Pulmonary nodules are frequently detected in patients with and without malignancy. While small pulmonary nodules detected in patients without malignancy are typically of little clinical significance, small pulmonary nodules in children with malignancy are clinically relevant as possible metastatic foci. As the lung is one of the most common sites of metastatic disease, the accurate detection of nodules is crucial for correct staging and therapy optimization. While the detection and characterization of pulmonary nodules is essential in pediatric cancer patients, this task can be challenging and time-consuming for radiologists to perform, in part due to the small size of some metastatic foci. Computer-aided detection systems and deep learning algorithms have been shown to improve sensitivity for nodule detection in adult patients, and recent research has investigated the use of these applications in children. This educational exhibit aims to provide a comprehensive review of the literature surrounding pediatric pulmonary nodules, summarizing the current state of knowledge and future directions for research. Read More

Meeting name: SPR 2025 Annual Meeting , 2025

Authors: Tanimoto Aki, Trout Andrew, Dillman Jonathan, Hardie Russell

Keywords: Pulmonary, Nodules, Computer-Aided Diagnosis

Children undergoing hematopoietic stem cell transplantation (HSCT) are at high risk for infectious and non-infectious complications after transplant. While computed tomography (CT) is commonly used to identify asymptomatic infections or other abnormalities before transplant, there are limited data to support routine pre-transplant imaging with CT. We aimed to investigate the frequency of CT findings of infection, air trapping, or other unexpected abnormalities pre-HSCT. Read More

Meeting name: SPR 2025 Annual Meeting , 2025

Authors: Obermark Tyler, Debnath Pradipta, Trout Andrew, Ayyala Rama, Myers Kasiani, Tanimoto Aki, Danzinger-isakov Lara, Otto William, Morin Cara

Keywords: Oncology, Bronchiolitis Obliterans, Chest Radiographs

Qualitative scores of parenchymal disease severity from 3D lung MRI predict clinical outcomes such as duration of respiratory support in infants with BPD. However, current methods suffer from low signal-to-noise ratio (SNR) and motion-related blurring, reducing interpretability and diagnostic confidence. The inherently quiet zero echo time (ZTE) MRI with deep learning reconstruction (DLR) may improve diagnostic reliability but has not been evaluated in infants. This study assessed the feasibility of ZTE MRI and image quality improvements with DLR in infants with BPD. Read More

Meeting name: IPR 2026 Congress , 2026

Authors: Munidasa Samal, Bates Alister, Kingma Paul, Hysinger Erik, Woods Jason, Willmering Matthew, Muslu Yavuz, De Arcos Jose, Morin Cara, Kocaoglu Murat, Fleck Robert, Pednekar Amol, Tanimoto Aki, Higano Nara

Keywords: Neonatal, Deep Learning, Pulmonary