Literature DB >> 33787537

A Novel Deep Learning Based Computer-Aided Diagnosis System Improves the Accuracy and Efficiency of Radiologists in Reading Biparametric Magnetic Resonance Images of the Prostate: Results of a Multireader, Multicase Study.

David J Winkel1, Angela Tong, Bin Lou, Ali Kamen, Dorin Comaniciu, Jonathan A Disselhorst, Alejandro Rodríguez-Ruiz, Henkjan Huisman, Dieter Szolar, Ivan Shabunin, Moon Hyung Choi, Pengyi Xing, Tobias Penzkofer, Robert Grimm, Heinrich von Busch, Daniel T Boll.   

Abstract

OBJECTIVE: The aim of this study was to evaluate the effect of a deep learning based computer-aided diagnosis (DL-CAD) system on radiologists' interpretation accuracy and efficiency in reading biparametric prostate magnetic resonance imaging scans.
MATERIALS AND METHODS: We selected 100 consecutive prostate magnetic resonance imaging cases from a publicly available data set (PROSTATEx Challenge) with and without histopathologically confirmed prostate cancer. Seven board-certified radiologists were tasked to read each case twice in 2 reading blocks (with and without the assistance of a DL-CAD), with a separation between the 2 reading sessions of at least 2 weeks. Reading tasks were to localize and classify lesions according to Prostate Imaging Reporting and Data System (PI-RADS) v2.0 and to assign a radiologist's level of suspicion score (scale from 1-5 in 0.5 increments; 1, benign; 5, malignant). Ground truth was established by consensus readings of 3 experienced radiologists. The detection performance (receiver operating characteristic curves), variability (Fleiss κ), and average reading time without DL-CAD assistance were evaluated.
RESULTS: The average accuracy of radiologists in terms of area under the curve in detecting clinically significant cases (PI-RADS ≥4) was 0.84 (95% confidence interval [CI], 0.79-0.89), whereas the same using DL-CAD was 0.88 (95% CI, 0.83-0.94) with an improvement of 4.4% (95% CI, 1.1%-7.7%; P = 0.010). Interreader concordance (in terms of Fleiss κ) increased from 0.22 to 0.36 (P = 0.003). Accuracy of radiologists in detecting cases with PI-RADS ≥3 was improved by 2.9% (P = 0.10). The median reading time in the unaided/aided scenario was reduced by 21% from 103 to 81 seconds (P < 0.001).
CONCLUSIONS: Using a DL-CAD system increased the diagnostic accuracy in detecting highly suspicious prostate lesions and reduced both the interreader variability and the reading time.
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.

Entities:  

Year:  2021        PMID: 33787537     DOI: 10.1097/RLI.0000000000000780

Source DB:  PubMed          Journal:  Invest Radiol        ISSN: 0020-9996            Impact factor:   6.016


  5 in total

Review 1.  Deep learning-based artificial intelligence applications in prostate MRI: brief summary.

Authors:  Baris Turkbey; Masoom A Haider
Journal:  Br J Radiol       Date:  2021-12-03       Impact factor: 3.039

2.  Assessing the clinical performance of artificial intelligence software for prostate cancer detection on MRI.

Authors:  Tobias Penzkofer; Anwar R Padhani; Baris Turkbey; Hashim U Ahmed
Journal:  Eur Radiol       Date:  2022-02-23       Impact factor: 7.034

3.  Textured-Based Deep Learning in Prostate Cancer Classification with 3T Multiparametric MRI: Comparison with PI-RADS-Based Classification.

Authors:  Yongkai Liu; Haoxin Zheng; Zhengrong Liang; Qi Miao; Wayne G Brisbane; Leonard S Marks; Steven S Raman; Robert E Reiter; Guang Yang; Kyunghyun Sung
Journal:  Diagnostics (Basel)       Date:  2021-09-28

Review 4.  Abbreviated MR Protocols in Prostate MRI.

Authors:  Andreas M Hötker; Hebert Alberto Vargas; Olivio F Donati
Journal:  Life (Basel)       Date:  2022-04-07

Review 5.  Artificial Intelligence Based Algorithms for Prostate Cancer Classification and Detection on Magnetic Resonance Imaging: A Narrative Review.

Authors:  Jasper J Twilt; Kicky G van Leeuwen; Henkjan J Huisman; Jurgen J Fütterer; Maarten de Rooij
Journal:  Diagnostics (Basel)       Date:  2021-05-26
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.