Atsushi Ikeda1, Hirokazu Nosato2, Yuta Kochi2,3, Hiromitsu Negoro4, Takahiro Kojima4, Hidenori Sakanashi2,3, Masahiro Murakawa2,3, Hiroyuki Nishiyama1,4. 1. Department of Urology, University of Tsukuba Hospital, Tsukuba, Japan. 2. Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan. 3. Department of Intelligent Interaction Technologies, Graduate School of System and Information Engineering, University of Tsukuba, Tsukuba, Japan. 4. Department of Urology, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.
Abstract
Background: Nonmuscle-invasive bladder cancer is diagnosed, treated, and monitored using cystoscopy. Artificial intelligence (AI) is increasingly used to augment tumor detection, but its performance is hindered by the limited availability of cystoscopic images required to form a large training data set. This study aimed to determine whether stepwise transfer learning with general images followed by gastroscopic images can improve the accuracy of bladder tumor detection on cystoscopic imaging. Materials and Methods: We trained a convolutional neural network with 1.2 million general images, followed by 8728 gastroscopic images. In the final step of the transfer learning process, the model was additionally trained with 2102 cystoscopic images of normal bladder tissue and bladder tumors collected at the University of Tsukuba Hospital. The diagnostic accuracy was evaluated using a receiver operating characteristic curve. The diagnostic performance of the models trained with cystoscopic images with or without stepwise organic transfer learning was compared with that of medical students and urologists with varying levels of experience. Results: The model developed by stepwise organic transfer learning had 95.4% sensitivity and 97.6% specificity. This performance was better than that of the other models and comparable with that of expert urologists. Notably, it showed superior diagnostic accuracy when tumors occupied >10% of the image. Conclusions: Our findings demonstrate the value of stepwise organic transfer learning in applications with limited data sets for training and further confirm the value of AI in medical diagnostics. Here, we applied deep learning to develop a tool to detect bladder tumors with an accuracy comparable with that of a urologist. To address the limitation that few bladder tumor images are available to train the model, we demonstrate that pretraining with general and gastroscopic images yields superior results.
Background: Nonmuscle-invasive bladder cancer is diagnosed, treated, and monitored using cystoscopy. Artificial intelligence (AI) is increasingly used to augment tumor detection, but its performance is hindered by the limited availability of cystoscopic images required to form a large training data set. This study aimed to determine whether stepwise transfer learning with general images followed by gastroscopic images can improve the accuracy of bladder tumor detection on cystoscopic imaging. Materials and Methods: We trained a convolutional neural network with 1.2 million general images, followed by 8728 gastroscopic images. In the final step of the transfer learning process, the model was additionally trained with 2102 cystoscopic images of normal bladder tissue and bladder tumors collected at the University of Tsukuba Hospital. The diagnostic accuracy was evaluated using a receiver operating characteristic curve. The diagnostic performance of the models trained with cystoscopic images with or without stepwise organic transfer learning was compared with that of medical students and urologists with varying levels of experience. Results: The model developed by stepwise organic transfer learning had 95.4% sensitivity and 97.6% specificity. This performance was better than that of the other models and comparable with that of expert urologists. Notably, it showed superior diagnostic accuracy when tumors occupied >10% of the image. Conclusions: Our findings demonstrate the value of stepwise organic transfer learning in applications with limited data sets for training and further confirm the value of AI in medical diagnostics. Here, we applied deep learning to develop a tool to detect bladder tumors with an accuracy comparable with that of a urologist. To address the limitation that few bladder tumor images are available to train the model, we demonstrate that pretraining with general and gastroscopic images yields superior results.
Authors: Okyaz Eminaga; T Jessie Ge; Eugene Shkolyar; Mark A Laurie; Timothy J Lee; Lukas Hockman; Xiao Jia; Lei Xing; Joseph C Liao Journal: J Med Syst Date: 2022-10-03 Impact factor: 4.920
Authors: Jeong Woo Yoo; Kyo Chul Koo; Byung Ha Chung; Sang Yeop Baek; Su Jin Lee; Kyu Hong Park; Kwang Suk Lee Journal: Sci Rep Date: 2022-10-21 Impact factor: 4.996