155 310

Cited 12 times in

Deep learning diagnostics for bladder tumor identification and grade prediction using RGB method

Authors
 Jeong Woo Yoo  ;  Kyo Chul Koo  ;  Byung Ha Chung  ;  Sang Yeop Baek  ;  Su Jin Lee  ;  Kyu Hong Park  ;  Kwang Suk Lee 
Citation
 SCIENTIFIC REPORTS, Vol.12(1) : 17699, 2022-10 
Journal Title
SCIENTIFIC REPORTS
Issue Date
2022-10
MeSH
Artificial Intelligence ; Deep Learning* ; Humans ; Neural Networks, Computer ; Retrospective Studies ; Urinary Bladder Neoplasms* / diagnostic imaging
Abstract
We evaluate the diagnostic performance of deep learning artificial intelligence (AI) for bladder cancer, which used white-light images (WLIs) and narrow-band images, and tumor grade prediction of AI based on tumor color using the red/green/blue (RGB) method. This retrospective study analyzed 10,991 cystoscopic images of suspicious bladder tumors using a mask region-based convolutional neural network with a ResNeXt-101-32 × 8d-FPN backbone. The diagnostic performance of AI was evaluated by calculating sensitivity, specificity, and diagnostic accuracy, and its ability to detect cancers was investigated using the dice score coefficient (DSC). Using the support vector machine model, we analyzed differences in tumor colors according to tumor grade using the RGB method. The sensitivity, specificity, diagnostic accuracy and DSC of AI were 95.0%, 93.7%, 94.1% and 74.7%. In WLIs, there were differences in red and blue values according to tumor grade (p < 0.001). According to the average RGB value, the performance was ≥ 98% for the diagnosis of benign vs. low-and high-grade tumors using WLIs and > 90% for the diagnosis of chronic non-specific inflammation vs. carcinoma in situ using WLIs. The diagnostic performance of the AI-assisted diagnosis was of high quality, and the AI could distinguish the tumor grade based on tumor color.
Files in This Item:
T202205073.pdf Download
DOI
10.1038/s41598-022-22797-7
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Urology (비뇨의학교실) > 1. Journal Papers
Yonsei Authors
Koo, Kyo Chul(구교철) ORCID logo https://orcid.org/0000-0001-7303-6256
Yoo, Jeong Woo(유정우)
Lee, Kwang Suk(이광석) ORCID logo https://orcid.org/0000-0002-7961-8393
Chung, Byung Ha(정병하) ORCID logo https://orcid.org/0000-0001-9817-3660
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/192262
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links