A novel summary report of colonoscopy: timeline visualization providing meaningful colonoscopy video information
- 39 Downloads
The colonoscopy adenoma detection rate depends largely on physician experience and skill, and overlooked colorectal adenomas could develop into cancer. This study assessed a system that detects polyps and summarizes meaningful information from colonoscopy videos.
One hundred thirteen consecutive patients had colonoscopy videos prospectively recorded at the Seoul National University Hospital. Informative video frames were extracted using a MATLAB support vector machine (SVM) model and classified as bleeding, polypectomy, tool, residue, thin wrinkle, folded wrinkle, or common. Thin wrinkle, folded wrinkle, and common frames were reanalyzed using SVM for polyp detection. The SVM model was applied hierarchically for effective classification and optimization of the SVM.
The mean classification accuracy according to type was over 93%; sensitivity was over 87%. The mean sensitivity for polyp detection was 82.1%, and the positive predicted value (PPV) was 39.3%. Polyps detected using the system were larger (6.3 ± 6.4 vs. 4.9 ± 2.5 mm; P = 0.003) with a more pedunculated morphology (Yamada type III, 10.2 vs. 0%; P < 0.001; Yamada type IV, 2.8 vs. 0%; P < 0.001) than polyps missed by the system. There were no statistically significant differences in polyp distribution or histology between the groups. Informative frames and suspected polyps were presented on a timeline. This summary was evaluated using the system usability scale questionnaire; 89.3% of participants expressed positive opinions.
We developed and verified a system to extract meaningful information from colonoscopy videos. Although further improvement and validation of the system is needed, the proposed system is useful for physicians and patients.
KeywordsColonoscopy Polyp detection Summary report Visualization Classification
This work was supported by Grant No. 0320150450 from the Seoul National University Hospital.
Compliance with ethical standards
This study was approved by the institutional review board of the Seoul National University Hospital (IRB No. 1509-062-703, approval date July 13, 2016), and it was conducted in accordance with the Declaration of Helsinki. Written informed consent was obtained from all participants.
Conflict of interest
The authors declare that they have no conflict of interest.
- 7.Burggraaf J, Kamerling IMC, Gordon PB, Schrier L, de Kam ML, Kales AJ, Bendiksen R, Indrevoll B, Bjerke RM, Moestue SA, Yazdanfar S, Langers AMJ, Swaerd-Nordmo M, Torheim G, Warren MV, Morreau H, Voorneveld PW, Buckle T, van Leeuwen FWB, Ødegårdstuen L-I, Dalsgaard GT, Healey A, Hardwick JCH (2015) Detection of colorectal polyps in humans using an intravenously administered fluorescent peptide targeted against c-Met. Nat Med 21(8):955–961CrossRefPubMedGoogle Scholar
- 9.Hong SN, Sung IK, Kim JH, Choe WH, Kim BK, Ko SY, Lee JH, Seol DC, Ahn SY, Lee SY, Park HS, Shim CS (2012) The effect of the bowel preparation status on the risk of missing polyp and adenoma during screening colonoscopy: a tandem colonoscopic study. Clinical endoscopy 45:404–411CrossRefPubMedPubMedCentralGoogle Scholar
- 19.Shang-bo, Zhou, et al. (2016) Bleeding detection in wireless capsule endoscope based on color feature vector. DEStech Transactions on Computer Science and Engineering, aice-ncsGoogle Scholar
- 23.Münzer B, Schoeffmann K, Böszörmenyi L (2017) Content-based processing and analysis of endoscopic images and videos: a survey. Multimed Tools and Appl, 1–40Google Scholar
- 24.Sudha N, Santhiyakumari N (2016) MIEEE. Summarizing wireless capsule endoscopy video frame based on inter-frame structural similarity index. Adv Nat Appl Sci 10(6 SE):199–208Google Scholar
- 28.Salvi E et al. (2017) Exploring IBM Watson to extract meaningful information from the list of references of a clinical practice guideline. In: Conference on Artificial Intelligence in Medicine in Europe. Springer: Cham, p. 193–197Google Scholar
- 29.Diomaiuta C et al. (2017) A novel system for the automatic extraction of a patient problem summary. In: Computers and Communications (ISCC), 2017 I.E. Symposium on IEEE. p. 182–186Google Scholar
- 33.Ikematsu H, Saito Y, Tanaka S, Uraoka T, Sano Y, Horimatsu T, Matsuda T, Oka S, Higashi R, Ishikawa H, Kaneko K (2012) The impact of narrow band imaging for colon polyp detection: a multicenter randomized controlled trial by tandem colonoscopy. J Gastroenterol 47:1099–1107CrossRefPubMedGoogle Scholar
- 34.Vilarino F et al. (2007) Automatic labeling of colonoscopy video for cancer detection. Pattern Recognit Image Anal 290–297Google Scholar
- 36.Hoyos J (2017) Automatic classification of non-informative frames in colonoscopy videos using texture analysis. In: Progress in pattern recognition, image analysis, computer vision, and applications: 21st Iberoamerican Congress, CIARP 2016, Lima, Peru, November 8–11, 2016, proceedings. Spring, p. 401Google Scholar
- 39.Xiong Y, et al. (2015) Bleeding detection in wireless capsule endoscopy based on mst clustering and svm. In: Signal processing systems (SiPS), 2015 I.E. Workshop on IEEE. p. 1–4Google Scholar
- 40.Mackiewicz MW, Fisher M, Jamieson C (2008) Bleeding detection in wireless capsule endoscopy using adaptive colour histogram model and support vector classification. In: Medical imaging. International Society for Optics and Photonics. p. 69140R-69140R-12Google Scholar
- 41.Hwang, Sae, et al. (2007) Polyp detection in colonoscopy video using elliptical shape feature. In: Image processing, 2007. ICIP 2007. IEEE International Conference on. IEEE. p. II-465-II-468Google Scholar
- 43.Sonka M, Hlavac V, Boyle R (2014) Image processing, analysis, and machine vision. Cengage Learning, BostonGoogle Scholar
- 44.Hua BO, Fu-Long M, Li-Cheng J (2006) Research on computation of GLCM of image texture [J]. Acta Electron Sin 1(1):155–158Google Scholar
- 47.Ionescu M et al (2015) Methods of diagnosis of intestinal polyps with software applications in wireless capsule endoscopy. Ann Comput Sci Ser 13:1Google Scholar
- 48.Valdeavilla EB, Miaou S-G Classification of capsule endoscope images using local binary patterns and support vector machinesGoogle Scholar
- 53.Brooke J (1996) SUS-A quick and dirty usability scale. Usability evaluation in industry. 189:4–7Google Scholar
- 60.Amber A et al. (2015) Feature point based polyp tracking in endoscopic videos. In: Applied computing and information technology/2nd International Conference on Computational Science and Intelligence (ACIT-CSI), 2015 3rd International Conference on IEEE. p. 299–304.Google Scholar
- 61.Park S, Lee M, Kwak N (2015) Polyp detection in colonoscopy videos using deeply-learned hierarchical features. Seoul National University, SeoulGoogle Scholar
- 62.Yu L, Chen H, Dou Q, Qin J, Heng PA (2016) Integrating online and offline 3D deep learning for automated polyp detection in colonoscopy videos. IEEE J Biomed Health InformGoogle Scholar
- 65.N. Tajbakhsh, S. R. Gurudu, J. Liang (2015) Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In: Proc. 2015 I.E. 12th Int Symp Biomed Imag, pp. 79–83Google Scholar
- 66.Sousa AC, Figueiredo P, Lopes S, Gouveia H, Sofia C, Correia LM (2007) A thousand total colonoscopies: what is the relationship between distal and proximal findings? Acta Medica Port 21:461–466Google Scholar
- 69.Robertson DJ, Kaminski MF, Bretthauer M (2015) Effectiveness, training and quality assurance of colonoscopy screening for colorectal cancer. GutGoogle Scholar