A co-axial excitation, dual-RGB/NIR paired imaging system toward computer-aided detection (CAD) of parathyroid glands in situ and ex vivo

• Published in: Journal of biophotonics Vol. 15; no. 8; p. e202200008
• Main Authors: Kim, Yoseph, Lee, Hun Chan, Kim, Jongchan, Oh, Eugene, Yoo, Jennifer, Ning, Bo, Lee, Seung Yup, Ali, Khalid Mohamed, Tufano, Ralph P., Russell, Jonathon O., Cha, Jaepyeong
• Format: Journal Article
• Language: English
• Published: 20.04.2022
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.202200008

Early and precise detection of parathyroid glands (PGs) is a challenging problem in thyroidectomy due to their small size and similar appearance to surrounding tissues. Near-infrared autofluorescence (NIRAF) has stimulated interest as a method to localize PGs. However, high incidence of false positives for PGs has been reported with this technique. We introduce a prototype equipped with a coaxial excitation light (785-nm) and a dual-sensor to address the issue of false positives with the NIRAF technique. We test the clinical feasibility of our prototype in situ and ex vivo using sterile drapes on 10 human subjects. Video data (1,287 images) of detected PGs were collected to train, validate, and compare the performance for PG detection. We achieved a mean average precision of 94.7% and a 19.5-millisecond processing time/detection. This feasibility study supports the effectiveness of the optical design and may open new doors for a deep learning-based PG detection method. This paper shows the preliminary feasibility of a co-axial excitation, dual-red-green-blue (RGB)/near-infrared (NIR) paired imaging system that detects autofluorescence signals from parathyroid glands intraoperatively and exploits computer-aided algorithms to localize them post-hoc. The aim of the study was to explore the potential of addressing false negative/positive issues from current NIR technology. Our machine learning algorithm was tested on real-time data from 6 thyroid/parathyroidectomy patients and achieved a mean average precision of 94.7% and a 19.5 millisecond processing time per detection.