Abstract
AI-basedlungcancerscreeningisconstrainedbyscarce,annotated CT data, particularly for rare nodule presentations. We investigate whether physics-based, anatomy-informed simulated CT can improveAIperformanceacrossthreelung-noduletasks:detection,segmentation, and malignancy classification. Using the Virtual Lung Screening Trial framework, we generated 174 digital human twins (XCAT3), embedded 512 procedurally controlled nodules (X-Lesions, 4–30 mm), andsimulatedCT(DukeSim)undertwoscannerconfigurations,yielding 1,044annotatedscans.Combinedwithclinicaldata,thesetrainedmodels fordetection(MONAI),segmentation(VISTA3D,nnU-Net),andclassification (Med3D), evaluated on external test sets. Detection sensitivity at1FP/scanrosefrom0.37to0.56(p<0.001);segmentationimproved modestly(Dice0.61→0.64,0.66→0.69);classificationAUCrosefrom0.78 to0.87(p<0.001).Physics-basedvirtualimagingtrialscanhelpaddress data scarcity in medical AI.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_052.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=vSCOpa00Sx
BibTex
@InProceedings{TusFak_Virtual_MICCAISAT2026,
author = { Tushar, Fakrul Islam AND Dahal, Lavsen AND Segars, Paul AND Lo, Joseph Y.},
title = { { Virtual Patients, Real Gains: Simulated CT from Digital Twins for Multi-Task Lung Nodule Analysis } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17258},
month = {pending},
page = {pending}
}