Daiki Nemoto1, Zhe Guo2, Boyuan Peng2, Ruiyao Zhang2, Yuki Nakajima1, Yoshikazu Hayashi3, Takeshi Yamashina4, Masato Aizawa1, Kenichi Utano1, Alan Kawarai Lefor5, Xin Zhu2, Kazutomo Togashi6. 1. Department of Coloproctology & Gastroenterology, Aizu Medical Center, Fukushima Medical University, 21-2 Maeda, Tanisawa, Aizuwakamatsu, Fukushima, 969-3492, Japan. 2. Biomedical Information Engineering Lab, The University of Aizu, Aizuwakamatsu, Fukushima, Japan. 3. Department of Medicine, Division of Gastroenterology, Jichi Medical University, Shimotsuke, Tochigi, Japan. 4. Gastroenterology and Hepatology, Kansai Medical University Medical Center, Moriguchi, Osaka, Japan. 5. Department of Surgery, Jichi Medical University, Shimotsuke, Tochigi, Japan. 6. Department of Coloproctology & Gastroenterology, Aizu Medical Center, Fukushima Medical University, 21-2 Maeda, Tanisawa, Aizuwakamatsu, Fukushima, 969-3492, Japan. togashik@fmu.ac.jp.
Abstract
PURPOSE: Computer-aided diagnosis systems for polyp characterization are commercially available but cannot recognize subtypes of sessile lesions. This study aimed to develop a computer-aided diagnosis system to characterize polyps using non-magnified white-light endoscopic images. METHODS: A total of 2249 non-magnified white-light images from 1030 lesions including 534 tubular adenomas, 225 sessile serrated adenoma/polyps, and 271 hyperplastic polyps in the proximal colon were consecutively extracted from an image library and divided into training and testing datasets (4:1), based on the date of colonoscopy. Using ResNet-50 networks, we developed a classifier (1) to differentiate adenomas from serrated lesions, and another classifier (2) to differentiate sessile serrated adenoma/polyps from hyperplastic polyps. Diagnostic performance was assessed using the testing dataset. The computer-aided diagnosis system generated a probability score for each image, and a probability score for each lesion was calculated as the weighted mean with a log10-transformation. Two experts (E1, E2) read the identical testing dataset with a probability score. RESULTS: The area under the curve of classifier (1) for adenomas was equivalent to E1 and superior to E2 (classifier 86%, E1 86%, E2 69%; classifier vs. E2, p < 0.001). In contrast, the area under the curve of classifier (2) for sessile serrated adenoma/polyps was inferior to both experts (classifier 55%, E1 68%, E2 79%; classifier vs. E2, p < 0.001). CONCLUSION: The classifier (1) developed using white-light images alone compares favorably with experts in differentiating adenomas from serrated lesions. However, the classifier (2) to identify sessile serrated adenoma/polyps is inferior to experts.
PURPOSE: Computer-aided diagnosis systems for polyp characterization are commercially available but cannot recognize subtypes of sessile lesions. This study aimed to develop a computer-aided diagnosis system to characterize polyps using non-magnified white-light endoscopic images. METHODS: A total of 2249 non-magnified white-light images from 1030 lesions including 534 tubular adenomas, 225 sessile serrated adenoma/polyps, and 271 hyperplastic polyps in the proximal colon were consecutively extracted from an image library and divided into training and testing datasets (4:1), based on the date of colonoscopy. Using ResNet-50 networks, we developed a classifier (1) to differentiate adenomas from serrated lesions, and another classifier (2) to differentiate sessile serrated adenoma/polyps from hyperplastic polyps. Diagnostic performance was assessed using the testing dataset. The computer-aided diagnosis system generated a probability score for each image, and a probability score for each lesion was calculated as the weighted mean with a log10-transformation. Two experts (E1, E2) read the identical testing dataset with a probability score. RESULTS: The area under the curve of classifier (1) for adenomas was equivalent to E1 and superior to E2 (classifier 86%, E1 86%, E2 69%; classifier vs. E2, p < 0.001). In contrast, the area under the curve of classifier (2) for sessile serrated adenoma/polyps was inferior to both experts (classifier 55%, E1 68%, E2 79%; classifier vs. E2, p < 0.001). CONCLUSION: The classifier (1) developed using white-light images alone compares favorably with experts in differentiating adenomas from serrated lesions. However, the classifier (2) to identify sessile serrated adenoma/polyps is inferior to experts.
Authors: A Ignjatovic; J E East; T Guenther; J Hoare; J Morris; K Ragunath; A Shonde; J Simmons; N Suzuki; S Thomas-Gibson; B P Saunders Journal: Endoscopy Date: 2011-01-26 Impact factor: 10.093
Authors: Mark Bettington; Neal Walker; Andrew Clouston; Ian Brown; Barbara Leggett; Vicki Whitehall Journal: Histopathology Date: 2013-02 Impact factor: 5.087
Authors: Christophe Rosty; David G Hewett; Ian S Brown; Barbara A Leggett; Vicki L J Whitehall Journal: J Gastroenterol Date: 2012-12-04 Impact factor: 7.527