Automatic detection of Gibbs artefact in MR images with transfer learning approach

被引:0
作者
Kocet, Laura [1 ]
Romaric, Katja [2 ]
Zibert, Janez [3 ]
机构
[1] Univ Med Ctr Maribor, Dept Radiol, Maribor, Slovenia
[2] Univ Ljubljana, Fac Med, Ctr Clin Physiol, Ljubljana, Slovenia
[3] Univ Ljubljana, Fac Hlth Sci, Ljubljana, Slovenia
关键词
Gibbs artefact; transfer learning; automatic detection; image quality control;
D O I
10.3233/THC-220234
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
BACKGROUND: Quality control of magnetic resonance imaging includes image validation, which covers also artefact detection. The daily manual review of magnetic resonance images for possible artefacts can be time-consuming, so automated methods for computer-assisted quality assessment of magnetic resonance imaging need to be developed. OBJECTIVE: The aim of this study was to develop automatic detection of Gibbs artefacts in magnetic resonance imaging using a deep learning method called transfer learning, and to demonstrate the potential of this approach for the development of an automatic quality control tool for the detection of such artefacts in magnetic resonance imaging. METHODS: The magnetic resonance image dataset of the scanned phantom for quality assurance was created using a turbo spin-echo pulse sequence in the transverse plane. Images were created to include Gibbs artefacts of varying intensities. The images were annotated by two independent reviewers. The annotated dataset was used to develop a method for Gibbs artefact detection using the transfer learning approach. The VGG-16, VGG-19, and ResNet-152 convolutional neural networks were used as pre-trained networks for transfer learning and compared using 5-fold cross-validation. RESULTS: All accuracies of the classification models were above 97%, while the AUC values were all above 0.99, confirming the high quality of the constructed models. CONCLUSION: We show that transfer learning can be successfully used to detect Gibbs artefacts on magnetic resonance images. The main advantages of transfer learning are that it can be applied on small training datasets, the procedures to build the models are not so complicated, and they do not require much computational power. This shows the potential of transfer learning for the more general task of detecting artefacts in magnetic resonance images of patients, which consequently can improve and speed up the process of quality assessment in medical imaging practice.
引用
收藏
页码:239 / 246
页数:8
相关论文
共 28 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
Arbane Mohamed, 2021, 2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH), P210, DOI 10.1109/IHSH51661.2021.9378739
[3]  
Arnold T.B., 2017, Journal of Open Source Software, V2, P296, DOI DOI 10.21105/JOSS.00296
[4]   Biomedical image augmentation using Augmentor [J].
Bloice, Marcus D. ;
Roth, Peter M. ;
Holzinger, Andreas .
BIOINFORMATICS, 2019, 35 (21) :4522-4524
[5]  
Bourne R, 2010, FUNDAMENTALS DIGITAL, P64
[6]   The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation [J].
Chicco, Davide ;
Totsch, Niklas ;
Jurman, Giuseppe .
BIODATA MINING, 2021, 14 (01) :1-22
[7]  
Erasmus L.J., 2004, S AFR J RADIOL, V8, P13, DOI 10.4102/sajr.v8i2.127
[8]  
Fantini I, 2018, 2018 INT WORKSHOP PA, P1, DOI [DOI 10.1109/PRNI.2018.8423948, 10.1109/PRNI.2018.8423948]
[9]   Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: An overview [J].
Gao, Jun ;
Jiang, Qian ;
Zhou, Bo ;
Chen, Daozheng .
MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2019, 16 (06) :6536-6561
[10]   Magnetic Resonance Imaging: Principles and Techniques: Lessons for Clinicians [J].
Grover, Vijay P. B. ;
Tognarelli, Joshua M. ;
Crossey, Mary M. E. ;
Cox, I. Jane ;
Taylor-Robinson, Simon D. ;
McPhail, Mark J. W. .
JOURNAL OF CLINICAL AND EXPERIMENTAL HEPATOLOGY, 2015, 5 (03) :246-255