Share:
Share this content in WeChat
X
Clinical Article
The value of 3D convolution neural network based on multimodal MRI images in the classification of liver fibrosis
FAN Fengxian  HU Wanjun  JIANG Yanli  ZOU Jie  YANG Pin  ZHANG Jing 

Cite this article as: Fan FX, Hu WJ, Jiang YL, et al. The value of 3D convolution neural network based on multimodal MRI images in the classification of liver fibrosis[J]. Chin J Magn Reson Imaging, 2022, 13(9): 30-34. DOI:10.12015/issn.1674-8034.2022.09.006.


[Abstract] Objective To construct a 3D convolution neural network (CNN) model of multi-modal MRI images, and verify its value in classification of liver fibrosis (LF).Materials and Methods Two hundred and twenty four cases with LF confirmed by pathology were retrospectively collected. All patients underwent 3.0 T MRI exams. Collected the T1WI, T2WI, and apparent diffusion coefficient (ADC) images and randomly divided them into training group and testing group according to the ratio of 8∶2. After the images were preprocessed, the images of training group were used to iteratively train the network structure of the model. And then a 3D-CNN model was established to distinguish between no-significant LF (S0-S1) and significant LF (≥S2). The 3D-CNN model was composed of three convolution layers, three pooling layers and two fully connected layers. The accuracy (ACC), loss function curves and receiver operating characteristic (ROC) curves acquired by using the testing dataset were used to evaluate the performance of the 3D-CNN model.Results The area under the curve (AUC) value of 3D-CNN model based on multiparametric MRI for LF classification was 0.94 in the training group and 0.98 in the testing group.Conclusions The multiparametric 3D-CNN deep learning model may be an effective method, which can distinguish between no-significant and significant LF. It provides more options for non-invasive assessment of LF.
[Keywords] liver fibrosis;multimodal magnetic resonance imaging;machine learning;convolutional neural network

FAN Fengxian1, 2   HU Wanjun1, 2   JIANG Yanli1, 2   ZOU Jie1, 2   YANG Pin1, 2   ZHANG Jing1, 2*  

1 Department of Magnetic Resonance, Lanzhou University Second Hospital, Lanzhou 730030, China

2 Gansu Province Clinical Research Center for Functional and Molecular Imaging, Lanzhou 730030, China

*Zhang J, E-mail: lztong2001@163.com

Conflicts of interest   None.

Received  2022-04-02
Accepted  2022-08-19
DOI: 10.12015/issn.1674-8034.2022.09.006
Cite this article as: Fan FX, Hu WJ, Jiang YL, et al. The value of 3D convolution neural network based on multimodal MRI images in the classification of liver fibrosis[J]. Chin J Magn Reson Imaging, 2022, 13(9): 30-34.DOI:10.12015/issn.1674-8034.2022.09.006

[1]
GBD 2017 Cirrhosis Collaborators. The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017[J]. Lancet Gastroenterol Hepatol, 2020, 5(3): 245-266. DOI: 10.1016/S2468-1253(19)30349-8.
[2]
Ozkurt H, Keskiner F, Karatag O, et al. Diffusion weighted MRI for hepatic fibrosis: impact of b-value[J/OL]. Iran J Radiol, 2014, 11(1) [2022-04-02]. https://doi.org/10.5812/iranjradiol.3555. DOI: 10.5812/iranjradiol.3555.
[3]
Spann A, Yasodhara A, Kang J, et al. Applying machine learning in liver disease and transplantation: a comprehensive review[J]. Hepatology, 2020, 71(3): 1093-1105. DOI: 10.1002/hep.31103.
[4]
Yasaka K, Akai H, Kunimatsu A, et al. Liver fibrosis: deep convolutional neural network for staging by using gadoxetic acid-enhanced hepatobiliary phase MR images[J]. Radiology, 2018, 287(1): 146-155. DOI: 10.1148/radiol.2017171928.
[5]
Sun YM, Zhou JL, Wang L, et al. New classification of liver biopsy assessment for fibrosis in chronic hepatitis B patients before and after treatment[J]. Hepatology, 2017, 65(5): 1438-1450. DOI: 10.1002/hep.29009.
[6]
Chinese Medical Association Hepatology Branch, Chinese Medical Association Digestive Disease Branch, Chinese Medical Association Infectious Disease Branch.Consensus on diagnosis and treatment of hepatic fibrosis in 2019[J]. Chin J Gastroenterol, 2019, 24(9): 546-556. DOI: 10.3969/j.issn.1008-7125.2019.09.007.
[7]
Park HJ, Park B, Lee SS. Radiomics and deep learning: hepatic applications[J]. Korean J Radiol, 2020, 21(4): 387-401. DOI: 10.3348/kjr.2019.0752.
[8]
Choi KJ, Jang JK, Lee SS, et al. Development and validation of a deep learning system for staging liver fibrosis by using contrast agent-enhanced CT images in the liver[J]. Radiology, 2018, 289(3): 688-697. DOI: 10.1148/radiol.2018180763.
[9]
Fu TT, Yao Z, Ding H, et al. Computer-aided assessment of liver fibrosis progression in patients with chronic hepatitis B: an exploratory research[J]. Natl Med J China, 2019, 99(7): 491-495. DOI: 10.3760/cma.j.issn.0376-2491.2019.07.003.
[10]
Lee JH, Joo I, Kang TW, et al. Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network[J]. Eur Radiol, 2020, 30(2): 1264-1273. DOI: 10.1007/s00330-019-06407-1.
[11]
Hectors SJ, Kennedy P, Huang KH, et al. Fully automated prediction of liver fibrosis using deep learning analysis of gadoxetic acid-enhanced MRI[J]. Eur Radiol, 2021, 31(6): 3805-3814. DOI: 10.1007/s00330-020-07475-4.
[12]
Bangalore Yogananda CG, Shah BR, Vejdani-Jahromi M, et al. A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas[J]. Neuro Oncol, 2020, 22(3): 402-411. DOI: 10.1093/neuonc/noz199.
[13]
Dou Q, Chen H, Yu LQ, et al. Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection[J]. IEEE Trans Biomed Eng, 2017, 64(7): 1558-1567. DOI: 10.1109/TBME.2016.2613502.
[14]
Yu JZ, Yang BH, Wang J, et al. 2versusD CNN 3D CNN for false-positive reduction in lung cancer screening[J/OL]. J Med Imaging (Bellingham), 2020, 7(5) [2022-04-02]. https://doi.org/10.1117/1.JMI.7.5.051202. DOI: 10.1117/1.JMI.7.5.051202.
[15]
Mzoughi H, Njeh I, Wali, et al. Deep multi-scale 3D convolutional neural network (CNN) for MRI gliomas brain tumor classification[J]. J Digit Imaging, 2020, 33(4): 903-915. DOI: 10.1007/s10278-020-00347-9.
[16]
Hu QY, Whitney HM, Giger ML. A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI[J/OL]. Sci Rep, 2020, 10 [2022-04-02]. https://www.nature.com/articles/s41598-020-67441-4. DOI: 10.1038/s41598-020-67441-4.
[17]
Park HJ, Lee SS, Park B, et al. Radiomics analysis of gadoxetic acid-enhanced MRI for staging liver fibrosis[J/OL]. Radiology, 2019, 292(1) [2022-04-02]. https://doi.org/10.1148/radiol.2019194012. DOI: 10.1148/radiol.2019194012.
[18]
Schawkat K, Ciritsis A, von Ulmenstein S, et al. Diagnostic accuracy of texture analysis and machine learning for quantification of liver fibrosis in MRI: correlation with MR elastography and histopathology[J]. Eur Radiol, 2020, 30(8): 4675-4685. DOI: 10.1007/s00330-020-06831-8.
[19]
Pan YQ, Chen R, Zhang X, et al. Precancerous diseases classification based on fusion of shallow and deep features[J]. Chin J Biomed Eng, 2020, 39(4): 413-421. DOI: 10.3969/j.issn.0258-8021.2020.04.004.
[20]
Liu ZY, Wang S, Dong D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges[J]. Theranostics, 2019, 9(5): 1303-1322. DOI: 10.7150/thno.30309.
[21]
Pepin KM, Welle CL, Guglielmo FF, et al. Magnetic resonance elastography of the liver: everything You need to know to get started[J]. Abdom Radiol (NY), 2022, 47(1): 94-114. DOI: 10.1007/s00261-021-03324-0.

PREV Comparative assessment of MRI BI-RADS 4 breast lesions with Kaiser score and apparent diffusion coefficient value
NEXT Correlation between Gd-EOB-DTPA enhanced MRI T1 mapping and Ki-67 expression in hepatocellular carcinoma
  



Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn