Abstract
The fractal features of liver fibrosis MR images exhibit an irregular fragmented distribution, and the diffuse feature distribution lacks interconnectivity, result- ing in incomplete feature learning and poor recognition accuracy. In this paper, we insert recursive gated convolution into the ResNet18 network to introduce spatial information interactions during the feature learning process and extend it to higher orders using recursion. Higher-order spatial information interactions enhance the correlation between features and enable the neural network to focus more on the pixel-level dependencies, enabling a global interpretation of liver MR images. Additionally, the existence of light scattering and quantum noise during the imaging process, coupled with environmental factors such as breathing artifacts caused by long time breath holding, affects the quality of the MR images. To improve the classification performance of the neural network and better cap- ture sample features, we introduce the Adaptive Rebalance loss function and incorporate the feature paradigm as a learnable adaptive attribute into the angular margin auxiliary function. Adaptive Rebalance loss function can expand the inter-class distance and narrow the intra-class difference to further enhance discriminative ability of the model. We conduct extensive experiments on liver fibrosis MR imaging involving 209 patients. The results demonstrate an average improvement of two percent in recognition accuracy compared to ResNet18. The github is at https://github.com/XZN1233/paper.git.
Similar content being viewed by others
Data Availability
Due to the privacy of the patients, the data are only available upon request.
References
Liu Y, Wang X, Xu F, Li D, Yang H, Sun N, Fan YC, Yang X. Risk factors of chronic kidney disease in chronic hepatitis b:a hospital-based case- control study from china. J Clin Transl Hepatol. 2022;10(2):238–46.
Egger J, Gsxaner C, Pepe A, Li J. Medical deep learning – a systematic meta-review. Comput Methods and Prog Biomed. 2020;221:106874.
Castera L. Noninvasive methods to assess liver disease in patients with hepatitis b or c. Gastroenterology. 2012;142(6):1293–302.
Crossan C, Tsochatzis EA, Longworth L, Gurusamy K, Davidson B, Rodríguez-Perálvarez M, Mantzoukis K, O’Brien J, Thalassinos E, Papastergiou V, Burroughs A. Cost-effectiveness of non-invasive methods for assessment and monitor- ing of liver fibrosis and cirrhosis in patients with chronic liver disease: systematic review and economic evaluation. Health Technol Assess. 2015;19(9):1–410.
Kluwer, W.: Current opinion in gastroenterology. Curr Opin Gastroenterol. 2012;28(6):547–550.
Kremer S, Lersy F, De Sèze J, Ferré JC, Maamar A, Carsin-Nicol B, Collange O, Bonneville F, Adam G, Martin-Blondel G, Rafiq M. Brain mri findings in severe covid-19: a retrospective observational study. Radiology. 2020;297(2):E242–51.
Kandemirli SG, Dogan L, Sarikaya ZT, Kara S, Kocer N. Brain mri find- ings in patients in the intensive care unit with covid-19 infection. Radiology. 2020;297(1): 201697.
Woods JC, Wild JM, Wielpütz MO, Clancy JP, Hatabu H, Kauczor H-U, van Beek EJR, Altes TA. Current state of the art mri for the longitudinal assessment of cystic fibrosis. J Magnet Res Imag. 2019;52(5):1306–20.
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Comput Sci. 2014. https://doi.org/10.48550/arXiv.1409.1556.
Tan M, Le QV (2021) Efficientnetv2: Smaller models and faster training. International conference on machine learning, 2021;10096–10106.
Khan A, Sohail A, Zahoora U, Qureshi AS. A survey of the recent architec- tures of deep convolutional neural networks. Artif Intell Rev. 2019;53:5455–516.
Gore JC. Artificial intelligence in medical imaging. Magnet Res Imag. 2019;68:A1–4.
Debelee TG, Schwenker F, Ibenthal A, Yohannes D. Survey of deep learning in breast cancer image analysis. Evol Syst. 2020;11(1):143–63.
Gupta S, Gupta M (2021) Deep learning for brain tumor segmentation using magnetic resonance images. In: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
Lockard JS, Wyler AR. The influence of attending on seizure activity in epileptic monkeys. Epilepsia. 2010;20(2):157–68.
Huang S, Lee F, Miao R, Si Q, Chen Q. A deep convolutional neural network architecture for interstitial lung disease pattern classification. Med Biol Eng Comput. 2020;58(5):725–37.
Xiang K, Jiang B, Shang D. The overview of the deep learning integrated into the medical imaging of liver: a review. Hepatol Int. 2021;15:868–80.
Mahesh B.: Machine learning algorithms-a review. (IJSR). 2020;9(1):381–386.
Chan H, Hadjiiski LM, Samala RK. Computer-aided diagnosis in the era of deep learning. Med Phys. 2020. https://doi.org/10.1002/mp.13764.
Islam MM, Wu CC, Poly TN, Nguyen PAA, Li YCJ. Prediction of fatty liver disease using machine learning algorithms. Comput Methods Prog Biomed. 2019;170:23–9.
Li W, Huang Y, Zhuang BW, Liu GJ, Hu HT, Li X, Liang JY, Wang Z, Huang XW, Zhang, C.Q.a. Multiparametric ultrasomics of significant liver fibrosis: a machine learning-based analysis. Eur Radiol. 2019;29(3):1496–506.
Ayeldeen H, Shaker O, Ayeldeen G, Anwar KM (2016) Prediction of liver fibrosis stages by machine learning model: A decision tree approach. In: Third World Conference on Complex Systems, IEEE
House MJ, Bangma SJ, Thomas M, Gan EK, Ayonrinde OT, Adams LA, Olynyk JK, Pierre TGS. Texture-based classification of liver fibrosis using mri. J Magnet Res Imag. 2013;41(2):322–8.
Barry B, Buch K, Soto JA, Jara H, Anderson SW. Quantifying liver fibro- sis through the application of texture analysis to diffusion weighted imaging. Magn Reson Imag. 2013;32(1):84–90.
Sheth D, Giger ML. Artificial intelligence in the interpretation of breast cancer on mri. J Magnet Res Imag. 2019;51(5):1310–24.
Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S. Deep learning for staging liver fibrosis on ct: a pilot study. Eur Radiol. 2018;28(11):4578–85.
Chen M, Zhang B, Topatana W, Cao J, Cai X. Classification and mutation prediction based on histopathology he images in liver cancer using deep learning. npj Precis Oncol. 2020;4(1):14.
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016;2818–2826.
Zhen SH, Cheng M, Tao YB, Wang YF, Cai XJ. Deep learning for accu- rate diagnosis of liver tumor based on magnetic resonance imaging and clinical data. Front Oncol. 2020. https://doi.org/10.3389/fonc.2020.00680.
Das B, Toraman S. Deep transfer learning for automated liver cancer gene recognition using spectrogram images of digitized dna sequences. Biomed Signal Process Control. 2022;72:103317.
Rao Y, Zhao W, Zhu Z, Lu J, Zhou J. Global filter networks for image classification. Adv Neural Inform Process Syst. 2021;34:980–93.
Ding X, Zhang X, Zhou Y, Han J, Ding G, Sun J (2022) Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. arXiv e-prints
Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: Attention over convolution kernels. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020;11030–11039.
Zhu Z, Xu, M., Bai, S., Huang, T., Bai, X., Zhu, Z.: Asymmetric Non-local Neural Networks for Semantic Segmentation. Proceedings of the IEEE/CVF international conference on computer vision. 2019;593–602.
Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: Introducing convolutions to vision transformers. Proceedings of the IEEE/CVF international conference on computer vision. 2021
Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Vaswani, A.: Bottleneck trans- formers for visual recognition. Proceedings of the IEEE/CVF international conference on computer vision and pattern recognition. 2021;16519–16529
Ott, M., Edunov, S., Grangier, D., Auli, M.: Scaling neural machine translation. International conference on machine learning. 2018;3956–3965.
Wen Y, Zhang K, Li Z, Qiao Y. A discriminative feature learning approach for deep face recognition. In: Leibe B, Matas J, Sebe N, Welling M, editors. Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII. Cham: Springer; 2016.
Ranjan R, Castillo CD, Chellappa R (2017) L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507.
Wang F, Xiang X, Cheng J, Yuille AL (2017) Normface: l2 hypersphere embedding for face verification. arXiv
Deng, J., Guo, J., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. 2019;4690–4699.
Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021;12884–12893
Wang H, Wang Y, Zhou Z, Ji X, Gong D, Zhou J, Li Z, Liu W (2018) Cos- face: Large margin cosine loss for deep face recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Wang F, Cheng J, Liu W, Liu H. Additive margin softmax for face verification. IEEE Signal Process Lett. 2018;25(7):926–30.
Rao Y, Zhao W, Tang Y, Zhou J, Lim S-N, Lu J (2022) HorNet: Effi- cient high-order spatial interactions with recursive gated convolutions (2022) arXiv:2207.14284 [cs.CV]
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localiza- tion. In: IEEE International Conference on Computer Vision (2017)
Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. JMLR.org
Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. IEEE
Meng, Q., Zhao, S., Huang, Z., Zhou, F.: Magface: A universal representation for face recognition and quality assessment. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2021;14225–14234.
Kleiner DE, Brunt EM, Van Natta M, Behling C, Contos MJ, Cummings OW, Ferrell LD, Liu Y-C, Torbenson MS, Unalp-Arida A, Yeh M, McCullough AJ, Sanyal AJ. Design and validation of a histological scoring system for nonalcoholic fatty liver disease. Hepatology. 2005;41(6):1313–21.
Niu S, Liu Y, Wang J, Song H. A decade survey of transfer learning. IEEE Trans Artif Intell. 2020;1(2):151–66.
Deng J.: A large-scale hierarchical image database. Proc. of IEEE Computer Vision and Pattern Recognition. 2009
Sompong C, Wongthanavasu S (2014) Mri brain tumor segmentation using glcm cellular automata-based texture feature. In: Computer Science Engineering Conference. 192–197
Saihood A, Karshenas H, Nilchi ARN. Deep fusion of gray level co- occurrence matrices for lung nodule classification. PLoS ONE. 2022;17(9):e0274516.
Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101.
Davies WS. Digital image processing methods. Optics and Lasers in Eng. 1994;4:250–1.
Acknowledgements
This study was funded partly by Guangdong Science and Technology Plan Project (2019B010139001, 2021B1212100004), Guangdong Natural Science Fund Project (2021A1515011243) and Guangzhou Science and Technology Plan Project (201902020016).
Funding
Natural Science Foundation of Guangdong Province, 2021A1515011243, Wenchao Jiang
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no confict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, L., Xiao, Z., Jiang, W. et al. Liver fibrosis MR images classification based on higher-order interaction and sample distribution rebalancing. Health Inf Sci Syst 11, 51 (2023). https://doi.org/10.1007/s13755-023-00255-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13755-023-00255-6