. The combination of anterior horn width, ventricular index, thalamo-occipital distance, and ventricular height served as the gold standard. A lateral ventricle would be considered dilatated if any of these four indices exceeded its upper reference value. These lateral ventricles were randomly split into training and testing sets at a 7:3 ratio. We evaluated the validity of our proposed approach and its competitors across the coronal plane, parasagittal plane, and overall performance. We also determined the impact of subjects' baseline characteristics on the overall performance of the proposed approach. Additionally, ablation analyses were conducted to ensure the efficacy of the proposed approach.

Results: Our proposed approach achieved the largest Youden index (0.65, 95% CI: 0.58-0.72), DOR (27.11, 95% CI: 15.89-46.26), area under curves (AUC) of receiver operating characteristic curve (ROC) (0.84, 95% CI: 0.80-0.88), and AUC of precision-recall curve (PRC) (0.81, 95% CI: 0.74-0.86) in the overall performance assessment and ablation analyses. Moreover, it boasted the biggest Cramer's V values on the coronal (Cramer's V = 0.488, p < 0.001) and parasagittal (Cramer's V = 0.713, p < 0.001) planes individually. Factors such as left side, male sex, singleton birth, and vaginal delivery were positively correlated with higher performance regarding the proposed algorithm, except for the gestational age.

Conclusion: This work provides a novel attention optimized algorithm for rapid and accurate ventricular dilatation predictions. It surpasses the traditional algorithms in terms of validity whether concerning the coronal plane, parasagittal plane, or overall performance. The overall performance of algorithms will be influenced by the baseline characteristics of populations.