Abstract
Morphological classification of human sperm heads is a key technology for diagnosing male infertility. Due to its sparse representation and learning capability, dictionary learning has shown remarkable performance in human sperm head classification. To promote the discriminability of the classification model, a novel local constraint and label embedding multi-layer dictionary learning model called LCLM-MDL is proposed in this study. Based on the multi-layer dictionary learning framework, two dictionaries are built on the basis of Laplacian regularized constraint and label embedding term in each layer, and the two dictionaries are approximated to each other as much as possible, so as to well exploit the nonlinear structure and discriminability features of the morphology of human sperm heads. In addition, to promote the robustness of the model, the asymmetric Huber loss is adopted in the last layer of LCLM-MDL, which approximates the misclassification error by using the absolute error function. Finally, the experimental results on HuSHeM dataset demonstrate the validity of the LCLM-MDL.
- [1] . 2017. Gold-standard for computer-assisted morphological sperm analysis. Computers in Biology and Medicine 83, 4 (2017), 143–150, https://doi.org/10.1016/j.compbiomed.2017.03.004 Google Scholar
Digital Library
- [2] . 2017. Automatic classification of human sperm head morphology. Computers in Biology and Medicine 84, 5 (2017), 205–216, https://doi.org/10.1016/j.compbiomed.2017.03.029 Google Scholar
Digital Library
- [3] . 2018. Automatic human sperm concentration in microscopic videos. Medical Technologies 2, 4 (2018), 301–307. https://doi.org/10.26415/2572-004X-vol2iss4p301-307Google Scholar
Cross Ref
- [4] WHO. 2010. World Health Organization-Laboratory Manual for the Examination and Processing of Human Semen. 5th Edition, Cambridge University Press, 2010.Google Scholar
- [5] . 2019. Deep learning for the classification of human sperm. Computers in Biology and Medicine 111, 8 (2019), 103342. https://doi.org/10.1016/j.compbiomed.2019.103342Google Scholar
Cross Ref
- [6] . 2019. Deep learning-based selection of human sperm with high DNA integrity. Communications Biology 2, 1 (2019), 250. https://doi.org/10.1038/s42003-019-0491-6Google Scholar
Cross Ref
- [7] . 2017. Automated analysis of individual sperm cells using stain-free interferometric phase microscopy and machine learning. Cytometry Part A 91, 9 (2017), 893–900. https://doi.org/10.1002/cyto.a.23189Google Scholar
Cross Ref
- [8] . 2020. A fully automated hybrid human sperm detection and classification system based on mobile-net and the performance comparison with conventional methods. Medical & Biological Engineering & Computing, 58, (2020), 1047–1068. https://doi.org/10.1007/s11517-019-02101-yGoogle Scholar
Cross Ref
- [9] . 2020. Deep learning-based morphological classification of human sperm heads. Diagnostics 10, 5 (2020), 325. https://doi.org/10.3390/diagnostics10050325Google Scholar
Cross Ref
- [10] . 2014. Gold-standard and improved framework for spermhead segmentation. Computer Methods and Programs in Biomedicine 117, 2 (2014), 225–237. https://doi.org/10.1016/j.cmpb.2014.06.018 Google Scholar
Digital Library
- [11] . 2015. An efficient method for automatic morphological abnormality detection from human sperm images. Computer Methods and Programs in Biomedicine 122, 3 (2015), 409–420. https://doi.org/10.1016/j.cmpb.2015.08.013 Google Scholar
Digital Library
- [12] . 2018. Automated sperm morphology testing using artificial intelligence. Fertility and Sterility 110, (2018) e432. https://doi.org/10.1016/j.fertnstertGoogle Scholar
Cross Ref
- [13] and Seyed Abolghasem Mirroshandel. 2019. A novel deep learning method for automatic assessment of human sperm images. Computers in Biology and Medicine 109, 6 (2019), 182–194, https://doi.org/10.1016/j.compbiomed.2019.04.030Google Scholar
Cross Ref
- [14] . 2017. A dictionary learning approach for human sperm heads classification. Computers in Biology and Medicine 91, 12 (2017), 181–190. https://doi.org/10.1016/j.compbiomed.2017.10.009 Google Scholar
Digital Library
- [15] . 2018. Medical image denoising based on sparse dictionary learning and cluster ensemble soft computing-a fusion of foundations. Methodologies and Applications 22, 5 (2018), 1467–1473. https://doi.org/10.1007/s00500-017-2853-7 Google Scholar
Digital Library
- [16] . 2018. Joint medical image fusion, denoising and enhancement via discriminative low-rank sparse dictionaries learning. Pattern Recognition 79, 7 (2018), 130–146. https://doi.org/10.1016/j.patcog.2018.02.005Google Scholar
Cross Ref
- [17] . 2015. Content based medical image retrieval using dictionary learning. Neurocomputing 168, 11 (2015), 880–895. https://doi.org/10.1016/j.neucom.2015.05.036 Google Scholar
Digital Library
- [18] . 2020. Action recognition using form and motion modalities. ACM Transactions on Multimedia Computing, Communications, and Applications 16, 1 (2020), 22. https://doi.org/10.1145/3350840 Google Scholar
Digital Library
- [19] . 1997. Adaptive greedy approximations. Journal of Constructive Approximation 13, (1997), 57–98.Google Scholar
Cross Ref
- [20] . 2006. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Processing 54, 11 (2006), 4311–4322.
DOI: 10.1109/TSP.2006.881199 Google ScholarDigital Library
- [21] . 2018. Theoretical foundations of deep learning via sparse representations: A multilayer sparse model and its connection to convolutional neural networks. IEEE Signal Processing Magazine 35, 4 (2018), 72–89.
DOI: 10.1109/MSP.2018.2820224Google ScholarCross Ref
- [22] . 2020. Detection of abnormal brain in MRI via improved AlexNet and ELM optimized by chaotic bat algorithm. Neural Computing and Applications, Online. https://doi.org/10.1007/s00521-020-05082-4Google Scholar
- [23] . 2019. Pathological brain detection based on AlexNet and transfer learning. Journal of Computational Science 30, 1 (2019), 41–47. https://doi.org/10.1016/j.jocs.2018.11.008Google Scholar
Cross Ref
- [24] . 2016. Multi-layer dictionary learning for image classification. In Proceedings of the International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2016) 522–533, Springer, Cham. https://doi.org/10.1007/978-3-319-48680-2_46Google Scholar
Cross Ref
- [25] . 2019. Multi-layer discriminative dictionary learning with locality constraint for image classification. Pattern Recognition 91, 7 (2019), 135–146. https://doi.org/10.1016/j.patcog.2019.02.018Google Scholar
Cross Ref
- [26] . 2017. A locality-constrained and label embedding dictionary learning algorithm for image classification. IEEE Trans. Neural Networks and Learning Systems 28, 2 (2017), 278–293.
DOI: 10.1109/TNNLS.2015.2508025Google ScholarCross Ref
- [27] . 2010. Iteratively reweighted least squares classifier and its ℓ2- and ℓ1-regularized kernel versions. Bulletin of the Polish Academy of Sciences, Technical Sciences 58, 1 (2010), 171–182.
DOI: 10.2478/v10175-010-0018-2Google ScholarCross Ref
- [28] . 2020. Extreme vector machine for fast training on large data. International Journal of Machine Learning and Cybernetics 11, 1 (2020), 33–53. https://doi.org/10.1007/s13042-019-00936-3Google Scholar
Cross Ref
- [29] . 2020. On pairing Huber support vector regression. Applied Soft Computing 10, 9 (2020), 106708. https://doi.org/10.1016/j.asoc.2020.106708Google Scholar
Cross Ref
- [30] . 2020. Robust regularized extreme learning machine with asymmetric Huber loss function. Neural Computing and Applications 32, 8 (2020), 12971–12998. https://doi.org/10.1007/s00521-020-04741-wGoogle Scholar
Digital Library
- [31] . 2019. Robust support vector regression in primal with asymmetric Huber loss. Neural Processing Letters 49, 7 (2019), 1399–1431. https://doi.org/10.1007/s11063-018-9875-8 Google Scholar
Digital Library
- [32] . 2017. Human sperm head morphology dataset (HuSHeM), Mendeley Data, 2017. Available at https://data.mendeley.com/datasets/tt3yj2pf38/1.Google Scholar
- [33] . 2013. Label consistent K-SVD: Learning a discriminative dictionary for recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 35, 11 (2013), 2651–2664.
DOI: 10.1109/TPAMI. 2013.88 Google ScholarDigital Library
- [34] . 2010. FSVM-CIL: Fuzzy support vector machines for class imbalance learning. IEEE Transactions on Fuzzy Systems 18, 3 (2010), 558–571.
DOI: 10.1109/TFUZZ.2010.2042721 Google ScholarDigital Library
- [35] . 2010. Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks. Journal of Neuroscience Methods 191, 1 (2010), 101–109. https://doi.org/10.1016/j.jneumeth.2010.05.020Google Scholar
Cross Ref
- [36] . 2020. Discriminative neural network for coronary heart disease detection. Journal of Medical Imaging and Health Informatics 10, 2 (2020), 463–468.
DOI: 10.1166/jmihi.2020.2900Google ScholarCross Ref
Index Terms
Local Constraint and Label Embedding Multi-layer Dictionary Learning for Sperm Head Classification
Recommendations
A dictionary learning approach for human sperm heads classification
Background and objectiveTo diagnose infertility in men, semen analysis is conducted in which sperm morphology is one of the factors that are evaluated. Since manual assessment of sperm morphology is time-consuming and subjective, automatic ...
Learn structured analysis discriminative dictionary for multi-label classification
AbstractMulti-label learning is a machine learning classification problem, in which an example belongs to more than one classes at the same time. Recently, multi-label learning has aroused a great deal of attention, and has achieved great success in the ...
Label embedded dictionary learning for image classification
AbstractRecently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error, classification error and discriminative sparse codes ...






Comments