Purpose or Case Report: 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.
Methods & Materials: With the assistance of a librarian, we performed a systematic literature search concerning pediatric pulmonary nodules and pulmonary nodule detection using AI and computer-aided detection systems. Review of this literature will form the basis for this educational exhibit.
Results: We will discuss commonly encountered benign and malignant nodules in the pediatric population. We will describe imaging features of pulmonary nodules on CT, including relevance of nodule size, margins, and internal characteristics. Additionally, we will explore our current state of knowledge regarding the use of computer-aided detection systems and AI for the detection and characterization of pediatric pulmonary nodules.
Conclusions: Small pulmonary nodules potentially carry greater importance in children. The arduous and essential task of pulmonary nodule detection may someday be improved with the application of appropriately trained computer-aided detection systems/AI.