Abstract
Automatic segmentation of shoulder muscle MRI is challenging due to the high variation in muscle size, shape, texture, and spatial position of tears. Manual segmentation of tear and muscle portion is hard, time-consuming, and subjective to pathological expertise. This work proposes a new Region and Edge-based Deep Auto-Encoder (RE-DAE) for shoulder muscle MRI segmentation. The proposed RE-DAE harmoniously employs average and max-pooling operations in the Convolutional encoder and decoder blocks. The DAE’s region and edge-based segmentation encourage the network to extract homogenous and anatomical information, respectively. These two concepts, systematically combined in a DAE, generate a discriminative and sparse hybrid feature space (exploiting both region homogeneity and boundaries). Moreover, the concept of static attention is exploited in the proposed RE-DAE that helps effectively learn the tear region. The performances of the proposed RE-DAE architectures have been tested using a 3D MRI shoulder muscle dataset using the hold-out cross-validation technique. The MRI data has been collected from the Korea University Anam Hospital, Seoul, South Korea. Experimental comparisons have been conducted by employing innovative custom-made and existing pre-trained CNN architectures using transfer learning and fine-tuning. Objective evaluation on the muscle datasets using the proposed SA-RE-DAE showed a dice similarity of 85.58% and 87.07%, an accuracy of 81.57% and 95.58% for tear and muscle regions, respectively. The high visual quality and the objective result suggest that the proposed SA-RE-DAE can correctly segment tear and muscle regions in shoulder muscle MRI for better clinical decisions.
Similar content being viewed by others
References
Ahmad P, Jin H, Qamar S et al (2021) RD2A: densely connected residual networks using ASPP for brain tumor segmentation. Multimed Tools Appl 80:27069–27094
Ahmed U, Khan A, Khan SH et al (2019) Transfer learning and meta classification based deep churn prediction system for telecom industry. arXiv
Alipour N, Hasanzadeh RPR (2021) Superpixel-based brain tumor segmentation in MR images using an extended local fuzzy active contour model. Multimed Tools Appl 80:8835–8859
Badrinarayanan V, Mishra B, Cipolla R (2015) Understanding symmetries in deep networks
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495
Biltz NK, Meyer GA (2017) A novel method for the quantification of fatty infiltration in skeletal muscle. Skelet Muscle 7:1
Bresson X, Esedoglu S, Vandergheynst P et al (2007) Fast global minimization of the active contour/snake model. J Math Imaging Vis 28:151–167
Chahal ES, Patel A, Gupta A et al (2021) Unet based Xception model for prostate cancer segmentation from MRI images. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-11334-9
Çiçek Ö, Abdulkadir A, Lienkamp SS et al (2016) 3D U-net: Learning dense volumetric segmentation from sparse annotation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 9901 LNCS:424–432
Conze P-H, Brochard S, Burdin V et al (2020) Healthy versus pathological learning transferability in shoulder muscle MRI segmentation using deep convolutional encoder-decoders. Comput Med Imaging Graph 83:101733. https://doi.org/10.1016/j.compmedimag.2020.101733
DEPALMA AF (1963) Surgical anatomy of the rotator cuff and the natural history of degenerative periarthritis. Surg Clin North Am 43:1507–1520
Devi D, Namasudra S, Kadry S (2020) A boosting-aided adaptive cluster-based undersampling approach for treatment of class imbalance problem. Int J Data Warehous Min 16:60–86. https://doi.org/10.4018/IJDWM.2020070104
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. 32nd Int. Conf. Mach. Learn. ICML 2015 1, pp 448–456
Javed SG, Majid A, Mirza AM, Khan A (2016) Multi-denoising based impulse noise removal from images using robust statistical features and genetic programming. Multimed Tools Appl 75:5887–5916
Jiang J, Liu X, Zhang K et al (2017) Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network. Biomed Eng Online 16:132
Khagi B, Kwon GR (2018) Pixel-label-based segmentation of cross-sectional brain MRI using simplified segnet architecture-based CNN. J Healthc Eng 2018:2018
Khan SH, Sohail A, Khan A, Lee YS (2020) Classification and region analysis of COVID-19 infection using lung. CT images and deep convolutional neural networks
Khan SH, Yousaf MH, Murtaza F, Velastin S (2020) Passenger detection and counting for public transport system. NED Univ J Res XVII:35–46
Khan SH, Sohail A, Zafar MM, Khan A (2021) Coronavirus disease analysis using chest X-ray images and a novel deep convolutional neural network. Photodiagnosis Photodyn Ther 35:102473. https://doi.org/10.1016/j.pdpdt.2021.102473
Khan SH, Sohail A, Khan A et al (2021) COVID-19 detection in chest X-ray images using deep boosted hybrid learning. Comput Biol Med 137:104816
Khan SH, Sohail A, Khan A, Lee YS (2022) COVID-19 detection in chest X-ray images using a new channel boosted CNN. Diagnostics 12:267
Khan A, Hussain Khan S, Saif M et al A survey of deep learning techniques for the analysis of COVID-19 and their usability for detecting omicron
Kim S, Lee D, Park S et al (2017) Automatic segmentation of supraspinatus from MRI by internal shape fitting and autocorrection. Comput Methods Programs Biomed 140:165–174
Kim JY, Ro K, You S et al (2019) Development of an automatic muscle atrophy measuring algorithm to calculate the ratio of supraspinatus in supraspinous fossa using deep learning. Comput Methods Programs Biomed 182:105063
Kollias D, Tagaris A, Stafylopatis A et al (2018) Deep neural architectures for prediction in healthcare. Complex Intell Syst 4:119–131
Kumar GA, Sridevi PV (2021) E-fuzzy feature fusion and thresholding for morphology segmentation of brain MRI modalities. Multimed Tools Appl 80:19715–19735
Kumar P, Nagar P, Arora C, Gupta A (2018) U-segnet: fully convolutional neural network based automated brain tissue segmentation tool. arXiv
Lee H, Troschel FM, Tajmir S et al (2017) Pixel-level deep segmentation: artificial intelligence quantifies muscle on computed tomography for body morphometric analysis. J Digit Imaging 30:487–498
Li MW, Wang YT, Geng J, Hong WC (2021) Chaos cloud quantum bat hybrid optimization algorithm. Nonlinear Dyn 103:1167–1193
Mandić M, Rullman E, Widholm P et al (2020) Automated assessment of regional muscle volume and hypertrophy using MRI. Sci Rep 10:2239
Pavel M, Jimison HB, Wactlar HD et al (2013) The role of technology and engineering models in transforming healthcare. IEEE Rev Biomed Eng 6:156–177
Pons C, Sheehan FT, Im HS et al (2017) Shoulder muscle atrophy and its relation to strength loss in obstetrical brachial plexus palsy. Clin Biomech 48:80–87
Qureshi AS, Khan A (2018) Adaptive transfer learning in deep neural networks: wind power prediction using knowledge transfer from region to region and between different task domains. arXiv
Qureshi AS, Khan A, Zameer A, Usman A (2017) Wind power prediction using deep neural network based meta regression and transfer learning. Appl Soft Comput J 58:742–755
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 9351:234–241
Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39:640–651
Schlemper J, Oktay O, Schaap M et al (2019) Attention gated networks: learning to leverage salient regions in medical images. Med Image Anal 53:197–207
Slabaugh MA, Friel NA, Karas V et al (2012) Interobserver and intraobserver reliability of the goutallier classification using magnetic resonance imaging. Am J Sports Med 40:1728–1734
Singh LK, Pooja, Garg H et al (2021) An analytical study on machine learning techniques, pp 137–157
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp 1–14
Tian Y, Duan F, Zhou M, Wu Z (2013) Active contour model combining region and edge information. Mach Vis Appl 24:47–61
van G STJJM, L DMJ et al (2017) Deep Learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Sci Rep 7:5301
Vedaldi A, Lenc K (2015) MatConvNet: Convolutional neural networks for MATLAB. MM 2015 - Proc. 2015 ACM Multimed. Conf., pp 689–692
Ward AD, Hamarneh G, Ashry R, Schweitzer ME (2007) 3D shape analysis of the supraspinatus muscle. Acad Radiol 14:1229–1241
Ward AD, Hamarneh G, Ashry R, Schweitzer ME (2007) 3D shape analysis of the supraspinatus muscle. A clinical study of the relationship between shape and pathology. Acad Radiol 14:1229–1241
Zafar MM, Rauf Z, Sohail A et al (2022) Detection of tumour infiltrating lymphocytes in CD3 and CD8 stained histopathological images using a two-phase deep CNN. Photodiagnosis Photodyn Ther 37:102676. https://doi.org/10.1016/j.pdpdt.2021.102676
Zhang Z, Hong WC (2021) Application of variational mode decomposition and chaotic grey wolf optimizer with support vector regression for forecasting electric loads. Knowl Based Syst 228:107297
Zhang C, Hua Q-Q, Chu Y-Y, Wang P-W (2021) Liver tumor segmentation using 2.5D UV-Net with multi-scale convolution. Comput Biol Med 133:104424. https://doi.org/10.1016/j.compbiomed.2021.104424
Acknowledgements
This work was conducted with the support of the PIEAS IT endowment fund under the Pakistan Higher Education Commission (HEC). This study was also supported by the research grant of National Research Foundation of Korea (2017R1A2B2005065).As well as, we thank Pattern Recognition Lab (PR-Lab) and Pakistan Institute of Engineering, and Applied Sciences (PIEAS), for providing necessary computational resources and a healthy research environment.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors declared no conflict 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 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
Khan, S.H., Khan, A., Lee, Y.S. et al. Segmentation of shoulder muscle MRI using a new Region and Edge based Deep Auto-Encoder. Multimed Tools Appl 82, 14963–14984 (2023). https://doi.org/10.1007/s11042-022-14061-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14061-x