Literature DB >> 29761358

Deep learning for staging liver fibrosis on CT: a pilot study.

Koichiro Yasaka1, Hiroyuki Akai1, Akira Kunimatsu1, Osamu Abe2, Shigeru Kiryu3.   

Abstract

OBJECTIVES: To investigate whether liver fibrosis can be staged by deep learning techniques based on CT images.
METHODS: This clinical retrospective study, approved by our institutional review board, included 496 CT examinations of 286 patients who underwent dynamic contrast-enhanced CT for evaluations of the liver and for whom histopathological information regarding liver fibrosis stage was available. The 396 portal phase images with age and sex data of patients (F0/F1/F2/F3/F4 = 113/36/56/66/125) were used for training a deep convolutional neural network (DCNN); the data for the other 100 (F0/F1/F2/F3/F4 = 29/9/14/16/32) were utilised for testing the trained network, with the histopathological fibrosis stage used as reference. To improve robustness, additional images for training data were generated by rotating or parallel shifting the images, or adding Gaussian noise. Supervised training was used to minimise the difference between the liver fibrosis stage and the fibrosis score obtained from deep learning based on CT images (FDLCT score) output by the model. Testing data were input into the trained DCNNs to evaluate their performance.
RESULTS: The FDLCT scores showed a significant correlation with liver fibrosis stage (Spearman's correlation coefficient = 0.48, p < 0.001). The areas under the receiver operating characteristic curves (with 95% confidence intervals) for diagnosing significant fibrosis (≥ F2), advanced fibrosis (≥ F3) and cirrhosis (F4) by using FDLCT scores were 0.74 (0.64-0.85), 0.76 (0.66-0.85) and 0.73 (0.62-0.84), respectively.
CONCLUSIONS: Liver fibrosis can be staged by using a deep learning model based on CT images, with moderate performance. KEY POINTS: • Liver fibrosis can be staged by a deep learning model based on magnified CT images including the liver surface, with moderate performance. • Scores from a trained deep learning model showed moderate correlation with histopathological liver fibrosis staging. • Further improvement are necessary before utilisation in clinical settings.

Entities:  

Keywords:  Artificial intelligence; Liver cirrhosis; Multidetector computed tomography; ROC curve

Mesh:

Year:  2018        PMID: 29761358     DOI: 10.1007/s00330-018-5499-7

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  25 in total

1.  Liver biopsy.

Authors:  Don C Rockey; Stephen H Caldwell; Zachary D Goodman; Rendon C Nelson; Alastair D Smith
Journal:  Hepatology       Date:  2009-03       Impact factor: 17.425

2.  Zero-Echo-Time and Dixon Deep Pseudo-CT (ZeDD CT): Direct Generation of Pseudo-CT Images for Pelvic PET/MRI Attenuation Correction Using Deep Convolutional Neural Networks with Multiparametric MRI.

Authors:  Andrew P Leynes; Jaewon Yang; Florian Wiesinger; Sandeep S Kaushik; Dattesh D Shanbhag; Youngho Seo; Thomas A Hope; Peder E Z Larson
Journal:  J Nucl Med       Date:  2017-10-30       Impact factor: 10.057

Review 3.  Evaluation of hepatic fibrosis: a review from the society of abdominal radiology disease focus panel.

Authors:  Jeanne M Horowitz; Sudhakar K Venkatesh; Richard L Ehman; Kartik Jhaveri; Patrick Kamath; Michael A Ohliger; Anthony E Samir; Alvin C Silva; Bachir Taouli; Michael S Torbenson; Michael L Wells; Benjamin Yeh; Frank H Miller
Journal:  Abdom Radiol (NY)       Date:  2017-08

4.  Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging.

Authors:  Luciano M Prevedello; Barbaros S Erdal; John L Ryu; Kevin J Little; Mutlu Demirer; Songyue Qian; Richard D White
Journal:  Radiology       Date:  2017-07-03       Impact factor: 11.105

5.  Hepatosplenic volumetric assessment at MDCT for staging liver fibrosis.

Authors:  Perry J Pickhardt; Kyle Malecki; Oliver F Hunt; Claire Beaumont; John Kloke; Timothy J Ziemlewicz; Meghan G Lubner
Journal:  Eur Radiol       Date:  2016-11-17       Impact factor: 5.315

6.  Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging.

Authors:  Fang Liu; Hyungseok Jang; Richard Kijowski; Tyler Bradshaw; Alan B McMillan
Journal:  Radiology       Date:  2017-09-19       Impact factor: 11.105

Review 7.  Deep learning with convolutional neural network in radiology.

Authors:  Koichiro Yasaka; Hiroyuki Akai; Akira Kunimatsu; Shigeru Kiryu; Osamu Abe
Journal:  Jpn J Radiol       Date:  2018-03-01       Impact factor: 2.374

8.  Diagnosis of cirrhosis by transient elastography (FibroScan): a prospective study.

Authors:  J Foucher; E Chanteloup; J Vergniol; L Castéra; B Le Bail; X Adhoute; J Bertet; P Couzigou; V de Lédinghen
Journal:  Gut       Date:  2005-07-14       Impact factor: 23.059

Review 9.  Hepatocellular carcinoma.

Authors:  Alejandro Forner; Josep M Llovet; Jordi Bruix
Journal:  Lancet       Date:  2012-02-20       Impact factor: 79.321

10.  Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging.

Authors:  Ken Chang; Harrison X Bai; Hao Zhou; Chang Su; Wenya Linda Bi; Ena Agbodza; Vasileios K Kavouridis; Joeky T Senders; Alessandro Boaro; Andrew Beers; Biqi Zhang; Alexandra Capellini; Weihua Liao; Qin Shen; Xuejun Li; Bo Xiao; Jane Cryan; Shakti Ramkissoon; Lori Ramkissoon; Keith Ligon; Patrick Y Wen; Ranjit S Bindra; John Woo; Omar Arnaout; Elizabeth R Gerstner; Paul J Zhang; Bruce R Rosen; Li Yang; Raymond Y Huang; Jayashree Kalpathy-Cramer
Journal:  Clin Cancer Res       Date:  2017-11-22       Impact factor: 13.801

View more
  21 in total

Review 1.  Technical and clinical overview of deep learning in radiology.

Authors:  Daiju Ueda; Akitoshi Shimazaki; Yukio Miki
Journal:  Jpn J Radiol       Date:  2018-12-01       Impact factor: 2.374

2.  Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network.

Authors:  Jeong Hyun Lee; Ijin Joo; Tae Wook Kang; Yong Han Paik; Dong Hyun Sinn; Sang Yun Ha; Kyunga Kim; Choonghwan Choi; Gunwoo Lee; Jonghyon Yi; Won-Chul Bang
Journal:  Eur Radiol       Date:  2019-09-02       Impact factor: 5.315

3.  Performance Comparison of Individual and Ensemble CNN Models for the Classification of Brain 18F-FDG-PET Scans.

Authors:  Tomomi Nobashi; Claudia Zacharias; Jason K Ellis; Valentina Ferri; Mary Ellen Koran; Benjamin L Franc; Andrei Iagaru; Guido A Davidzon
Journal:  J Digit Imaging       Date:  2020-04       Impact factor: 4.056

4.  Non-invasive precise staging of liver fibrosis using deep residual network model based on plain CT images.

Authors:  Qiuju Li; Han Kang; Rongguo Zhang; Qiyong Guo
Journal:  Int J Comput Assist Radiol Surg       Date:  2022-02-22       Impact factor: 2.924

Review 5.  Liver fibrosis quantification.

Authors:  Sudhakar K Venkatesh; Michael S Torbenson
Journal:  Abdom Radiol (NY)       Date:  2022-01-12

6.  A radiomics-based model on non-contrast CT for predicting cirrhosis: make the most of image data.

Authors:  Jin-Cheng Wang; Rao Fu; Xue-Wen Tao; Ying-Fan Mao; Fei Wang; Ze-Chuan Zhang; Wei-Wei Yu; Jun Chen; Jian He; Bei-Cheng Sun
Journal:  Biomark Res       Date:  2020-09-17

7.  A radiomics-based model to classify the etiology of liver cirrhosis using gadoxetic acid-enhanced MRI.

Authors:  Aboelyazid Elkilany; Uli Fehrenbach; Timo Alexander Auer; Tobias Müller; Wenzel Schöning; Bernd Hamm; Dominik Geisel
Journal:  Sci Rep       Date:  2021-05-24       Impact factor: 4.379

8.  Multiparametric ultrasomics of significant liver fibrosis: A machine learning-based analysis.

Authors:  Wei Li; Yang Huang; Bo-Wen Zhuang; Guang-Jian Liu; Hang-Tong Hu; Xin Li; Jin-Yu Liang; Zhu Wang; Xiao-Wen Huang; Chu-Qing Zhang; Si-Min Ruan; Xiao-Yan Xie; Ming Kuang; Ming-De Lu; Li-Da Chen; Wei Wang
Journal:  Eur Radiol       Date:  2018-09-03       Impact factor: 5.315

Review 9.  Noninvasive staging of liver fibrosis: review of current quantitative CT and MRI-based techniques.

Authors:  Won Hyeong Im; Ji Soo Song; Weon Jang
Journal:  Abdom Radiol (NY)       Date:  2021-07-06

10.  Construction of a convolutional neural network classifier developed by computed tomography images for pancreatic cancer diagnosis.

Authors:  Han Ma; Zhong-Xin Liu; Jing-Jing Zhang; Feng-Tian Wu; Cheng-Fu Xu; Zhe Shen; Chao-Hui Yu; You-Ming Li
Journal:  World J Gastroenterol       Date:  2020-09-14       Impact factor: 5.742

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.