Validating the Utility of Super-Resolution for Downstream Tasks in Periapical Films

View Full Paper

Ask AI

Bookmark

Share

Key Points

Evaluate the effectiveness of a deep-learning super-resolution framework to enhance diagnostic accuracy of periapical films.
Established a clinical evaluation pipeline with 6283 periapical films.
Used 5998 images for training an AI restoration model and validated with 285 annotated clinical images.
Compared diagnostic performance between original low-resolution and super-resolution enhanced images.
Super-resolution improved mean intersection over union (IoU) from 55.17% to 60.24% (P < .0001).
Boundary precision increased from 23.64% to 48.22% (P < .0001).
Detection recall improved by 4.24% (P = .0121), with a modest increase in mean Average Precision (mAP@50) from 67.18% to 69.30% (P = .1114).

We only have this paper's title and publication details.

Evaluates improved diagnostic performance in periapical films using super-resolution techniques, suggesting substantial clinical benefits.

No takes yet. Share an insight, caveat, or question.

Peng et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share