Literature DB >> 34075548

Multichannel three-dimensional fully convolutional residual network-based focal liver lesion detection and classification in Gd-EOB-DTPA-enhanced MRI.

Tomomi Takenaga1, Shouhei Hanaoka2, Yukihiro Nomura3, Takahiro Nakao3, Hisaichi Shibata3, Soichiro Miki3, Takeharu Yoshikawa3, Naoto Hayashi3, Osamu Abe2.   

Abstract

PURPOSE: Gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) has high diagnostic accuracy in the detection of liver lesions. There is a demand for computer-aided detection/diagnosis software for Gd-EOB-DTPA-enhanced MRI. We propose a deep learning-based method using one three-dimensional fully convolutional residual network (3D FC-ResNet) for liver segmentation and another 3D FC-ResNet for simultaneous detection and classification of a focal liver lesion in Gd-EOB-DTPA-enhanced MRI.
METHODS: We prepared a five-phase (unenhanced, arterial, portal venous, equilibrium, and hepatobiliary phases) series as the input image sets and labeled focal liver lesion (hepatocellular carcinoma, metastasis, hemangiomas, cysts, and scars) images as the output image sets. We used 100 cases to train our model, 42 cases to determine the hyperparameters of our model, and 42 cases to evaluate our model. We evaluated our model by free-response receiver operating characteristic curve analysis and using a confusion matrix.
RESULTS: Our model simultaneously detected and classified focal liver lesions. In the test cases, the detection accuracy for whole focal liver lesions had a true-positive ratio of 0.6 at an average of 25 false positives per case. The classification accuracy was 0.790.
CONCLUSION: We proposed the simultaneous detection and classification of a focal liver lesion in Gd-EOB-DTPA-enhanced MRI using multichannel 3D FC-ResNet. Our results indicated simultaneous detection and classification are possible using a single network. It is necessary to further improve detection sensitivity to help radiologists.

Entities:  

Keywords:  Classification; Computer-aided detection/diagnosis (CAD); Convolutional neural network; Detection; Gd-EOB-DTPA; Liver

Year:  2021        PMID: 34075548     DOI: 10.1007/s11548-021-02416-y

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  5 in total

1.  Four-dimensional fully convolutional residual network-based liver segmentation in Gd-EOB-DTPA-enhanced MRI.

Authors:  Tomomi Takenaga; Shouhei Hanaoka; Yukihiro Nomura; Mitsutaka Nemoto; Masaki Murata; Takahiro Nakao; Soichiro Miki; Takeharu Yoshikawa; Naoto Hayashi; Osamu Abe
Journal:  Int J Comput Assist Radiol Surg       Date:  2019-03-30       Impact factor: 2.924

2.  Evaluation of motion correction for clinical dynamic contrast enhanced MRI of the liver.

Authors:  M J A Jansen; H J Kuijf; W B Veldhuis; F J Wessels; M S van Leeuwen; J P W Pluim
Journal:  Phys Med Biol       Date:  2017-09-12       Impact factor: 3.609

3.  Detection of hepatocellular carcinoma by Gd-EOB-DTPA-enhanced liver MRI: comparison with triple phase 64 detector row helical CT.

Authors:  Hiroyuki Akai; Shigeru Kiryu; Izuru Matsuda; Jirou Satou; Hidemasa Takao; Taku Tajima; Yasushi Watanabe; Hiroshi Imamura; Norihiro Kokudo; Masaaki Akahane; Kuni Ohtomo
Journal:  Eur J Radiol       Date:  2010-08-21       Impact factor: 3.528

4.  The varied appearances of hepatic cavernous hemangiomas with sonography, computed tomography, magnetic resonance imaging and scintigraphy.

Authors:  R L Bree; R E Schwab; G M Glazer; D Fink-Bennett
Journal:  Radiographics       Date:  1987-11       Impact factor: 5.333

5.  Gadoxetic acid-enhanced 3.0 T MR imaging versus multidetector-row CT in the detection of colorectal metastases in fatty liver using intraoperative ultrasound and histopathology as a standard of reference.

Authors:  V Berger-Kulemann; W Schima; S Baroud; C Koelblinger; K Kaczirek; T Gruenberger; M Schindl; J Maresch; M Weber; A Ba-Ssalamah
Journal:  Eur J Surg Oncol       Date:  2012-05-30       Impact factor: 4.424

  5 in total
  1 in total

1.  Imaging-based deep learning in liver diseases.

Authors:  Enyu Yuan; Zheng Ye; Bin Song
Journal:  Chin Med J (Engl)       Date:  2022-06-05       Impact factor: 6.133

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.