DOI QR코드

DOI QR Code

Estimating Gastrointestinal Transition Location Using CNN-based Gastrointestinal Landmark Classifier

CNN 기반 위장관 랜드마크 분류기를 이용한 위장관 교차점 추정

  • Received : 2019.12.31
  • Accepted : 2020.02.06
  • Published : 2020.03.31

Abstract

Since the performance of deep learning techniques has recently been proven in the field of image processing, there are many attempts to perform classification, analysis, and detection of images using such techniques in various fields. Among them, the expectation of medical image analysis software, which can serve as a medical diagnostic assistant, is increasing. In this study, we are attention to the capsule endoscope image, which has a large data set and takes a long time to judge. The purpose of this paper is to distinguish the gastrointestinal landmarks and to estimate the gastrointestinal transition location that are common to all patients in the judging of capsule endoscopy and take a lot of time. To do this, we designed CNN-based Classifier that can identify gastrointestinal landmarks, and used it to estimate the gastrointestinal transition location by filtering the results. Then, we estimate gastrointestinal transition location about seven of eight patients entered the suspected gastrointestinal transition area. In the case of change from the stomach to the small intestine(pylorus), and change from the small intestine to the large intestine(ileocecal valve), we can check all eight patients were found to be in the suspected gastrointestinal transition area. we can found suspected gastrointestinal transition area in the range of 100 frames, and if the reader plays images at 10 frames per second, the gastrointestinal transition could be found in 10 seconds.

최근의 영상 처리 분야는 딥러닝 기법들의 성능이 입증됨에 따라 다양한 분야에서 이와 같은 기법들을 활용해 영상에 대한 분류, 분석, 검출 등을 수행하려는 시도가 활발하다. 그중에서도 의료 진단 보조 역할을 할 수 있는 의료 영상 분석 소프트웨어에 대한 기대가 증가하고 있는데, 본 연구에서는 데이터 셋이 방대하고 판단에 시간이 오래 걸리는 캡슐내시경 영상에 주목하였다. 본 논문의 목적은 캡슐내시경 영상의 판독에서 모든 환자에 대해 공통으로 수행되고, 판독하는 데 많은 시간을 차지하는 위장관 랜드마크를 구별하고 위장관 교차점을 추정하는 것이다. 이를 위해, 위장관 랜드마크를 식별할 수 있는 CNN 학습 모델을 설계하였으며, 이를 이용하여 결괏값을 필터링해 위장관 교차점을 추정하였다. 무작위로 환자 데이터를 샘플링한 모델을 이용해서 나온 결과를 필터링 후에 위장관 교차점을 추정하였을 때, 88% 환자는 위장에서 소장으로 변화하는 위장관 교차점(유문판) 의심 구역 안에 들어왔으며, 소장에서 대장으로 변화하는 위장관 교차점(회맹판)의 경우 100% 환자가 위장관 교차점 의심 구역 안에 들어온 것을 확인할 수 있었다. 100프레임 범위로 위장관 교차점 의심 구역을 찾을 수 있었으며, 판독자가 초당 10프레임의 속도로 판독을 진행한다면 10초안에 위장관 교차점을 찾아낼 수 있다.

Keywords

References

  1. Geet Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A.W.M van der Laak, Bram van Ginneken, and Clara I. Sanchez, "A survey on deep learning in medical image analysis," Medical Image Analysis, Vol.42, pp.60-88, 2017. https://doi.org/10.1016/j.media.2017.07.005
  2. Kim Jeong Rye, Woo Hyun Shim, Hee Mang Yoon, Sang Hyup Hong, Jin Seong Lee, Young Ah Cho, and Sangki Kim, "Computerized bone age estimation using deep learning based program: evaluation of the accuracy and efficiency," American Journal of Roentgenology, Vol.209, No.6, pp.1374-1380, 2017. https://doi.org/10.2214/AJR.17.18224
  3. Eui Jin Hwang, Sunggyun Park, Jung Im Kim, So Young Choi, Jong Hyuk Lee, Jin Mo Goo, Jaehong Aum, Jae-Joon Yim, Julien G.Cohen, Gilbert R.Ferretti, and Chang Min Park, "Development and Validation of a Deep Learning-Based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs," Clinical Infectious Diseases, Vol.69, No.5, pp.739-747, doi: 10.1093/cid/ciy967, 2018.11.
  4. Karargyris, Alexandros, and Nikolaos Bourbakis, "Detection of small bowel polyps and ulcers in wireless capsule endoscopy videos," IEEE Transactions on BioMedical Engineering, Vol.58, No.10, pp.2777-2786, 2011. https://doi.org/10.1109/TBME.2011.2155064
  5. Baopu Li and Max Q.-H Meng, "Tumor Recognition in Wireless Capsule Endoscopy Images Using Textural Features and SVM-Based Feature Selection," IEEE Transactions on Information Technology in Biomedicine, Vol.16, No.3, pp.323-329, 2012. https://doi.org/10.1109/TITB.2012.2185807
  6. Meryem Souaidi, Said Charfi, Abdelkaher Ait Abdelouahad, and Mohamed El Ansari, "New Features for wireless capsule endoscopy polyp detection," Intelligent Systems and Computer Visions(ISCV), 2018 International Conference on IEEE, 2018.
  7. H. G Lee, H. K Choi, D. H. Lee, and S. C Lee, "Intelligent Diagnosis Assistant System of Capsule Endoscopy Video Through Analysis of Video Frames," Korea Intelligent Information System Sociery (KIISS), Vol.15, No.2, pp.33-48, 2009.
  8. D.Y Yoo, Y.S Park, and J.W Lee, "SVM-based Classification of Over-residue Images for Filtering Learning-obstruction Images of Capsule Endoscopy," Korea Computer Congress (KCC), pp.1865-1867, 2018.
  9. D. Y. Yoo, Y. S. Park, B. J. Lee, and J. W. Lee, "Classification of Noise Interfering with Learning for Medical Image Data-driven Software Development," Korea Conference on Software Engineering(KCSE), pp.317-322, 2019.
  10. H. Chen, X. Wu, G. Tao, and Q. Peng, "Automatic content understanding with cascaded spatial-temporal deep framework for capsule endoscopy videos," Neurocomputing, 229, pp.77-87, 2017. https://doi.org/10.1016/j.neucom.2016.06.077
  11. J. P. Silva Cuncha, M. Coimbra, P. Campos, and J. M. Soares, "Automated Topographic Segmentation and Transit Time Estimation in Endoscopic Capsule Exams," IEEE Transaction on Medical Imaging, Vol.27, No.1, pp.19-27, Jan. 2008. https://doi.org/10.1109/TMI.2007.901430
  12. Horn, Eli, Hagai Krupnik, and Ofra Zinaty, "System and method to detect a transition in an image stream," U.S. Patent No.7, 684,599, filed Sep.27 2005, and issued Mar 23, 2010.
  13. Michal Mackiewicz, Jeff Barens, Mark Fisher, and Duncan Bell, "Colour and texture based gastrointestinal tissue discrimination," IEEE International Conference on Acoustics Speech and Signal Processing Proceedings. Vol.2, doi: 10.1109/ICASSP.2006.1660413, 2006.7.
  14. Michal Mackiewicz, Jeff Berens, and Mark Fisher "Wireless capsule endoscopy color video segmentation," IEEE Transactions on Medical Imaging, Vol.27, No.12, pp.1769-1781, 2008. https://doi.org/10.1109/TMI.2008.926061