Exploring near-infrared autofluorescence properties in parathyroid tissue: an analysis of fresh and paraffin-embedded thyroidectomy specimens.

Significance: Near-infrared autofluorescence (NIRAF) utilizes the natural autofluorescence of parathyroid glands (PGs) to improve their identification during thyroid surgeries, reducing the risk of inadvertent removal and subsequent complications such as hypoparathyroidism. This study evaluates NIRAF's effectiveness in real-world surgical settings, highlighting its potential to enhance surgical outcomes and patient safety. Aim: We evaluate the effectiveness of NIRAF in detecting PGs during thyroidectomy and central neck dissection and investigate autofluorescence characteristics in both fresh and paraffin-embedded tissues. Approach: We included 101 patients diagnosed with papillary thyroid cancer who underwent surgeries in 2022 and 2023. We assessed NIRAF's ability to locate PGs, confirmed via parathyroid hormone assays, and involved both junior and senior surgeons. We measured the accuracy, speed, and agreement levels of each method and analyzed autofluorescence persistence and variation over 10 years, alongside the expression of calcium-sensing receptor (CaSR) and vitamin D. Results: NIRAF demonstrated a sensitivity of 89.5% and a negative predictive value of 89.1%. However, its specificity and positive predictive value (PPV) were 61.2% and 62.3%, respectively, which are considered lower. The kappa statistic indicated moderate to substantial agreement (kappa = 0.478; P < 0.001 ). Senior surgeons achieved high specificity (86.2%) and PPV (85.3%), with substantial agreement (kappa = 0.847; P < 0.001 ). In contrast, junior surgeons displayed the lowest kappa statistic among the groups, indicating minimal agreement (kappa = 0.381; P < 0.001 ). Common errors in NIRAF included interference from brown fat and eschar. In addition, paraffin-embedded samples retained stable autofluorescence over 10 years, showing no significant correlation with CaSR and vitamin D levels. Conclusions: NIRAF is useful for PG identification in thyroid and neck surgeries, enhancing efficiency and reducing inadvertent PG removals. The stability of autofluorescence in paraffin samples suggests its long-term viability, with false positives providing insights for further improvements in NIRAF technology.

Intraoperative AI-assisted early prediction of parathyroid and ischemia alert in endoscopic thyroid surgery.

BACKGROUND: The preservation of parathyroid glands is crucial in endoscopic thyroid surgery to prevent hypocalcemia and related complications. However, current methods for identifying and protecting these glands have limitations. We propose a novel technique that has the potential to improve the safety and efficacy of endoscopic thyroid surgery. PURPOSE: Our study aims to develop a deep learning model called PTAIR 2.0 (Parathyroid gland Artificial Intelligence Recognition) to enhance parathyroid gland recognition during endoscopic thyroidectomy. We compare its performance against traditional surgeon-based identification methods. MATERIALS AND METHODS: Parathyroid tissues were annotated in 32 428 images extracted from 838 endoscopic thyroidectomy videos, forming the internal training cohort. An external validation cohort comprised 54 full-length videos. Six candidate algorithms were evaluated to select the optimal one. We assessed the model's performance in terms of initial recognition time, identification duration, and recognition rate and compared it with the performance of surgeons. RESULTS: Utilizing the YOLOX algorithm, we developed PTAIR 2.0, which demonstrated superior performance with an AP50 score of 92.1%. The YOLOX algorithm achieved a frame rate of 25.14 Hz, meeting real-time requirements. In the internal training cohort, PTAIR 2.0 achieved AP50 values of 94.1%, 98.9%, and 92.1% for parathyroid gland early prediction, identification, and ischemia alert, respectively. Additionally, in the external validation cohort, PTAIR outperformed both junior and senior surgeons in identifying and tracking parathyroid glands (p < 0.001). CONCLUSION: The AI-driven PTAIR 2.0 model significantly outperforms both senior and junior surgeons in parathyroid gland identification and ischemia alert during endoscopic thyroid surgery, offering potential for enhanced surgical precision and patient outcomes.