Quantitative analysis of high resolution microendoscopic images for diagnosis of esophageal squamous cell carcinoma
JIA Yiwen1, QU Yawei2, and LIU Haifeng1,2
1.Graduate School, Anhui Medical University,Hefei 230032,China;
2.Department of Gastroenterology,General Hospital of Chinese People’s Armed Police Force,Beijing 100039,China
Objective To explore the diagnostic value of high-resolution microendoscopy in quantitative analysis of esophageal squamous cell carcinoma.Methods Thirty-five cases of esophageal squamous cell carcinoma and normal esophageal mucosa were selected. The HRME image of esophageal squamous cell carcinoma was analyzed retrospectively. According to the pathological Results of specimens, an HRME image was selected by an experienced HRME clinician to be included in the training set. The image features were quantitatively analyzed by computer software, and diagnostic criteria for image analysis were formulated. On this basis,the HRME images of biopsy specimens of 100 cases of suspected esophageal squamous cell carcinoma were input into the test set for quantitative analysis of these HRME images. The Results of pre-diagnosis via a computer were compared with pathological Results. The diagnostic value of quantitative HRME images for esophageal squamous cell carcinoma was determined.Results The quantitative analysis of the nuclear area in HRME images was used to distinguish esophageal squamous cell carcinoma from normal esophageal mucosa. Statistical analysis showed that the sensitivity and specificity were 90% and 97% respectively in the training set, but were 97% and 90% respectively in the test set.Conclusions Quantitative analysis of HRME images can distinguish esophageal squamous cell carcinoma from normal esophageal mucosa, increase the reliability of diagnosis, and contribute to the popularization and application of this technology.
Howlader N,Noone A M,Krapcho M,et al.SEER cancer statistics review 1975-2009 (vintage 2009 populations)[J].National Ca Ins,2013,1(10):3-10.
[2]
Reddymasu S C, Sharma P. Advances in endoscopic imaging of the esophagus[J]. GastroenterolClin N Am, 2008, 37(4):763-774.
[3]
Connor M J, Sharma P. Chromoendoscopy and magnification endoscopy for diagnosing esophageal cancer and dysplasia[J]. ThoracSurgClin, 2004,14(1):87-94.
[4]
Freitag C P, Barros S G, Kruel C D, et al. Esophageal dysplasias are detected by endoscopy with Lugol in patients at risk for squamous cell carcinoma in southern Brazil[J]. Dis Esophagus,1999,12(3):191-195.
[5]
Goda K, Dobashi A, Yoshimura N, et al. Narrow-Band Imaging Magnifying Endoscopy versus LugolChromoendoscopy with Pink-Color Sign Assessment in the Diagnosis of Superficial Esophageal Squamous Neoplasms: A RandomisedNoninferiority Trial[J]. Gastroenterol Res Pract, 2015, 2015(1):055-055.
[6]
Dawsey S M, Fleischer D E, Wang G, et al. Mucosal iodine staining improves endoscopic visualization of squamous dysplasia and squamous cell carcinoma of the esophagus in Linxian, China[J]. Cancer, 1998, 83(2):220-231.
[7]
Yoshida Y, Goda K, Tajiri H, et al. Assessment of novel endoscopic techniques for visualizing superficial esophageal squamous cell carcinoma: autofluorescence and narrow-band imaging[J]. Dis Esophagus, 2009, 22(5):439-446.
[8]
Iguchi Y, Niwa Y, Miyahara R, et al. Pilot study on confocal endomicroscopy for determination of the depth of squamous cell esophageal cancer in vivo[J]. J Gastroenterol Hepatol, 2009, 24(11):1733-1739.
[9]
Rosbach K J, Shin D, Muldoon T J, et al. High-resolution fiber optic microscopy with fluorescent contrast enhancement for the identification of axillary lymph node metastases in breast cancer: a pilot study[J]. Biomed Opt Express, 2010, 1(3):911-922.
[10]
Quinn M K, Bubi T C, Pierce M C, et al. High-resolution microendoscopy for the detection of cervical neoplasia in low-resource settings[J]. Plos One, 2012, 7(9).123-132.
[11]
Birdlieberman E L, Neves A A, Laosirieix P, et al. Molecular imaging using fluorescent lectins permits rapid endoscopic identification of dysplasia in Barrett's esophagus[J]. Nat Med, 2012, 18(2):315-321.
[12]
Goetz M, Hoetker M S, Diken M, et al. In vivo molecular imaging with cetuximab, an anti-EGFR antibody, for prediction of response in xenograft models of human colorectal cancer[J]. Endoscopy, 2013, 45(6):469-477.
[13]
Muldoon T J, Roblyer D, Williams M D, et al. Noninvasive imaging of oral neoplasia with a high-resolution fiber-optic microendoscope [J]. Head Neck, 2011, 34(34):305-312.
[14]
Vila P M, Chan W P, Pierce M C, et al. Discrimination of benign and neoplastic mucosa with a High-resolution microendoscope (HRME) in head and neck cancer[J]. Ann Surg Oncol, 2012,19(11):3534-3539.
[15]
Thekkek N, Lee M H, Polydorides A D, et al. Quantitative evaluation of in vivo vital-dye fluorescence endoscopic imaging for the detection of Barrett's-associated neoplasia[J]. JBiomed Opt, 2015, 20(5): 956-962.
[16]
Dittberner A, Rodner E, Ortmann W, et al. Automated analysis of confocal laser endomicroscopy images to detect head and neck cancer[J]. Head Neck, 2015, 38(S1):215-229.
[17]
Prieto S P, Powless A J, Lai K, et al. Qualitative and quantitative comparison of colonic microendoscopy image features to histopathology[C].SPIE BiOS. International Society for Optics and Photonics, 2015.
Louie J S, Richards K R, Anandasabapathy S. Applications and advancements in the use of high-resolution microendoscopy for detection of gastrointestinal neoplasia[J]. ClinGastroenterolHepatol, 2014, 12(11):1789-1792.
[20]
Chang S S, Shukla R, Polydorides A D, et al. High resolution microendoscopy for classification of colorectal polyps[J]. Endoscopy, 2013, 45(7):553-559.
[21]
Protano M A, Xu H, Wang G, et al. Low-cost high-resolution microendoscopy for the detection of esophageal squamous cell neoplasia: an international trial[J]. Gastroenterology, 2015, 149(2):321-329.
Downskelly E, Mendelin J E, Bennett A E, et al. Poor interobserver agreement in the distinction of high-grade dysplasia and adenocarcinoma in pretreatment Barrett’s esophagus biopsies[J]. Am J Gastroenterol, 2008, 103(9):2333-2340.
[24]
Ishijima A, Schwarz R A, Shin D, et al. Automated frame selection process for high-resolution microendoscopy[J]. J Biomed Opt, 2015, 20(4):321-327.
[25]
Miles B, Patsias A, Quang T, et al. Operative margin control with high-resolution optical microendoscopy for head and neck squamous cell carcinoma[J]. Laryngoscope, 2015, 125(10):2308-2316.
2017, Vol. 28 
