LightRefine-PCXR: A Lightweight Refinement Framework for Efficient Medical Device Suppression in Pediatric Chest X-Rays

Mingze Jiang, Xueyang Li, John Kheir, Alec Girten, Yiyu Shi
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1598-1617, 2026.

Abstract

In pediatric chest radiography, indwelling support devices (e.g., tubes and lines) are ubiquitous and often obscure critical thoracic structures, complicating radiologic interpretation and reducing the reliability of automated analysis methods. Although generative inpainting has advanced rapidly, reliable deployment in pediatric chest radiographs remains challenging. Subtle anatomical cues must be preserved under substantial domain shift, while full adaptation of large backbones is often impractical because of limited pediatric data and constrained clinical compute budgets. To address these limitations, we propose LightRefine-PCXR, a lightweight, backbone-agnostic refinement framework for suppressing medical devices in pediatric chest X-rays (PCXRs). LightRefine-PCXR follows a two-stage strategy: a frozen pretrained inpainting backbone first produces a coarse device-removed estimate, and a compact anatomy-aware refiner then predicts mask-constrained residual corrections to restore local structures while preserving all unmasked pixels exactly. This plug-in design substantially reduces trainable parameters and peak GPU memory compared with end-to-end fine-tuning, yet consistently improves reconstruction fidelity and perceptual quality across diverse inpainting paradigms, including CNN-, transformer-, and diffusion-based models. Comprehensive in-domain and cross-dataset experiments demonstrate robust device suppression and strong generalization in low-data pediatric settings, highlighting the practicality of LightRefine-PCXR for real-world pediatric radiology workflows.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-jiang26a, title = {LightRefine-PCXR: A Lightweight Refinement Framework for Efficient Medical Device Suppression in Pediatric Chest X-Rays}, author = {Jiang, Mingze and Li, Xueyang and Kheir, John and Girten, Alec and Shi, Yiyu}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1598--1617}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/jiang26a/jiang26a.pdf}, url = {https://proceedings.mlr.press/v315/jiang26a.html}, abstract = {In pediatric chest radiography, indwelling support devices (e.g., tubes and lines) are ubiquitous and often obscure critical thoracic structures, complicating radiologic interpretation and reducing the reliability of automated analysis methods. Although generative inpainting has advanced rapidly, reliable deployment in pediatric chest radiographs remains challenging. Subtle anatomical cues must be preserved under substantial domain shift, while full adaptation of large backbones is often impractical because of limited pediatric data and constrained clinical compute budgets. To address these limitations, we propose LightRefine-PCXR, a lightweight, backbone-agnostic refinement framework for suppressing medical devices in pediatric chest X-rays (PCXRs). LightRefine-PCXR follows a two-stage strategy: a frozen pretrained inpainting backbone first produces a coarse device-removed estimate, and a compact anatomy-aware refiner then predicts mask-constrained residual corrections to restore local structures while preserving all unmasked pixels exactly. This plug-in design substantially reduces trainable parameters and peak GPU memory compared with end-to-end fine-tuning, yet consistently improves reconstruction fidelity and perceptual quality across diverse inpainting paradigms, including CNN-, transformer-, and diffusion-based models. Comprehensive in-domain and cross-dataset experiments demonstrate robust device suppression and strong generalization in low-data pediatric settings, highlighting the practicality of LightRefine-PCXR for real-world pediatric radiology workflows.} }
Endnote
%0 Conference Paper %T LightRefine-PCXR: A Lightweight Refinement Framework for Efficient Medical Device Suppression in Pediatric Chest X-Rays %A Mingze Jiang %A Xueyang Li %A John Kheir %A Alec Girten %A Yiyu Shi %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-jiang26a %I PMLR %P 1598--1617 %U https://proceedings.mlr.press/v315/jiang26a.html %V 315 %X In pediatric chest radiography, indwelling support devices (e.g., tubes and lines) are ubiquitous and often obscure critical thoracic structures, complicating radiologic interpretation and reducing the reliability of automated analysis methods. Although generative inpainting has advanced rapidly, reliable deployment in pediatric chest radiographs remains challenging. Subtle anatomical cues must be preserved under substantial domain shift, while full adaptation of large backbones is often impractical because of limited pediatric data and constrained clinical compute budgets. To address these limitations, we propose LightRefine-PCXR, a lightweight, backbone-agnostic refinement framework for suppressing medical devices in pediatric chest X-rays (PCXRs). LightRefine-PCXR follows a two-stage strategy: a frozen pretrained inpainting backbone first produces a coarse device-removed estimate, and a compact anatomy-aware refiner then predicts mask-constrained residual corrections to restore local structures while preserving all unmasked pixels exactly. This plug-in design substantially reduces trainable parameters and peak GPU memory compared with end-to-end fine-tuning, yet consistently improves reconstruction fidelity and perceptual quality across diverse inpainting paradigms, including CNN-, transformer-, and diffusion-based models. Comprehensive in-domain and cross-dataset experiments demonstrate robust device suppression and strong generalization in low-data pediatric settings, highlighting the practicality of LightRefine-PCXR for real-world pediatric radiology workflows.
APA
Jiang, M., Li, X., Kheir, J., Girten, A. & Shi, Y.. (2026). LightRefine-PCXR: A Lightweight Refinement Framework for Efficient Medical Device Suppression in Pediatric Chest X-Rays. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1598-1617 Available from https://proceedings.mlr.press/v315/jiang26a.html.

Related Material