Dual-Channel Near-Infrared Autofluorescence Imaging and AI Analysis to Locate Parathyroid Glands (PTFinder)

Condition(s) studied

Investigational drug(s) / intervention(s)

PTFinder Dual-Channel NIR Autofluorescence Imaging System: Ex vivo, non-contact imaging of resected thyroid/parathyroid specimens; captures near-infrared autofluorescence and overlays it on white-light video to highlight parathyroid glands (2-5 min per specimen).

Offline Machine-Learning Algorithm (PTFinder-AI Beta): training/validation on de-identified NIR/RGB frames.

Study summary

This study tests PTFinder, a dual-camera system that makes parathyroid glands glow on screen by capturing their natural near-infrared autofluorescence. After a thyroid or parathyroid operation, the removed tissue is scanned with PTFinder and then checked again under normal white light. We will measure how fast (seconds) and how accurately the device finds real glands, confirmed by frozen pathology or a rapid PTH strip. About 180 adult patients at three Chinese hospitals will join. The imaging adds only a few minutes and does not change any part of the surgery. We will also record blood calcium and PTH at 1 h, 24 h, and 7 d after surgery to see whether better gland recovery lowers low-calcium risk.Collected images will also be used to train and test a deep-learning model for fully automated parathyroid recognition; model performance metrics constitute secondary outcomes.

Eligibility

Primary outcome measure(s)

• Detection Rate of Pathology-Confirmed Parathyroid Glands per Specimen (PTFinder) — Intra-operative imaging session (0-5 minutes)
  Proportion of parathyroid glands correctly located by PTFinder divided by the total number of glands confirmed on frozen section or rapid PTH strip. Unit = % (higher = better).

Trial sites (1)

Other trials for the same condition