Mimi C Tan1, Sheena Bhushan1, Timothy Quang2, Richard Schwarz3, Kalpesh H Patel1, Xinying Yu4, Zhengqi Li4, Guiqi Wang4, Fan Zhang5, Xueshan Wang5, Hong Xu5, Rebecca R Richards-Kortum3, Sharmila Anandasabapathy1. 1. Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas. 2. National Institute for Child Health and Human Development, National Institutes of Health, Bethesda, Maryland. 3. Department of Bioengineering, Rice University, Houston, Texas. 4. Department of Endoscopy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. 5. Department of Gastrointestinal Medicine, The First Hospital of Jilin University, Changchun, Jilin, China.
Abstract
BACKGROUND AND AIMS: High-resolution microendoscopy (HRME) is an optical biopsy technology that provides subcellular imaging of esophageal mucosa but requires expert interpretation of these histopathology-like images. We compared endoscopists with an automated software algorithm for detection of esophageal squamous cell neoplasia (ESCN) and evaluated the endoscopists' accuracy with and without input from the software algorithm. METHODS: Thirteen endoscopists (6 experts, 7 novices) were trained and tested on 218 post-hoc HRME images from 130 consecutive patients undergoing ESCN screening/surveillance. The automated software algorithm interpreted all images as neoplastic (high-grade dysplasia, ESCN) or non-neoplastic. All endoscopists provided their interpretation (neoplastic or non-neoplastic) and confidence level (high or low) without and with knowledge of the software overlay highlighting abnormal nuclei and software interpretation. The criterion standard was histopathology consensus diagnosis by 2 pathologists. RESULTS: The endoscopists had a higher mean sensitivity (84.3%, standard deviation [SD] 8.0% vs 76.3%, P = .004), lower specificity (75.0%, SD 5.2% vs 85.3%, P < .001) but no significant difference in accuracy (81.1%, SD 5.2% vs 79.4%, P = .26) of ESCN detection compared with the automated software algorithm. With knowledge of the software algorithm, the specificity of the endoscopists increased significantly (75.0% to 80.1%, P = .002) but not the sensitivity (84.3% to 84.8%, P = .75) or accuracy (81.1% to 83.1%, P = .13). The increase in specificity was among novices (P = .008) but not experts (P = .11). CONCLUSIONS: The software algorithm had lower sensitivity but higher specificity for ESCN detection than endoscopists. Using computer-assisted diagnosis, the endoscopists maintained high sensitivity while increasing their specificity and accuracy compared with their initial diagnosis. Automated HRME interpretation would facilitate widespread usage in resource-poor areas where this portable, low-cost technology is needed. Published by Elsevier Inc.
BACKGROUND AND AIMS: High-resolution microendoscopy (HRME) is an optical biopsy technology that provides subcellular imaging of esophageal mucosa but requires expert interpretation of these histopathology-like images. We compared endoscopists with an automated software algorithm for detection of esophageal squamous cell neoplasia (ESCN) and evaluated the endoscopists' accuracy with and without input from the software algorithm. METHODS: Thirteen endoscopists (6 experts, 7 novices) were trained and tested on 218 post-hoc HRME images from 130 consecutive patients undergoing ESCN screening/surveillance. The automated software algorithm interpreted all images as neoplastic (high-grade dysplasia, ESCN) or non-neoplastic. All endoscopists provided their interpretation (neoplastic or non-neoplastic) and confidence level (high or low) without and with knowledge of the software overlay highlighting abnormal nuclei and software interpretation. The criterion standard was histopathology consensus diagnosis by 2 pathologists. RESULTS: The endoscopists had a higher mean sensitivity (84.3%, standard deviation [SD] 8.0% vs 76.3%, P = .004), lower specificity (75.0%, SD 5.2% vs 85.3%, P < .001) but no significant difference in accuracy (81.1%, SD 5.2% vs 79.4%, P = .26) of ESCN detection compared with the automated software algorithm. With knowledge of the software algorithm, the specificity of the endoscopists increased significantly (75.0% to 80.1%, P = .002) but not the sensitivity (84.3% to 84.8%, P = .75) or accuracy (81.1% to 83.1%, P = .13). The increase in specificity was among novices (P = .008) but not experts (P = .11). CONCLUSIONS: The software algorithm had lower sensitivity but higher specificity for ESCN detection than endoscopists. Using computer-assisted diagnosis, the endoscopists maintained high sensitivity while increasing their specificity and accuracy compared with their initial diagnosis. Automated HRME interpretation would facilitate widespread usage in resource-poor areas where this portable, low-cost technology is needed. Published by Elsevier Inc.
Authors: Dongsuk Shin; Marion-Anna Protano; Alexandros D Polydorides; Sanford M Dawsey; Mark C Pierce; Michelle Kang Kim; Richard A Schwarz; Timothy Quang; Neil Parikh; Manoop S Bhutani; Fan Zhang; Guiqi Wang; Liyan Xue; Xueshan Wang; Hong Xu; Sharmila Anandasabapathy; Rebecca R Richards-Kortum Journal: Clin Gastroenterol Hepatol Date: 2014-07-25 Impact factor: 11.382
Authors: Benjamin D Grant; José H T G Fregnani; Júlio C Possati Resende; Cristovam Scapulatempo-Neto; Graziela M Matsushita; Edmundo C Mauad; Timothy Quang; Mark H Stoler; Philip E Castle; Kathleen M Schmeler; Rebecca R Richards-Kortum Journal: Eur J Cancer Prev Date: 2017-01 Impact factor: 2.497
Authors: Mary K Quinn; Tefo C Bubi; Mark C Pierce; Mukendi K Kayembe; Doreen Ramogola-Masire; Rebecca Richards-Kortum Journal: PLoS One Date: 2012-09-18 Impact factor: 3.240