Abstract
Brachial plexopathy is a form of peripheral neuropathy, which occurs when there is damage to the brachial plexus (BP). However, the diagnosis of breast cancer related BP from radiological imaging is still a great challenge. This paper proposes a texture pattern based convolutional neural network, called TPPNet, to carry out abnormal prediction of BP from multiple routine magnetic resonance image (MRI) pulse sequences, i.e. T2, T1, and T1 post-gadolinium contrast administration. Different from classic CNNs, the input of the proposed TPPNet is multiple texture patterns instead of images. This allows for direct integration of radiomic (i.e. texture) features into the classification models. Beyond conventional radiomic features, we also developed a new family of texture patterns, called triple point patterns (TPPs), to extract huge number of texture patterns as representations of BPā heterogeneity from its MRIs. These texture patterns share the same size and show very stable properties under several geometric transformations. Then, the TPPNet is proposed to carry out the differentiation task of abnormal BP for our study. It has several special characteristics including 1) avoidance of image augmentation, 2) huge number of channels, 3) simple end-to-end architecture, 4) free from the interference of multi-texture-pattern arrangements. Ablation study and comparisons demonstrate that the proposed TPPNet yields outstanding performances with the accuracies of 96.1%, 93.5% and 93.6% over T2, T1 and post-gadolinium sequences which exceed at least 1.3%, 5.3% and 3.4% over state-of-the-art methods for classification of normal vs. abnormal brachial plexus.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shabeeb, D., Musa, A.E., et al.: Brachial plexopathy as a complication of radio-therapy: a systematic review. Curr. Cancer Ther. Rev. 15(2), 110ā120 (2020)
Wittenberg, K.H., Adkins, M.C.: MR imaging of nontraumatic brachial plex-opathies: frequency and spectrum of findings. Radiographics 20(4), 1024ā1032 (2004)
Nisce, L.Z., Chu, F.C.H.: Radiation therapy of brachial plexus syndrome from breast cancer. Radiology 91(5), 1022ā1025 (1968)
Lutz, A.M., Gold, G., Beaulieu, C.: MR imaging of the brachial plexus. Magn. Reson. Imaging Clin. N. Am. 20(4), 791ā826 (2012)
Wang, R., Shen, H., Zhou, M.: Ultrasound nerve segmentation of brachial plexus based on optimized resu-net. In: 2019 IEEE International Conference on Imaging Systems and Techniques (IST). pp. 1ā6 (2019)
Pisda, K., Jain, P., Sisodia, D.S.: Deep networks for brachial plexus nerves segmentation and detection using ultrasound images. In: Garg, L., Kesswani, N., Vella, J.G., Xuereb, P.A., Lo, M.F., Diaz, R., Misra, S., Gupta, V., Randhawa, P. (eds.) ISMS 2020. LNNS, vol. 303, pp. 132ā146. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-86223-7_13
Wang, Y., Geng, J., Zhou, C., Zhang, Y.: Segmentation of ultrasound brachial plexus based on u-net. In: 2021 International Conference on Communications, Information System and Computer Engineering (CISCE). pp. 482ā485 (2021)
Tian, D., Wang, Q., et al.: Brachial plexus nerve trunk recognition from ultra-sound images: a comparative study of deep learning models. IEEE Access 10, 82003ā82014 (2022)
Sureka, J., Cherian, R.A., Alexander, M., Thomas, B.P.: MRI of brachial plex-opathies. Clin. Radiol. 64(2), 208ā218 (2009)
Lambin, P., Leijenaar, R.T.H., et al.: Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 14(12), 749ā762 (2017)
van Griethuysen, J.J.M., Fedorov, A., et al.: Computational radiomics system to decode the radiographic phenotype. Can. Res. 77(21), e104āe107 (2017)
Ramel, A.A.: Analysis of membrane process model from black box to machine learning. J. Mach. Comput. 2(1), 2788ā7669 (2022)
Tan, J., Lei, B., et al.: 3D-GLCM CNN: a 3-dimensional gray-level cosoccur-rence matrix-based CNN model for polyp classification via CT colonography. IEEE Trans. Med. Imaging 39(6), 2013ā2024 (2020)
Yoo, T.S., Ackerman, M.J., et al.: Engineering and algorithm design for an image processing API: a technical report on ITK ā the insight toolkit. In: Westwood, J. (ed.) Proceeding of Medicine Meets Virtual Reality, pp. 586ā592 (2002)
McCormick, M., Liu, X., et al.: Enabling reproducible research and open science. Front. Neuroinform. 8, 13 (2014)
Isensee, F., Jaeger, P.F., et al.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203ā211 (2021)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971ā987 (2002)
Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE Trans. Image Process. 19(6), 1635ā1650 (2010)
ValliĆØres, M., Zwanenburg, A., et al.: Responsible radiomics research for faster clinical translation. J. Nucl. Med. 59(2), 189ā193 (2018)
GĆ¼ner, A., AlƧin, Ć.F., ÅengĆ¼r, A.: Automatic digital modulation classification using extreme learning machine with local binary pattern histogram features. Measurement 145, 214ā225 (2019)
Bian, M., Liu, J. K., et al.: Verifiable privacy-enhanced rotation invariant LBP feature extraction in fog computing. In: IEEE Transactions on Industrial Informatics (2023)
Cao, W., Liang, Z., Gao, Y., et al.: A dynamic lesion model for differentiation of malignant and benign pathologies. Sci. Rep. 11, 3485 (2021)
Galavis, P.E., Hollensen, C., et al.: Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters. Acta Oncol. 49(7), 1012ā1016 (2010)
Doumou, G., Siddique, M., Tsoumpas, C., et al.: The precision of textural analysis in 18F-FDG-PET scans of oesophageal cancer. Eur. Radiol. 25(9), 2805ā2812 (2015)
Wahid, K.A., He, R., et al.: Intensity standardization methods in magnetic reso-nance imaging of head and neck cancer. Phy. Imaging Radiat. Oncol. 20, 88ā93 (2021)
Cao, W., Pomeroy, M.J., et al.: Lesion classification by model-based feature extraction: a differential affine invariant model of soft tissue elasticity. arXiv pre-print arXiv:2205.14029 (2022)
Pomeroy, M.J., Pickhardt, P., Liang, J., Lu, H.: Histogram-based adaptive gray level scaling for texture feature classification of colorectal polyps. In: Medical Imaging 2018: Computer-Aided Diagnosis, vol. 10575, pp. 507ā513. SPIE (2018)
Simonyan, K., Zisserman, A.: Very deep convolution newtworks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Liu, W., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 1ā9 (2015)
Howard A.G., Zhu, M., et al.: MobileNets: efficient convolutional neural net-works for mobile vision applications. arXiv:1704.04861 (2017)
Wu, B., et al.: Visual transformers: where do transformers really belong in vi-sion models?. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 579ā589 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cao, W. et al. (2023). A Texture Neural Network to Predict the Abnormal Brachial Plexus from Routine Magnetic Resonance Imaging. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention ā MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14227. Springer, Cham. https://doi.org/10.1007/978-3-031-43993-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-43993-3_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43992-6
Online ISBN: 978-3-031-43993-3
eBook Packages: Computer ScienceComputer Science (R0)