Deep Learning May Help Surgeons Spot Diseased Parathyroid Glands

Akgun E, Ibrahimli A, Berber E. Near-Infrared Autofluorescence Signature: A New Parameter for Intraoperative Assessment of Parathyroid Glands in Primary Hyperparathyroidism. J Am Coll Surg. January 2025.

The success of parathyroidectomy in primary hyperparathyroidism depends on intraoperative differentiation of diseased from normal glands. Deep learning may help standardize this subjective assessment, which relies heavily on surgeon expertise. 

The researchers investigated whether diseased and normal parathyroid glands have different near-infrared autofluorescence (NIRAF) signatures and whether deep learning models can differentiate between them based on intraoperative in vivo images.

This prospective study included patients who underwent parathyroidectomy for primary hyperparathyroidism or thyroidectomy using intraoperative NIRAF imaging at a single tertiary referral center from November 2019 to March 2024. Autofluorescence intensity and heterogeneity were compared between normal and diseased glands, and a deep learning model was developed.

NIRAF images of 1,506 normal and 597 diseased parathyroid glands from 797 patients were analyzed. Normal glands, compared with diseased glands, exhibited a higher median normalized NIRAF intensity (2.68 [2.19 to 3.23] vs 2.09 [1.68 to 2.56] pixels, p < 0.0001) and lower heterogeneity index (0.11 [0.08 to 0.15] vs 0.18 [0.13 to 0.23], p < 0.0001). The deep learning model achieved precision and recall of 83.3% each, with an area under the precision-recall curve of 0.908.

Normal and diseased parathyroid glands in primary hyperparathyroidism demonstrated different intraoperative NIRAF patterns that were quantified using intensity and heterogeneity analyses. Visual deep learning models relying on these Deep learning models using these signatures could help surgeons differentiate normal from diseased parathyroid glands.