Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique

Jongchan Kim; Jennifer Yoo; Yoseph Kim; Eugene Oh; Bo Ning; Jonathon O. Russell; Jaepyeong Cha

doi:10.1117/12.2608939

Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique

Jongchan Kim, Jennifer Yoo, Yoseph Kim, Eugene Oh, Bo Ning, Jonathon O. Russell, Jaepyeong Cha

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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.

Original language	English (US)
Title of host publication	Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022
Editors	Brian Jet-Fei Wong, Justus F. Ilgner
Publisher	SPIE
ISBN (Electronic)	9781510647411
DOIs	https://doi.org/10.1117/12.2608939
State	Published - 2022
Event	Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022 - San Francisco, United States Duration: Jan 22 2022 → Jan 27 2022

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	11935
ISSN (Print)	1605-7422

Conference

Conference	Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022
Country/Territory	United States
City	San Francisco
Period	1/22/22 → 1/27/22

Keywords

CADe
Deep learning
Parathyroid gland identification

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Biomaterials
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2608939

Cite this

Kim, J., Yoo, J., Kim, Y., Oh, E., Ning, B., Russell, J. O., & Cha, J. (2022). Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique. In B. J.-F. Wong, & J. F. Ilgner (Eds.), Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022 Article 1193504 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11935). SPIE. https://doi.org/10.1117/12.2608939

Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique. / Kim, Jongchan; Yoo, Jennifer; Kim, Yoseph et al.
Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022. ed. / Brian Jet-Fei Wong; Justus F. Ilgner. SPIE, 2022. 1193504 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11935).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kim, J, Yoo, J, Kim, Y, Oh, E, Ning, B, Russell, JO & Cha, J 2022, Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique. in BJ-F Wong & JF Ilgner (eds), Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022., 1193504, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11935, SPIE, Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022, San Francisco, United States, 1/22/22. https://doi.org/10.1117/12.2608939

Kim J, Yoo J, Kim Y, Oh E, Ning B, Russell JO et al. Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique. In Wong BJF, Ilgner JF, editors, Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022. SPIE. 2022. 1193504. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2608939

Kim, Jongchan ; Yoo, Jennifer ; Kim, Yoseph et al. / Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique. Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022. editor / Brian Jet-Fei Wong ; Justus F. Ilgner. SPIE, 2022. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{31dbfa34a5ba460c94dd714574d43438,

title = "Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique",

abstract = "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.",

keywords = "CADe, Deep learning, Parathyroid gland identification",

author = "Jongchan Kim and Jennifer Yoo and Yoseph Kim and Eugene Oh and Bo Ning and Russell, {Jonathon O.} and Jaepyeong Cha",

note = "Publisher Copyright: {\textcopyright} COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.; Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022 ; Conference date: 22-01-2022 Through 27-01-2022",

year = "2022",

doi = "10.1117/12.2608939",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Wong, {Brian Jet-Fei} and Ilgner, {Justus F.}",

booktitle = "Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022",

}

TY - GEN

T1 - Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique

AU - Kim, Jongchan

AU - Yoo, Jennifer

AU - Kim, Yoseph

AU - Oh, Eugene

AU - Ning, Bo

AU - Russell, Jonathon O.

AU - Cha, Jaepyeong

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - CADe

KW - Deep learning

KW - Parathyroid gland identification

UR - http://www.scopus.com/inward/record.url?scp=85129213097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85129213097&partnerID=8YFLogxK

U2 - 10.1117/12.2608939

DO - 10.1117/12.2608939

M3 - Conference contribution

AN - SCOPUS:85129213097

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022

A2 - Wong, Brian Jet-Fei

A2 - Ilgner, Justus F.

PB - SPIE

T2 - Imaging, Therapeutics, and Advanced Technology in Head and Neck Surgery and Otolaryngology 2022

Y2 - 22 January 2022 through 27 January 2022

ER -

Computer-aided detection of parathyroid glands using a dual-RGB/NIR imaging and deep learning technique

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this