Deep Learning Quality Control for RECIST-Oriented Assessment: A Vision Transformer Predicts Inter-Reader Variability of Unidimensional Lesion Measurements on Contrast CT.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY 10065, USA.
- Department of Radiation Oncology, William Beaumont University Hospital-Corewell Health, 3601 W 13 Mile Rd, Royal Oak, MI 48084, USA.
- The D-Lab, Department of Precision Medicine, GROW-Research Institute for Oncology and Reproduction, Maastricht University, Universiteitsingel 40, 6229 ER Maastricht, The Netherlands.
- Department of Medicine, College of Medicine, University of Arizona-Tucson, 1501 N Campbell Ave, Tucson, AZ 85724, USA.
- School of Medicine, New York Medical College, 40 Sunshine Cottage Rd, Valhalla, NY 10595, USA.
Abstract
<b>Background/Objectives:</b> Inter-reader variation can alter unidimensional tumor measurements used in RECIST-oriented response assessment. Unlike systems that automate segmentation or target selection, this study aimed to predict lesion-specific measurement uncertainty itself. <b>Methods:</b> The development cohort comprised 463 lung, liver, and lymph-node lesions from 280 patients in Vol-PACT, with four segmentations per lesion. Inter-reader variability was defined as (maximum longest diameter-minimum longest diameter)/minimum longest diameter. A Swin Transformer was trained to regress this continuous score. A value > 0.20 was used as a pragmatic high-variability alert threshold, with high variability designated as the positive class; this threshold is not equivalent to RECIST progressive disease. Preliminary external evaluation used 21 NSCLC lesions with five reader contours, providing one reader mask at a time. <b>Results:</b> The validation and internal test AUCs were 0.74 (95% CI, 0.61-0.85) and 0.89 (95% CI, 0.80-0.95), respectively. On the internal test set, MAE was 0.10 (95% CI, 0.08-0.12), accuracy was 82% (95% CI, 74-90%), sensitivity 72% (95% CI, 59-85%), and specificity for lower-variability lesions was 92% (95% CI, 82-100%). Across the five external readers, AUCs ranged from 0.77 to 0.92; the wide confidence intervals reflect the small external sample. <b>Conclusions:</b> This proof-of-concept model may provide a measurement-quality signal that supports target selection or adjudication. Larger multi-institutional studies, patient-level resampling, calibration, ablation testing, and workflow validation are required before clinical use.