Objective Assessment of the Utility of Chromoendoscopy with a Support Vector Machine
Tóm tắt
The utility of chromoendoscopy for early gastric cancer (GC) was determined by machine learning using data of color differences. Eighteen histopathologically confirmed early GC lesions were examined. We prepared images from white light endoscopy (WL), indigo carmine (Indigo), and acetic acid-indigo carmine chromoendoscopy (AIM). A border between cancerous and non-cancerous areas on endoscopic images was established from post-treatment pathological findings, and 2000 pixels with equivalent luminance values were randomly extracted from each image of cancerous and non-cancerous areas. Each pixel was represented as a three-dimensional vector with RGB values and defined as a sample. We evaluated the Mahalanobis distance using RGB values, indicative of color differences between cancerous and non-cancerous areas. We then conducted diagnosis test using a support vector machine (SVM) for each image. SVM was trained using the 100 training samples per class and determined which area each of 1900 test samples per class came from. The means of the Mahalanobis distances for WL, Indigo, and AIM were 1.52, 1.32, and 2.53, respectively and there were no significant differences in the three modalities. Diagnosability per endoscopy technique was assessed using the F1 measure. The means of F1 measures for WL, Indigo, and AIM were 0.636, 0.618, and 0.687, respectively. AIM images were better than WL and Indigo images for the diagnosis of GC. Objective assessment by SVM found AIM to be suitable for diagnosis of early GC based on color differences.
Tài liệu tham khảo
Kaise M, Kato M, Tajiri H. High-definition endoscopy and magnifying endoscopy combined with narrow band imaging in gastric cancer. Gastroenterology Clinics of North America. 2010;39:771–84. https://doi.org/10.1016/j.gtc.2010.08.028.
Sugano K. Detection and management of early gastric cancer. Curr Treat Options Gastroenterol. 2015;13:398–408. https://doi.org/10.1007/s11938-015-0070-y.
Lambert R, Saito H, Saito Y. High-resolution endoscopy and early gastrointestinal cancer...dawn in the East. Endoscopy. 2007;39:232–7.
Ezoe Y, Muto M, Uedo N, Doyama H, Yao K, Oda I, et al. Magnifying narrowband imaging is more accurate than conventional white-light imaging in diagnosis of gastric mucosal cancer. Gastroenterology. 2011;141:2017–25. https://doi.org/10.1053/j.gastro.2011.08.007.
Yao K, Anagnostopoulos GK, Ragunath K. Magnifying endoscopy for diagnosing and delineating early gastric cancer. Endoscopy. 2009;41:462–7. https://doi.org/10.1055/s-0029-1214594.
Sumie H, Sumie S, Nakahara K, Watanabe Y, Matsuo K, Mukasa M, et al. Usefulness of magnifying endoscopy with narrow-band imaging for diagnosis of depressed gastric lesions. Mol Clin Oncol. 2014;2:129–33. https://doi.org/10.3892/mco.2013.213.
Szalóki T. Indigo carmine contrast staining in combination with high resolution electronic endoscopy. Orv Hetil. 2002;143:25–9.
Dinis-Ribeiro M. Chromoendoscopy for early diagnosis of gastric cancer. Eur J Gastroenterol Hepatol. 2006;18:831–8.
Vladimir NV (1995) The nature of statistical learning theory. Springer-Verlag, New York.
Numata N, Oka S, Tanaka S, Yoshifuku Y, Miwata T, Sanomura Y, et al. Useful condition of chromoendoscopy with indigo carmine and acetic acid for identifying a demarcation line prior to endoscopic submucosal dissection for early gastric cancer. BMC Gastroenterol. 2016;16:72. https://doi.org/10.1186/s12876-016-0483-7.
Kawahara Y, Takenaka R, Okada H, Kawano S, Inoue M, Tsuzuki T, et al. Novel chromoendoscopic method using an acetic acid-indigo carmine mixture for diagnostic accuracy in delineating the margin of early gastric cancers. Dig Endosc. 2009;21:14–9. https://doi.org/10.1111/j.1443-1661.2008.00824.x.
Nishio M, Nagashima C. Computer-aided diagnosis for lung cancer: usefulness of nodule heterogeneity. Acad Radiol. 2017;24:328–36. https://doi.org/10.1016/j.acra.2016.11.007.
Chang CC, Chen HH, Chang YC, Yang MY, Lo CM, Ko WC, et al. Computer-aided diagnosis of liver tumors on computed tomography images. Comput Methods Prog Biomed. 2017;14:45–51. https://doi.org/10.1016/j.cmpb.2017.04.008.
Van der Sommen F, Zinger S, Curvers WL, Bisschops R, Pech O, Weusten BL, et al. Computer-aided detection of early neoplastic lesions in Barrett’s esophagus. Endoscopy. 2016;48:617–24. https://doi.org/10.1055/s-0042-105284.
Kodogiannis VS, Boulougoura M, Lygouras JN, Petrounias I. A neuro-fuzzy-based system for detecting abnormal patterns in wireless-capsule endoscopic images. Neurocomputing. 2005;70:704–17. https://doi.org/10.1016/j.neucom.2006.10.024.
Nagao M, Nishikawa J, Ogawa R, Sasaki S, Nakamura M, Nishimura J, Goto A, Hashimoto S, Okamoto T, Suenaga M, Hamamoto Y, Sakaida I. Evaluation of the diagnostic ability of optical enhancement system in early gastric cancer demarcation. Gastroenterol Res Pract. 2016;2016:2439621. https://doi.org/10.1155/2016/2439621.
Mahalanobis PC (1936) On the generalized distance in statistics. In: Proc Nat Inst Sciences, India, pp 49–55.
Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011;2:27.1–27.
Powers DMW. Evaluation: from precision, recall and f-measure to ROC, informedness, markedness & correlation. Journal of Machine Learning Technology. 2011;2:37–63.
Hassanpour S, Langlotz CP, Amrhein TJ, Befera NT, Lungren MP. Performance of a machine learning classifier of knee MRI reports in two large academic radiology practices: a tool to estimate diagnostic yield. AJR Am J Roentgenol. 2017;208:750–3.
Li Y, Zhang T. Deep neural mapping support vector machines. Neural Netw. 2017;93:185–94. https://doi.org/10.1016/j.neunet.2017.05.010.
Kiyotoki S, Nishikawa J, Okamoto T, Hamabe K, Saito M, Goto A, et al. New method for detection of gastric cancer by hyperspectral imaging: a pilot study. J Biomed Opt. 2013;18:026010. https://doi.org/10.1117/1.JBO.18.2.026010.