During thyroid surgery, parathyroid glands may be accidentally extracted due to their similar shapes and colors to the surrounding tissues (lymph nodes, fat, and thyroid tissue). In order to avoid damaging or resecting vulnerable glands, we aim to assist surgeons to better identify the parathyroids with real-time bounding boxes on a screen available in operating rooms. Parathyroids are auto fluorescent when excited with near infrared (NIR) light; therefore, videos recorded simultaneously in NIR, and RGB color formats can be used to train a deep learning model for robust object detection and localization without the need for expert annotation. The use of NIR images facilitates the generation of the ground truth dataset. We collected 16 patients' videos during total thyroidectomy. The videos were initially decomposed into a series of images taken at every 10 frames. From this, an intensity threshold was applied on the NIR images creating newer images where the parathyroid can be easily selected. Using these images, ground truth bounding boxes were generated. Our ground truth database size was over 600 images, of which 540 images contained parathyroid glands and 66 did not. We ran Faster R-CNN twice, initially to perform localization using the images with parathyroids only. The second method was to perform classification using the entire dataset. For the first method, we achieved an average intersection over union of 85% and for second, we obtained a precision of 98% and a recall of 100%. Given the limited dataset we are very excited with these results.
KEYWORDS: RGB color model, Data modeling, Performance modeling, Surgery, Near infrared, Computer-aided diagnosis, Computer aided diagnosis and therapy, Imaging systems, Visual process modeling
Parathyroid glands (PGs), small endocrine glands in the neck, control calcium levels in the body and are crucial to maintaining homeostasis. Accidental removal of or direct damage to healthy parathyroid glands during thyroid surgery may occur due to its small size and similar appearance to surrounding anatomical structures, potentially leading to postoperative hypocalcemia. Thus precise and quick detection of normal parathyroid glands in real-time during surgery can improve the surgical outcome. In this study, we introduce a deep learning system (YOLOv5) based on dual RGB/NIR imaging for Computer-aided detection (CADe) of PG with high accuracy. This model can effectively detect parathyroid glands in real-time as it also includes the confidence level, which can help surgeons make decisions. We tested a computer-aided detection (CADe) using the co-registered RGB/NIR camera and ex-vivo thyroid tissue specimen. The average precisions of models were significantly higher when trained by the dual-RGB/NIR (0.99) data than NIR (0.94) and RGB (0.96) data alone at a high confidence threshold (0.7). The proposed CADe may increase the parathyroid detection rates clinically.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.