Background: Radiologic volumetric evaluation of Wilms’ tumor (WT) is an important indicator to guide treatment decisions. However, due to the heterogeneity of the tumors, radiologists have main-guard differences in diagnosis that can lead to misdiagnosis and poor treatment. The aim of this study was to explore whether CT-based outlining of WT foci can be automated using deep learning. Methods: We included CT intravenous phase images of 105 patients with WT and double-blind outlining of lesions by two radiologists. Then, we trained an automatic segmentation model using nnUnet. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD₉₅) were used to assess the performance. Next, we optimized the automatic segmentation results based on the ratio of the three-dimensional diameter of the lesion to improve the performance of volumetric assessment. Results: The DSC and HD₉₅ was 0.83 ± 0.22 and 10.50 ± 8.98 mm. The absolute difference and percentage difference in tumor size was 72.27 ± 134.84 cm³ and 21.08% ± 30.46%. After optimization according to our method, it decreased to 40.22 ± 96.06 cm³ and 10.16% ± 9.70%. Conclusion: We introduce a novel method that enhances the accuracy of predicting WT volume by integrating AI automated outlining and 3D tumor diameters. This approach surpasses the accuracy of using AI outcomes alone and has the potential to enhance the clinical evaluation of pediatric patients with WT. By intertwining AI outcomes with clinical data, this method becomes more interpretive and offers promising applications beyond Wilms tumor, extending to other pediatric diseases.

Magnetic resonance imaging (MRI) is an important non-invasive examination in the early diagnosis of juvenile dermatomyositis (JDM). We aimed to evaluate the feasibility of radiomics to establish a quantitative analysis of MRI images. Radiomics and machine learning were used to retrospectively analyze MRI T2 fat suppression sequences and relevant clinical data. The model associated with radiomics features was established using a cohort of patients who underwent thigh MRI at the children’s hospital from June 2014 to September 2021. In total, 75 patients with JDM and 75 control children were included in the training cohort (n = 102) and validation cohort (n = 48). The independent factors including lower muscle strength (OR, 0.75; 95% CI, 0.59–0.90), higher creatine kinase (CK) level (OR, 1.65; 95% CI, 1.20–2.38), and higher radiomics score (OR, 2.30; 95% CI, 1.63–3.62) were associated with a clinical diagnosis of JDM. The combined model achieved good discrimination performance compared the radiomics score model under linear discriminant analyses in the training cohort (AUC, 0.949; 95% CI, 0.912–0.986 vs. AUC, 0.912; 95% CI, 0.858–0.967; p = 0.02) and in the validation cohort (AUC, 0.945; 95% CI, 0.878–1 vs. AUC, 0.905; 95% CI, 0.812–0.998; p = 0.03). The combined model showed the diagnostic value was not weaker than the biopsy (AUC, 0.950; 95% CI, 0.919–0.981, n = 150 vs. AUC, 0.952; 95% CI, 0.889–1, n = 72; p = 0.95) and electromyogram (EMG) (AUC, 0.950; 95% CI, 0.919–0.981 vs. AUC, 0.900; 95% CI, 0.852–0.948; p = 0.10) among all the patients. The combination of radiomics features extracted from the MRI and non-invasive clinical characteristics obtained a pronounced discriminative performance to assist in discriminating JDM.

(2020). Transcatheter closure of congenital right coronary artery-to-left atrium fistula using Amplatzer duct occlude: Image focus. Acta Cardiologica. Ahead of Print.