With an incidence of 3.25%, breast masses in the pediatric population are a relatively rare phenomenon. Despite this, breast masses are a substantial source of anxiety and concern for parents and patients alike, largely due to the increased awareness of breast cancer in the adult population. Fortunately, the vast majority of masses are benign, and pediatric breast malignancies constitute less than 1% of all pediatric malignancies. Moreover, malignancy tends to be secondary to metastatic disease from lymphoma, leukemia, or rhabdomyosarcoma, as primary breast carcinoma is exceedingly rare. Although initial sonographic characteristics of breast masses may be nonspecific, recommendation for further evaluation with biopsy and/or excision of the mass is usually not recommended due to the rarity of malignancy, and avoidance of disrupting immature breast parenchymal tissue. In adults, the Breast Imaging-Reporting and Data System classification is quite accurate for dictating management recommendations. However, this system grossly over-emphasizes the risk of malignancy in pediatric patients, as imaging findings are usually discordant with histology. Currently, there are no standardized guidelines for management recommendations of pediatric breast masses, and short-term follow-up ultrasound is usually recommended to evaluate for malignant potential. The purpose of this educational exhibit is to compare the sonographic abnormalities of breast pathologies arising from normal breast development, including but not limited to gynecomastia, mastitis, and abscesses, from those arising from neoplastic processes including fibroadenomas, hemangiomas, arterio-venous malformations, and phyllodes tumors. In addition, the current literature on management recommendations, including indications for MRI and biopsy/excision of breast masses, will be reviewed. Finally, this exhibit will discuss the important role pediatric radiologists play in understanding the epidemiology and natural history of breast pathologies, enabling accurate characterization of masses and appropriate treatment recommendations to further guide patient management. Read More

Meeting name: SPR 2019 Annual Meeting & Postgraduate Course , 2019

Authors: Saini Rimpi, Wermers Joshua, Larson Shelby, Mitchell Grace, Patel Amy

Keywords: Breast, Ultrasound, hemangioma

MRI is crucial to the diagnosis, treatment planning, and monitoring of pediatric posterior fossa tumors; recent advances in machine and deep learning offer the prospect of increased diagnostic accuracy and minimally invasive management strategies. Machine learning and deep learning represent two artificial intelligence (AI) applications of radiomics that show promising results in the identification and classification of pediatric posterior fossa tumors, such as medulloblastoma, diffuse intrinsic pontine glioma, ependymoma, and pilocytic astrocytoma, based on MRI data. Many AI models demonstrate comparable, or in some cases, better, performance than human radiologists. Beyond diagnosis, machine and deep learning algorithms have been developed for tumor histology determination, prognostication, and molecular subtyping, to name just a few examples. In its early stages, however, the technology has several barriers to overcome before mainstream use. Studies of AI algorithms are often conducted with small sample sizes due to the relative rarity of pediatric posterior fossa tumors; many are also conducted at a single institution. Algorithms are susceptible to class imbalance as well, making it more difficult to identify tumors with lower prevalence. Multi-institution studies are important in addressing those limitations, though they have their own cumbersome requirements, such as data harmonization. Deep learning training strategies, such as federated learning, data augmentation, and transfer learning, help to address the problems introduced by working with small data sets. The purpose of this exhibit is to review the methods, results, and limitations identified in studies testing the efficacy of machine and deep learning models for the identification and classification of pediatric posterior fossa tumors and to discuss their potential for use in the clinical setting. Read More

Meeting name: SPR 2024 Annual Meeting & Postgraduate Course , 2024

Authors: Randhawa Hari, Park Brandon, Khanna Praneet, Jung Daniel, Das Ayushman, Ginn Kevin, Mitchell Grace

Keywords: Artificial Intelligence, Deep Learning, Machine Learning