Thyroid Nodules on Ultrasound in Children and Young Adults: Comparison of Diagnostic Performance of Radiologists' Impressions, ACR TI-RADS, and a Deep Learning Algorithm.

BACKGROUND. In current clinical practice, thyroid nodules in children are generally evaluated on the basis of radiologists' overall impressions of ultrasound images. OBJECTIVE. The purpose of this article is to compare the diagnostic performance of radiologists' overall impression, the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS), and a deep learning algorithm in differentiating benign and malignant thyroid nodules on ultrasound in children and young adults. METHODS. This retrospective study included 139 patients (median age 17.5 years; 119 female patients, 20 male patients) evaluated from January 1, 2004, to September 18, 2020, who were 21 years old and younger with a thyroid nodule on ultrasound with definitive pathologic results from fine-needle aspiration and/or surgical excision to serve as the reference standard. A single nodule per patient was selected, and one transverse and one longitudinal image each of the nodules were extracted for further evaluation. Three radiologists independently characterized nodules on the basis of their overall impression (benign vs malignant) and ACR TI-RADS. A previously developed deep learning algorithm determined for each nodule a likelihood of malignancy, which was used to derive a risk level. Sensitivities and specificities for malignancy were calculated. Agreement was assessed using Cohen kappa coefficients. RESULTS. For radiologists' overall impression, sensitivity ranged from 32.1% to 75.0% (mean, 58.3%; 95% CI, 49.2-67.3%), and specificity ranged from 63.8% to 93.9% (mean, 79.9%; 95% CI, 73.8-85.7%). For ACR TI-RADS, sensitivity ranged from 82.1% to 87.5% (mean, 85.1%; 95% CI, 77.3-92.1%), and specificity ranged from 47.0% to 54.2% (mean, 50.6%; 95% CI, 41.4-59.8%). The deep learning algorithm had a sensitivity of 87.5% (95% CI, 78.3-95.5%) and specificity of 36.1% (95% CI, 25.6-46.8%). Interobserver agreement among pairwise combinations of readers, expressed as kappa, for overall impression was 0.227-0.472 and for ACR TI-RADS was 0.597-0.643. CONCLUSION. Both ACR TI-RADS and the deep learning algorithm had higher sensitivity albeit lower specificity compared with overall impressions. The deep learning algorithm had similar sensitivity but lower specificity than ACR TI-RADS. Interobserver agreement was higher for ACR TI-RADS than for overall impressions. CLINICAL IMPACT. ACR TI-RADS and the deep learning algorithm may serve as potential alternative strategies for guiding decisions to perform fine-needle aspiration of thyroid nodules in children.

Subventricular zone stem cell niche injury is associated with intestinal perforation in preterm infants and predicts future motor impairment.

Brain injury is highly associated with preterm birth. Complications of prematurity, including spontaneous or necrotizing enterocolitis (NEC)-associated intestinal perforations, are linked to lifelong neurologic impairment, yet the mechanisms are poorly understood. Early diagnosis of preterm brain injuries remains a significant challenge. Here, we identified subventricular zone echogenicity (SVE) on cranial ultrasound in preterm infants following intestinal perforations. The development of SVE was significantly associated with motor impairment at 2 years. SVE was replicated in a neonatal mouse model of intestinal perforation. Examination of the murine echogenic subventricular zone (SVZ) revealed NLRP3-inflammasome assembly in multiciliated FoxJ1+ ependymal cells and a loss of the ependymal border in this postnatal stem cell niche. These data suggest a mechanism of preterm brain injury localized to the SVZ that has not been adequately considered. Ultrasound detection of SVE may serve as an early biomarker for neurodevelopmental impairment after inflammatory disease in preterm infants.

Interhospital variability in localization techniques for small pulmonary nodules in children: A pediatric surgical oncology research collaborative study.

BACKGROUND: Pulmonary nodules that are deep within lung parenchyma and/or small in size can be challenging to localize for biopsy. This study describes current trends in performance of image-guided localization techniques for pulmonary nodules in pediatric patients. METHODS: A retrospective review was performed on patients < 21 years of age undergoing localization of pulmonary nodules at 15 institutions. Localization and resection success, time in interventional radiology (IR), operating room (OR) and total anesthesia time, complications, and technical problems were compared between techniques. RESULTS: 225 patients were included with an average of 1.3 lesions (range 1-5). Median nodule size and depth were 4 mm (range 0-30) and 5.4 mm (0-61), respectively. The most common localization techniques were: wire + methylene blue dye (MBD) (28%), MBD only (25%), wire only (14%), technetium-99 only (11%), coil + MBD (7%) and coil only (5%). Localization technique was associated with institution (p < 0.01); technique and institution were significantly associated with mean IR, OR, and anesthesia time (all p < 0.05). Comparing techniques, there was no difference in successful IR localization (range 92-100%, p = 0.75), successful resection (94-100%, p = 0.98), IR technical problems (p = 0.22), or operative complications (p = 0.16). CONCLUSIONS: Many IR localization techniques for small pulmonary nodules in children can be successful, but there is wide variability in application by institution and in procedure time. LEVEL OF EVIDENCE: Retrospective review, Level 3.