후두 내시경 영상에서의 성문 분할 및 성대 점막 형태의 정량적 평가 = Segmentation of the Glottis and Quantitative Measurement of the Vocal Cord Mucosal Morphology in the Laryngoscopic Image

다국어 초록 (Multilingual Abstract)

The purpose of this study is to compare and analyze Deep Learning (DL) and Digital Image Processing (DIP) techniques using the results of the glottis segmentation of the two methods followed by the quantification of the asymmetric degree of the vocal cord mucosa. The data consists of 40 normal and abnormal images. The DL model is based on Deeplab V3 architecture, and the Canny edge detector algorithm and morphological operations are used for the DIP technique. According to the segmentation results, the average accuracy of the DL model and the DIP was 97.5% and 94.7% respectively. The quantification results showed high correlation coefficients for both the DL experiment (r=0.8512, p<0.0001) and the DIP experiment (r=0.7784, p<0.0001). In the conclusion, the DL model showed relatively higher segmentation accuracy than the DIP. In this paper, we propose the clinical applicability of this technique applying the segmentation and asymmetric quantification algorithm to the glottal area in the laryngoscopic images.

참고문헌 (Reference)

1 왕수건 ; 박희준, "후두 스트로보스코피" 대한이비인후과학회 부산,울산,경남 지부회 26 (26): 3-9, 2015

2 최성희 ; 최철희, "초고속성대촬영시스템을 이용한 정상 성인 성대 움직임의 질적 분석" 한국언어청각임상학회 17 (17): 591-602, 2012

3 김영재 ; 김광기, "의료 영상에 최적화된 딥러닝 모델의 개발" 대한영상의학회 81 (81): 1274-1289, 2020

4 이진춘 ; 배인호, "성대진동검사의 최신 지견" 대한후두음성언어의학회 32 (32): 1-8, 2021

5 권관영 ; 김종훈 ; 김영재 ; 이상민 ; 김광기, "딥러닝을 활용한 피부 발적의 경계 판별" 한국멀티미디어학회 24 (24): 1492-1499, 2021

6 김범상 ; 이익현, "딥러닝 기법을 이용한 망막 혈관 분할" 한국정보기술학회 17 (17): 77-83, 2019

7 조용현, "디지털 피부영상의 관심영역 추출과 조합특징을 이용한 효율적인 병변 분할" 한국지능시스템학회 30 (30): 472-481, 2020

8 Y. Wang, "Skin Lesion Segmentation using Atrous Convolution via DeepLab V3"

9 L. -C. Chen, "Rethinking Atrous Convolution for Semantic Image Segmentation"

10 차원재 ; 왕수건 ; 장전엽 ; 김근효 ; 이연우, "Post-Processing of High-Speed Video-Laryngoscopic Images to Two-Dimensional Scanning Digital Kymographic Images" 대한후두음성언어의학회 28 (28): 89-95, 2017

11 김진필 ; 조영복, "OpenCV를 이용한 홍채 영상에서 병변 추출 영상처리 기법" 한국디지털콘텐츠학회 19 (19): 2035-2040, 2018

12 R. M. Haralick, "Image Analysis using Mathematical Morphology" (4) : 532-550, 1987

13 K. Zuiderveld, "Graphics Gems" 474-485, 1994

14 S. H. Lee, "Diagnostic Role of Stroboscopy" 21 (21): 13-16, 2010

15 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016

16 S. Subramaniam, "Deep Learning Architectures for Medical Image Segmentation" 579-584, 2020

17 T. K. Kwon, "Current Standpoints on the Pathophysiology of Benign Vocal Fold Lesions" 26 (26): 91-93, 2015

18 M. Kunduk, "Assessment of the Variability of Vocal Fold Dynamics within and between Recordings with High‐Speed Imaging and by Phonovibrogram" 120 (120): 981-987, 2010

19 D. P. Kingma, "Adam : A Method for Stochastic Optimization"

20 R. Kohavi, "A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection" 14 (14): 1137-1145, 1995

21 J. Canny, "A Computational Approach to Edge Detection" (6) : 679-698, 1986