Literature DB >> 31958630

Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time.

Guilherme Moura Cunha1, Kyle A Hasenstab2, Atsushi Higaki3, Kang Wang4, Timo Delgado3, Ryan L Brunsing5, Alexandra Schlein3, Armin Schwartzman6, Albert Hsiao7, Claude B Sirlin3, Katie J Fowler3.   

Abstract

PURPOSE: To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations.
METHODS: We retrospectively identified EOB-enhanced MRI-HBP series from examinations performed 2011-2018 (internal and external datasets). Our algorithm, comprising a liver segmentation and classification CNN, produces an adequacy score. Two abdominal radiologists independently classified series as adequate or suboptimal. The consensus determination of HBP adequacy was used as ground truth for CNN model training and validation. Reader agreement was evaluated with Cohen's kappa. Performance of the algorithm was assessed by receiver operating characteristics (ROC) analysis and computation of the area under the ROC curve (AUC). Potential examination duration reduction was evaluated descriptively.
RESULTS: 1408 HBP series from 484 patients were included. Reader kappa agreement was 0.67 (internal dataset) and 0.80 (external dataset). AUCs were 0.97 (0.96-0.99) for internal and 0.95 (0.92-96) for external and were not significantly different from each other (p = 0.24). 48 % (50/105) examinations could have been shorter by applying the algorithm.
CONCLUSION: A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Gd-EOB-DTPA; Liver; Magnetic resonance imaging

Mesh:

Substances:

Year:  2020        PMID: 31958630      PMCID: PMC7309446          DOI: 10.1016/j.ejrad.2020.108837

Source DB:  PubMed          Journal:  Eur J Radiol        ISSN: 0720-048X            Impact factor:   3.528


  23 in total

1.  Respiratory motion correction for free-breathing 3D abdominal MRI using CNN-based image registration: a feasibility study.

Authors:  Jun Lv; Ming Yang; Jue Zhang; Xiaoying Wang
Journal:  Br J Radiol       Date:  2018-01-31       Impact factor: 3.039

2.  Gd-EOB-DTPA-enhanced 3.0 T MR imaging: quantitative and qualitative comparison of hepatocyte-phase images obtained 10 min and 20 min after injection for the detection of liver metastases from colorectal carcinoma.

Authors:  Keitaro Sofue; Masakatsu Tsurusaki; Hiroyuki Tokue; Yasuaki Arai; Kazuro Sugimura
Journal:  Eur Radiol       Date:  2011-07-12       Impact factor: 5.315

3.  Limitations of GD-EOB-DTPA-enhanced MRI: can clinical parameters predict suboptimal hepatobiliary phase?

Authors:  M Kobi; V Paroder; M Flusberg; A M Rozenblit; V Chernyak
Journal:  Clin Radiol       Date:  2016-11-11       Impact factor: 2.350

4.  The diagnostic advantage of EOB-MR imaging over CT in the detection of liver metastasis in patients with potentially resectable pancreatic cancer.

Authors:  Takaaki Ito; Teiichi Sugiura; Yukiyasu Okamura; Yusuke Yamamoto; Ryo Ashida; Takeshi Aramaki; Masahiro Endo; Katsuhiko Uesaka
Journal:  Pancreatology       Date:  2017-03-08       Impact factor: 3.996

Review 5.  The diagnostic value of Gd-EOB-DTPA-MRI for the diagnosis of focal nodular hyperplasia: a systematic review and meta-analysis.

Authors:  Chong Hyun Suh; Kyung Won Kim; Gene Young Kim; Yong Moon Shin; Pyo Nyun Kim; Seong Ho Park
Journal:  Eur Radiol       Date:  2014-12-24       Impact factor: 5.315

6.  Diagnostic per-patient accuracy of an abbreviated hepatobiliary phase gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance.

Authors:  Robert M Marks; Andrew Ryan; Elhamy R Heba; An Tang; Tanya J Wolfson; Anthony C Gamst; Claude B Sirlin; Mustafa R Bashir
Journal:  AJR Am J Roentgenol       Date:  2015-03       Impact factor: 3.959

Review 7.  Gadoxetic acid: pearls and pitfalls.

Authors:  Ryan B Schwope; Lauren A May; Michael J Reiter; Christopher J Lisanti; Daniel J A Margolis
Journal:  Abdom Imaging       Date:  2015-08

8.  A machine-learning framework for automatic reference-free quality assessment in MRI.

Authors:  T Küstner; S Gatidis; A Liebgott; M Schwartz; L Mauch; P Martirosian; H Schmidt; N F Schwenzer; K Nikolaou; F Bamberg; B Yang; F Schick
Journal:  Magn Reson Imaging       Date:  2018-07-21       Impact factor: 2.546

9.  Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks.

Authors:  Chi Zhang; Steen Moeller; Sebastian Weingärtner; Kâmil Uğurbil; Mehmet Akçakaya
Journal:  Conf Rec Asilomar Conf Signals Syst Comput       Date:  2019-02-21

10.  Optimization of hepatobiliary phase delay time of Gd-EOB-DTPA-enhanced magnetic resonance imaging for identification of hepatocellular carcinoma in patients with cirrhosis of different degrees of severity.

Authors:  Jian-Wei Wu; Yue-Cheng Yu; Xian-Li Qu; Yan Zhang; Hong Gao
Journal:  World J Gastroenterol       Date:  2018-01-21       Impact factor: 5.742

View more
  1 in total

1.  Alternative approach of hepatocellular carcinoma surveillance: abbreviated MRI.

Authors:  Ryan L Brunsing; Kathryn J Fowler; Takeshi Yokoo; Guilherme Moura Cunha; Claude B Sirlin; Robert M Marks
Journal:  Hepatoma Res       Date:  2020-09-01
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.