DOI QR코드

DOI QR Code

비대면 원격진단을 위한 디지털 검이경 청진기 헬스케어 플랫폼 개발

Development of a Digital Otoscope-Stethoscope Healthcare Platform for Telemedicine

  • 최수영 (한국기계연구원 대구융합기술연구센터 의료기계연구실) ;
  • 이학 (경북대학교 기계공학부) ;
  • 박찬용 (한국기계연구원 대구융합기술연구센터 의료기계연구실) ;
  • 주수빈 (한국기계연구원 대구융합기술연구센터 의료기계연구실) ;
  • 권오원 (한국기계연구원 대구융합기술연구센터 의료기계연구실) ;
  • 이동규 (한국기계연구원 대구융합기술연구센터 의료기계연구실)
  • Su Young Choi (Department of Medical Device, Korea Institute of Machinery & Materials (KIMM)) ;
  • Hak Yi (School of Mechanical Engineering, Kyungpook National University) ;
  • Chanyong Park (Department of Medical Device, Korea Institute of Machinery & Materials (KIMM)) ;
  • Subin Joo (Department of Medical Device, Korea Institute of Machinery & Materials (KIMM)) ;
  • Ohwon Kwon (Department of Medical Device, Korea Institute of Machinery & Materials (KIMM)) ;
  • Dongkyu Lee (Department of Medical Device, Korea Institute of Machinery & Materials (KIMM))
  • 투고 : 2024.04.29
  • 심사 : 2024.06.04
  • 발행 : 2024.06.30

초록

We developed a device that integrates digital otoscope and stethoscope for telemedicine. The integrated device was utilized for the collection of tympanic membrane images and cardiac auscultation data. Data accumulated on the platform server can support real-time diagnosis of heart and eardrum diseases using artificial intelligence. Public data from Kaggle were used for deep learning. After comparing with various deep learning models, the MobileNetV2 model showed superior performance in analyzing tympanic membrane data, and the VGG16 model excelled in analyzing cardiac data. The classification algorithm achieved an accuracy of 89.9% for eardrums data and 100% for heart sound data. These results demonstrate the possibility of diagnosing diseases without the limitations of time and space by using this platform.

키워드

과제정보

본 연구는 산업통산자원부 바이오산업기술개발사업 글로벌진출형 디지털치료기기 개발지원 세부사업(20018535)의 지원을 받아 수행되었습니다.

참고문헌

  1. Jung KH, Torrone D, Lovinsky-Desir S, Perzanowski M, Bautista J, Jezioro JR, et al. Short-term exposure to PM(2.5) and vanadium and changes in asthma gene DNA methylation and lung function decrements among urban children. Respir Res. 2017;18(1):63.
  2. Labarca G, Drake L, Horta G, Jantz MA, Mehta HJ, Fernandez-Bussy S, et al. Association between inflammatory bowel disease and chronic obstructive pulmonary disease: a systematic review and meta-analysis. BMC Pulm Med. 2019;19(1):186.
  3. Schraufnagel DE, Balmes JR, Cowl CT, De Matteis S, Jung SH, Mortimer K, et al. Air Pollution and Noncommunicable Diseases: A Review by the Forum of International Respiratory Societies' Environmental Committee, Part 1: The Damaging Effects of Air Pollution. Chest. 2019;155(2):409-16. https://doi.org/10.1016/j.chest.2018.10.042
  4. Ma Y, Zhao C, Zhao Y, Lu J, Jiang H, Cao Y, et al. Telemedicine application in patients with chronic disease: a systematic review and meta-analysis. BMC Med Inform Decis Mak. 2022;22(1):105.
  5. Wang H, Yuan X, Wang J, Sun C, Wang G. Telemedicine maybe an effective solution for management of chronic disease during the COVID-19 epidemic. Prim Health Care Res Dev. 2021;22:e48.
  6. D'Onofrio KL, Zeng FG. Tele-Audiology: Current State and Future Directions. Front Digit Health. 2021;3:788103.
  7. Dendere R, Myburg N, Douglas TS. A review of cellphone microscopy for disease detection. J Microsc. 2015;260(3):248-59. https://doi.org/10.1111/jmi.12307
  8. Mousseau S, Lapointe A, Gravel J. Diagnosing acute otitis media using a smartphone otoscope; a randomized controlled trial. Am J Emerg Med. 2018;36(10):1796-801. https://doi.org/10.1016/j.ajem.2018.01.093
  9. Hafke-Dys H, Kuznar-Kaminska B, Grzywalski T, Maciaszek A, Szarzynski K, Kocinski J. Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients. Front Physiol. 2021;12:745635.
  10. Kim Y, Hyon Y, Lee S, Woo SD, Ha T, Chung C. The coming era of a new auscultation system for analyzing respiratory sounds. BMC Pulm Med. 2022;22(1):119.
  11. Kim Y, Hyon Y, Woo SD, Lee S, Lee SI, Ha T, et al. Evolution of the Stethoscope: Advances with the Adoption of Machine Learning and Development of Wearable Devices. Tuberc Respir Dis (Seoul). 2023;86(4):251-63. https://doi.org/10.4046/trd.2023.0065
  12. McDaniel NL, Novicoff W, Gunnell B, Cattell Gordon D. Comparison of a Novel Handheld Telehealth Device with Stand-Alone Examination Tools in a Clinic Setting. Telemed J E Health. 2019;25(12):1225-30. https://doi.org/10.1089/tmj.2018.0214
  13. Cha D, Pae C, Seong SB, Choi JY, Park HJ. Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database. EBioMedicine. 2019;45:606-14. https://doi.org/10.1016/j.ebiom.2019.06.050
  14. Chen J, Sun K, Sun Y, Li X. Signal Quality Assessment of PPG Signals using STFT Time-Frequency Spectra and Deep Learning Approaches. Annu Int Conf IEEE Eng Med Biol Soc. 2021;2021:1153-6.
  15. Goto R, Horimoto T, Koyama S, Suzuki T, Tsutsumi J, Matsuyama T, et al. Detection of Heartbeat Components Through Doppler Radar Systems Using Semantic Segmentation and Non-Harmonic Analysis. IEEE Access. 2024;12:32349-60.
  16. Khan MA, Kwon S, Choo J, Hong SM, Kang SH, Park IH, et al. Automatic detection of tympanic membrane and middle ear infection from oto-endoscopic images via convolutional neural networks. Neural Netw. 2020;126:384-94. https://doi.org/10.1016/j.neunet.2020.03.023
  17. Park YS, Jeon JH, Kong TH, Chung TY, Seo YJ. Deep Learning Techniques for Ear Diseases Based on Segmentation of the Normal Tympanic Membrane. Clin Exp Otorhinolaryngol. 2023;16(1):28-36. https://doi.org/10.21053/ceo.2022.00675
  18. Yadav K, Tiwari S, Jain A, Dafhalla AKY. Deep learning based cardiovascular disease diagnosis system from heartbeat sound. International Journal of Speech Technology. 2021.
  19. Rao D, Singh R, Kamath SK, Pendekanti SK, Pai D, Kolekar SV, et al. OTONet: Deep Neural Network for Precise Otoscopy Image Classification. IEEE Access. 2024;12:7734-46. https://doi.org/10.1109/ACCESS.2024.3351668
  20. Chowdhury MEH, Khandakar A, Alzoubi K, Mansoor S, A MT, Reaz MBI, et al. Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. Sensors (Basel). 2019;19(12).
  21. Quiceno AF, Delgado E, Vallverd M, Matijasevic AM, Castellanos-Domnguez G. Effective phonocardiogram segmentation using nonlinear dynamic analysis and high-frequency decomposition. In: 2008 Computers in Cardiology. IEEE; 2008.
  22. Lee K, Ji Y, Jeon Y, Park YC. Development and Implementation of Noise-Canceling Technology for Digital Stethoscope. Journal of Biomedical Engineering Research. 2013;34(4):204-11. https://doi.org/10.9718/JBER.2013.34.4.204
  23. Tympanic membrane / eardrum dataset / otitis media. Published online June 6, 2022.
  24. King E. Heartbeat Sounds. Published online November 27, 2016.
  25. Akay M, Du Y, Sershen CL, Wu M, Chen TY, Assassi S, et al. Deep Learning Classification of Systemic Sclerosis Skin Using the MobileNetV2 Model. IEEE Open J Eng Med Biol. 2021;2:104-10. https://doi.org/10.1109/OJEMB.2021.3066097
  26. Dong N, Zhao L, Wu CH, Chang JF. Inception v3 based cervical cell classification combined with artificially extracted features. Applied Soft Computing. 2020;93.
  27. Guefrechi S, Jabra MB, Ammar A, Koubaa A, Hamam H. Deep learning based detection of COVID-19 from chest X-ray images. Multimed Tools Appl. 2021;80(21-23):31803-20. https://doi.org/10.1007/s11042-021-11192-5
  28. Younis A, Qiang L, Nyatega CO, Adamu MJ, Kawuwa HB. Brain Tumor Analysis Using Deep Learning and VGG-16 Ensembling Learning Approaches. Applied Sciences. 2022;12(14).
  29. Ma N, Zhang X, Zheng H-T, Sun J. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. Computer Vision - ECCV 2018. Lecture Notes in Computer Science2018. p. 122-38.
  30. Ji Q, Huang J, He W, Sun Y. Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images. Algorithms. 2019;12(3).