A Bayesian ordinal classifier with calibrated uncertainty thresholds is proposed for radiotherapy auto-contour QA, but the reported high accuracy is undermined by a missing majority-class baseline in a 93.1% Class 2 test set.
The CT scans from these patients had slice thickness ranging from 1.5 to 3.0 mm, resolution of 0.9 to 1.5 mm, image size of 512x512 pixels, and 90 to 290 slices per scan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AI-Assisted Decision-Making for Clinical Assessment of Auto-Segmented Contour Quality
A Bayesian ordinal classifier with calibrated uncertainty thresholds is proposed for radiotherapy auto-contour QA, but the reported high accuracy is undermined by a missing majority-class baseline in a 93.1% Class 2 test set.