Identification of an Ultra-High-Risk Subgroup of Neuroblastoma Patients within the High-Risk Cohort Using a Computed Tomography-Based Radiomics Approach.

RATIONALE AND OBJECTIVES: To identify ultra-high-risk (UHR) neuroblastoma patients who experienced disease-related mortality within 18 months of diagnosis within the high-risk cohort using computed tomography (CT)-based radiomics analysis. MATERIALS AND METHODS: A retrospective analysis was conducted on 105 high-risk neuroblastoma patients, divided into a training set (n = 74) and a test set (n = 31). Radiomics features were extracted and selected from arterial phase CT images, and an optimal radiomics signature was established using the support vector machine algorithm. Evaluation metrics, including area under the curve (AUC) and 95% confidence interval (CI), were calculated. Furthermore, the fit and clinical benefit of the signature, along with its correlation with overall survival (OS), were analyzed. RESULTS: The optimal radiomics signature comprised 11 features. In the training set, AUC and accuracy were 0.911 (95% CI: 0.840-0.982) and 0.892, respectively. In the test set, AUC and accuracy were 0.828 (95% CI: 0.669-0.987) and 0.839, respectively. There was no significant difference between predicted probability and actual probability, and the signature demonstrated net benefit. The concordance index of this signature for predicting OS was 0.743 (95% CI: 0.672-0.814) in the training set and 0.688 (95% CI: 0.566-0.810) in the test set. Moreover, the signature achieved AUC values of 0.832, 0.863, and 0.721 for 1-year, 2-year, and 3-year OS in the training set, and 0.870, 0.836, and 0.638 in the test set for the respective time periods. CONCLUSION: The utilization of CT-based radiomics signature to identify an UHR subgroup of neuroblastoma patients within the high-risk cohort can help aid in predicting early disease progression.

Using computed tomography angiography and computational fluid dynamics to study aortic coarctation in different arch morphologies.

Objective: To study the differences in computed tomography angiography (CTA) imaging of gothic arches, crenel arches, and romanesque arches in children with Aortic Coarctation (CoA), and to apply computational fluid dynamics (CFD) to study hemodynamic changes in CoA children with gothic arch aorta. Methods: The case data and CTA data of children diagnosed with CoA (95 cases) in our hospital were retrospectively collected, and the morphology of the aortic arch in the children was defined as gothic arch (n = 27), crenel arch (n = 25) and romanesque arch (n = 43). The three groups were compared with D1/AOA, D2/AOA, D3/AOA, D4/AOA, D5/AOA, and AAO-DAO angle, TAO-DAO angle, and aortic arch height to width ratio (A/T). Computational fluid dynamics was applied to assess hemodynamic changes in children with gothic arches. Results: There were no significant differences between D1/AOA and D2/AOA among gothic arch, crenel arch, and romanesque arch (P > 0.05). The differences in D3/AOA, D4/AOA, and D5/AOA among the three groups were statistically significant (P < 0.05), D4/AOA, D5/AOA of the gothic arch group were smaller than the crenel arch group, and the D3/AOA and D5/AOA of the gothic arch group were smaller than the romanesque arch group (P < 0.05). The difference in AAO-DAO angle among the three groups was statistically significant (P < 0.05), and the AAO-DAO angle of gothic arch was smaller than that of romanesque arch and crenel arch group (P < 0.05). There was no significant difference in the TAO-DAO angle between the three groups (P > 0.05). The difference in A/T values among the three groups was statistically significant (P < 0.05), and the A/T values: gothic arch > romanesque arch > crenel arch (P < 0.05). The CFD calculation of children with gothic arch showed that the pressure drop between the distal stenosis and the descending aorta was 58 mmHg, and the flow rate at the isthmus and descending aorta was high and turbulent. Conclusion: Gothic aortic arch is common in CoA, it may put adverse effects on the development of the aortic isthmus and descending aorta, and its A/T value and AAO-DAO angle are high. CFD could assess hemodynamic changes in CoA.

Correlations between contrast-enhanced CT-measured extracellular volume fraction, histopathological features, and MYCN amplification status in abdominal neuroblastoma: a retrospective study.

PURPOSE: To retrospectively investigate the correlations between contrast-enhanced CT (CECT)-measured extracellular volume fraction (fECV) and histopathological features, as well as MYCN amplification status, in abdominal neuroblastoma. MATERIALS AND METHODS: One hundred and forty-one patients with abdominal neuroblastoma who underwent CECT scanning were retrospectively enrolled. Calculation of fECV involved the measurement of CT values within regions of interest located within the neuroblastoma and aorta on both non-contrast-enhanced CT and equilibrium CECT. The correlations between fECV and various factors, including pathological subtype, mitosis karyorrhexis index (MKI), Shimada classification, MYCN amplification status, International Neuroblastoma Risk Group (INRG) stage, and risk group were analyzed using either the Mann-Whitney U test or Kruskal-Wallis test. RESULTS: Neuroblastoma and ganglioneuroblastoma exhibited fECV values of 0.349 (0.252, 0.424) and 0.438 (0.327, 0.508), respectively, indicating a statistically significant difference (Z = 2.200, P = 0.028). Additionally, the fECV decreased significantly in neuroblastoma with high MKI (H = 8.314, P = 0.016) or unfavorable histology (Z = 3.880, P < 0.001), as well as in those with MYCN amplification (Z = 5.486, P < 0.001). Notably, a significant variation in fECV was observed among different INRG stages (H = 16.881, P <0.001) and risk groups (H = 29.014, P < 0.001). CONCLUSION: CECT-derived fECV is associated with histopathological features, MYCN amplification status, INRG stage, and risk stratification of abdominal neuroblastoma, reflecting a potential correlation between the extracellular matrix and the biological behavior of neuroblastoma.

Risk factors for recurrence after surgical repair of coarctation of the aorta in children: a single-center experience based on 51 children.

Background: Coarctation of the aorta (CoA), is a congenital malformation, often combined with several cardiac abnormalities. At present, the operation effect is satisfactory, but postoperative restenosis is still a matter. Identification of risk factors for restenosis and prompt therapy adjustments may improve patient outcomes. Materials and methods: A retrospective clinical study of patients under 12 who had CoA repair in 2012-2021, with a randomized cohort population of 475 patients. Results: A total of 51 patients (M/F: 30/21) with a mean age of 5.33 (2.00-15.00) months and a median weight of 5.60 (4.20-10.00) kg. The mean follow-up was 8.93 (3.77-19.37) months. Patients were divided into 2 groups: no-restenosis (n-reCoA) (G1, 38 patients) and restenosis (reCoA) (G2, 13 patients). ReCoA was defined as a restenosis requiring interventional or surgery or a pressure gradient >20 mmHg at the repair site as reported by B-ultrasound with the presence of an upper and lower limb blood pressure gradient or growing dysplasia. The overall reCoA incidence was 25% (13/51). In multivariate COX regression, smaller preoperative z-score of the ascending aorta (P = 0.009, HR = 0.68) and transverse aortic arch (P = 0.015, HR = 0.66), arm-leg systolic pressure gradient ≥12.5 mmHg at discharge (P = 0.003, HR = 1.09) were independent risk factors for reCoA. Conclusion: The overall outcome of CoA surgery is successful. Smaller preoperative z-score of the ascending aorta and transverse aortic arch, and an arm-leg systolic pressure gradient ≥12.5 mmHg at discharge increase reCoA risk, and closer follow-up for such patients are required especially within 1 postoperative year.

Research and application of intelligent image processing technology in the auxiliary diagnosis of aortic coarctation.

Objective: To explore the application of the proposed intelligent image processing method in the diagnosis of aortic coarctation computed tomography angiography (CTA) and to clarify its value in the diagnosis of aortic coarctation based on the diagnosis results. Methods: Fifty-three children with coarctation of the aorta (CoA) and forty children without CoA were selected to constitute the study population. CTA was performed on all subjects. The minimum diameters of the ascending aorta, proximal arch, distal arch, isthmus, and descending aorta were measured using manual and intelligent methods, respectively. The Wilcoxon signed-rank test was used to analyze the differences between the two measurements. The surgical diagnosis results were used as the gold standard, and the diagnostic results obtained by the two measurement methods were compared with the gold standard to quantitatively evaluate the diagnostic results of CoA by the two measurement methods. The Kappa test was used to analyze the consistency of intelligence diagnosis results with the gold standard. Results: Whether people have CoA or not, there was a significant difference (p < 0.05) in the measurements of the minimum diameter at most sites using the two methods. However, close final diagnoses were made using the intelligent method and the manual. Meanwhile, the intelligent measurement method obtained higher accuracy, specificity, and AUC (area under the curve) compared to manual measurement in diagnosing CoA based on Karl's classification (accuracy = 0.95, specificity = 0.9, and AUC = 0.94). Furthermore, the diagnostic results of the intelligence method applied to the three criteria agreed well with the gold standard (all kappa ≥ 0.8). The results of the comparative analysis showed that Karl's classification had the best diagnostic effect on CoA. Conclusion: The proposed intelligent method based on image processing can be successfully applied to assist in the diagnosis of CoA.

Whole-tumor radiomics analysis of T2-weighted imaging in differentiating neuroblastoma from ganglioneuroblastoma/ganglioneuroma in children: an exploratory study.

PURPOSE: To examine the potential of whole-tumor radiomics analysis of T2-weighted imaging (T2WI) in differentiating neuroblastoma (NB) from ganglioneuroblastoma/ganglioneuroma (GNB/GN) in children. MATERIALS AND METHODS: This study included 102 children with peripheral neuroblastic tumors, comprising 47 NB patients and 55 GNB/GN patients, which were randomly divided into a training group (n = 72) and a test group (n = 30). Radiomics features were extracted from T2WI images, and feature dimensionality reduction was applied. Linear discriminant analysis was used to construct radiomics models, and one-standard error role combined with leave-one-out cross-validation was used to choose the optimal radiomics model with the least predictive error. Subsequently, the patient age at initial diagnosis and the selected radiomics features were incorporated to construct a combined model. The receiver operator characteristic (ROC) curve, decision curve analysis (DCA) and clinical impact curve (CIC) were applied to evaluate the diagnostic performance and clinical utility of the models. RESULTS: Fifteen radiomics features were eventually chosen to construct the optimal radiomics model. The area under the curve (AUC) of the radiomics model in the training group and test group was 0.940 [95% confidence interval (CI) 0.886, 0.995] and 0.799 (95%CI 0.632, 0.966), respectively. The combined model, which incorporated patient age and radiomics features, achieved an AUC of 0.963 (95%CI 0.925, 1.000) in the training group and 0.871 (95%CI 0.744, 0.997) in the test group. DCA and CIC demonstrated that the radiomics model and combined model could provide benefits at various thresholds, with the combined model being superior to the radiomics model. CONCLUSION: Radiomics features derived from T2WI, in combination with the age of the patient at initial diagnosis, may offer a quantitative method for distinguishing NB from GNB/GN, thus aiding in the pathological differentiation of peripheral neuroblastic tumors in children.

Contrast-enhanced computed tomography radiomics in predicting primary site response to neoadjuvant chemotherapy in high-risk neuroblastoma.

PURPOSE: To explore the clinical value of contrast-enhanced computed tomography (CECT) radiomics in predicting primary site response to neoadjuvant chemotherapy in high-risk neuroblastoma. MATERIALS AND METHODS: Seventy patients were retrospectively included and separated into very good partial response (VGPR) group and non-VGPR group according to the changes in primary tumor volume. The clinical features with statistical difference between the two groups were used to construct the clinical models using a logistic regression (LR) algorithm. The radiomics models based on different radiomics features selected by Kruskal-Wallis (KW) test and recursive feature elimination (RFE) were established using support vector machine (SVM) and LR algorithms. The radiomics score (Radscore) and clinical features were integrated into the combined models. Leave-one-out cross-validation (LOOCV) was used to validate the predictive performance of models in the entire dataset. RESULTS: The optimal clinical model achieved an area under the curve (AUC) of 0.767 [95% confidence interval (CI): 0.638, 0.896] and an accuracy of 0.771 after LOOCV. The AUCs of the best KW + SVM, KW + LR, RFE + SVM, and RFE + LR radiomics models were 0.816, 0.826, 0.853, and 0.850, respectively, and the corresponding AUCs after LOOCV were 0.780, 0.785, 0.755, and 0.772, respectively. The AUC and accuracy after LOOCV of the optimal combined model was 0.804 (95% CI: 0.694, 0.915) and 0.814, respectively. The Delong test showed a statistical difference in predictive performance between the optimal clinical and combined models after LOOCV (Z = 2.003, P = 0.045). The decision curve analysis showed that the combined model performs better than the clinical model. CONCLUSION: The CECT radiomics models have a favorable predictive performance in predicting VGPR of high-risk neuroblastoma to neoadjuvant chemotherapy. When integrating radiomics features and clinical features, the predictive performance of the combined models can be further improved.

Correlations Between Preoperative Radiographic Vascular Involvement of Abdominal/Pelvic Neuroblastomas on Computed Tomography and Intraoperative Vascular Injuries: Experience From a Tertiary Children's Hospital.

RATIONALE AND OBJECTIVES: This research examines the prevalence and occurrence of intraoperative vascular injuries in abdominal or pelvic neuroblastomas. It also investigates the correlations between preoperative radiographic vascular involvement on computed tomography (CT) and intraoperative vascular injuries in abdominal or pelvic neuroblastomas. MATERIALS AND METHODS: This study enrolled 297 patients with abdominal or pelvic neuroblastomas. The relationships between neuroblastomas and adjacent arteries on preoperative CT were categorized as no contact, contact (less than 50% of vessel circumference involved), partial encasement (less than 100% of vessel circumference involved), and total encasement (100% of vessel circumference involved). Similarly, the relationships between neuroblastomas and adjacent veins on preoperative CT were categorized as no compression, flattened with a visible lumen, and flattened with an invisible lumen. Furthermore, the correlations between preoperative radiographic vascular involvement of neuroblastomas and intraoperative vascular injuries were analyzed. RESULTS: A total of 61 patients had intraoperative vascular injuries, among which 76 vessels suffered injuries. Venous injuries (66/76, 86.84%) were more common than arterial injuries (10/76, 13.16%). Moreover, venous injuries frequently occurred in the inferior vena cava (32/66, 48.48%), renal veins (19/66, 28.79%), and iliac veins (8/66, 12.12%). All the injured arteries exhibited a total encasement on preoperative CT, and no injury occurred when the arteries were contacted or partially encased. In total, 87.88% (58/66) of injured veins were flattened with a visible lumen on preoperative CT, whereas only 12.12% (8/66) of the injured veins were flattened with an invisible lumen. CONCLUSION: Intraoperative injuries to veins occur more frequently than that to arteries in abdominal or pelvic neuroblastomas. Importantly, intraoperative injuries to veins may occur even if the veins are flattened with a visible lumen.