Leonardo Zorron Cheng Tao Pu1, Gabriel Maicas2, Yu Tian3, Takeshi Yamamura4, Masanao Nakamura5, Hiroto Suzuki4, Gurfarmaan Singh6, Khizar Rana6, Yoshiki Hirooka7, Alastair D Burt6, Mitsuhiro Fujishiro5, Gustavo Carneiro2, Rajvinder Singh8. 1. Faculty of Health and Medical Sciences, University of Adelaide, Adelaide, South Australia, Australia; Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan. 2. Australian Institute for Machine Learning, University of Adelaide, Adelaide, South Australia, Australia. 3. Australian Institute for Machine Learning, University of Adelaide, Adelaide, South Australia, Australia; South Australian Health and Medical Research Institute, Adelaide, South Australia, Australia. 4. Department of Endoscopy, Nagoya University Hospital, Nagoya, Aichi, Japan. 5. Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan. 6. Faculty of Health and Medical Sciences, University of Adelaide, Adelaide, South Australia, Australia. 7. Department of Liver, Biliary Tract and Pancreas Diseases, Fujita Health University, Toyoake, Aichi, Japan. 8. Faculty of Health and Medical Sciences, University of Adelaide, Adelaide, South Australia, Australia; Department of Gastroenterology and Hepatology, Lyell McEwin Hospital, Adelaide, South Australia, Australia.
Abstract
BACKGROUND AND AIMS: Endoscopy guidelines recommend adhering to policies such as resect and discard only if the optical biopsy is accurate. However, accuracy in predicting histology can vary greatly. Computer-aided diagnosis (CAD) for characterization of colorectal lesions may help with this issue. In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI). METHODS: CAD software developed using machine learning and densely connected convolutional neural networks was modeled with NBI colorectal lesion images (Olympus 190 series - Australia) and validated for NBI (Olympus 290 series) and BLI (Fujifilm 700 series) with Japanese datasets. All images were correlated with histology according to the modified Sano classification. The CAD software was trained with Australian NBI images and tested with separate sets of images from Australia (NBI) and Japan (NBI and BLI). RESULTS: An Australian dataset of 1235 polyp images was used as training, testing, and internal validation sets. A Japanese dataset of 20 polyp images on NBI and 49 polyp images on BLI was used as external validation sets. The CAD software had a mean area under the curve (AUC) of 94.3% for the internal set and 84.5% and 90.3% for the external sets (NBI and BLI, respectively). CONCLUSIONS: The CAD achieved AUCs comparable with experts and similar results with NBI and BLI. Accurate CAD prediction was achievable, even when the predicted endoscopy imaging technology was not part of the training set.
BACKGROUND AND AIMS: Endoscopy guidelines recommend adhering to policies such as resect and discard only if the optical biopsy is accurate. However, accuracy in predicting histology can vary greatly. Computer-aided diagnosis (CAD) for characterization of colorectal lesions may help with this issue. In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI). METHODS: CAD software developed using machine learning and densely connected convolutional neural networks was modeled with NBI colorectal lesion images (Olympus 190 series - Australia) and validated for NBI (Olympus 290 series) and BLI (Fujifilm 700 series) with Japanese datasets. All images were correlated with histology according to the modified Sano classification. The CAD software was trained with Australian NBI images and tested with separate sets of images from Australia (NBI) and Japan (NBI and BLI). RESULTS: An Australian dataset of 1235 polyp images was used as training, testing, and internal validation sets. A Japanese dataset of 20 polyp images on NBI and 49 polyp images on BLI was used as external validation sets. The CAD software had a mean area under the curve (AUC) of 94.3% for the internal set and 84.5% and 90.3% for the external sets (NBI and BLI, respectively). CONCLUSIONS: The CAD achieved AUCs comparable with experts and similar results with NBI and BLI. Accurate CAD prediction was achievable, even when the predicted endoscopy imaging technology was not part of the training set.