Critical retained foreign objects (RFOs) on intraoperative chest radiographs are rare but high-risk events. Their scarcity limits robust automated detection model training and generalization. We introduce SurgRFO, a two-stage synthesis framework for generating realistic RFO-present intraoperative chest X-rays. In Stage 1, a Roentgen chest X-ray foundation model is fine-tuned on surgical-domain images to generate realistic RFO-free backgrounds that preserve anatomy, indwelling lines and tubes, and intraoperative imaging characteristics. In Stage 2, a lightweight generator trained on localized RFO patches from limited positive cases synthesizes diverse RFO instances, which are composited onto generated backgrounds using conditional Poisson fusion to improve photometric consistency. We evaluate SurgRFO through (i) a blinded clinician study assessing realism and clinical plausibility, and (ii) downstream detection experiments in which synthesized data are used to augment Faster R-CNN, YOLOv8, and RetinaNet. SurgRFO consistently improves sensitivity at low false-positive-per-image (FPPI) operating points on internal and external test sets. Clinician ratings indicate that the synthesized images achieve realism comparable to real intraoperative images. Ablation analyses further examine fusion strategies and synthesis scale. Ethical safeguards for synthetic surgical data are also discussed.
@article{arxiv.2605.24787,
title = {SurgRFO: Foundation Model Based Compositional Synthesis of Critical Retained Foreign Objects in Intraoperative Chest X-rays},
author = {Yuanyun Hu and Yuli Wang and Noemi Acevedo Rodriguez and Ronald Yang and Wen-Chi Hsu and Siwei Luo and Zihao Bai and Jing Wu and Yuwei Dai and Shaoju Wu and Jonathon Lindquist and Justin Honce and Premal Trivedi and Zhicheng Jiao and Ihab Kamel and Elliott Haut and Pamela Johnson and John Eng and Cheng Ting Lin and Nan Su and Bo Chen and Sun Yu and Harrison Bai},
journal= {arXiv preprint arXiv:2605.24787},
year = {2026}
}