Pediatric device aware chest x ray analysis aids icu monitoring
PCXR-Copilot: Device-aware pediatric chest radiographic analysis with segmentation, suppression, and edema-related cues
Computer Vision and Pattern Recognition
Summary
Children in intensive care often need many chest X-rays, but these images can be hard to read because of tubes and devices in their bodies. The authors created a special collection of 1,000 kids’ X-rays with detailed labels for the devices they carry. They then built a computer program called PCXR-Copilot that helps doctors by identifying devices, showing lung areas, and highlighting signs of fluid or swelling. This tool runs quickly in a real hospital, showing it can work in real life.
What this means in practice
- •For pediatric radiologists: Access device-aware lung and edema visualization to improve interpretation of ICU chest X-rays in children.
- •For clinical informatics teams: Deploy integrated real-time pipelines in hospital imaging platforms for enhanced pediatric ICU chest X-ray analysis.
Authors
Xueyang Li, Alec Girten, Peng Zeng, Mingze Jiang, Shaoyang Huang, Gelei Xu, Danny Z. Chen, Yiyu Shi, John N. Kheir
Abstract
Patients admitted to pediatric ICU and cardiac ICU often require intensive perioperative support and frequent chest radiography to monitor support devices, extravascular lung water, and body-wall edema. Radiographic interpretation and analysis is often difficult due to superimposed anatomic and iatrogenic structures that obscure clinically relevant signals. While deep learning can provide decision support, translation to pediatric radiographs is still limited by high device burden and scarcity of pediatric datasets with clinically grounded device annotations. To address this gap, we first introduce PediaDeviceSeg-1K, a curated dataset of 1,000 anterior-posterior radiographs of pediatric CICU patients with clinically grounded, fine-grained annotations of common ICU devices. To our best knowledge, this is the first publicly available pediatric CICU CXR resource with clinically grounded device annotations for device-focused benchmarking. Building on PediaDeviceSeg-1K, we further present PCXR-Copilot, a device-aware pipeline that outputs lung and device masks, optional device-suppressed views, and edema-related visualization maps and scalar indices. The full pipeline has been integrated and runs in real time within the TWIST platform at Boston Children's Hospital, demonstrating feasibility for real-world clinical deployment.