Development of deep learning model for diagnosing muscle-invasive bladder cancer on MRI with vision transformer
Yasuhisa Kurata, Mizuho Nishio, Yusaku Moribata, Satoshi Otani, Yuki Himoto, Satoru Takahashi, Jiro Kusakabe, Ryota Okura, Marina Shimizu, Keisuke Hidaka, Naoko Nishio, Akihiko Furuta, Aki Kido, Kimihiko Masui, Hiroyuki Onishi, Takehiko Segawa, Takashi Kobayashi, Yuji Nakamoto
Abstract
Rationale and objectives To develop and validate a deep learning (DL) model to automatically diagnose muscle-invasive bladder cancer (MIBC) on MRI with Vision Transformer (ViT). Materials and methods This multicenter retrospective study included patients with BC who reported to two institutions between January 2016 and June 2020 (training dataset) and a third institution between May 2017 and May 2022 (test dataset). The diagnostic model for MIBC and the segmentation model for BC on MRI were developed using the training dataset with 5-fold cross-validation. ViT- and convolutional neural network (CNN)-based diagnostic models were developed and compared for diagnostic performance using the area under the curve (AUC). The performance of the diagnostic model with manual and auto-generated regions of interest (ROI manual and ROI auto , respectively) was validated on the test dataset and compared to that of radiologists (three senior and three junior radiologists) using Vesical Imaging Reporting and Data System scoring. Results The training and test datasets included 170 and 53 patients, respectively. Mean AUC of the top 10 ViT-based models with 5-fold cross-validation outperformed those of the CNN-based models (0.831 ± 0.003 vs. 0.713 ± 0.007–0.812 ± 0.006, p < .001). The diagnostic model with ROI manual achieved AUC of 0.872 (95 % CI: 0.777, 0.968), which was comparable to that of junior radiologists (AUC = 0.862, 0.873, and 0.930). Semi-automated diagnosis with the diagnostic model with ROI auto achieved AUC of 0.815 (95 % CI: 0.696, 0.935). Conclusion The DL model effectively diagnosed MIBC. The ViT-based model outperformed CNN-based models, highlighting its utility in medical image analysis.