Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-learned Features

• Autorzy: Czaplewski Bartosz , Dzwonkowski Mariusz , Panas Damian

Identyfikatory

DOI

10.26636/jtit.2022.165322

• Języki publikacji: EN

Abstrakty

EN

Nematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed approach relies on deep learning techniques, specifically on convolutional neural networks (CNNs), to solve the problem and achieve high classification accuracy by focusing on non-handcrafted self-learned features. Various networks known from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) have been investigated and adapted for the purposes of the C. elegans muscle aging dataset by applying transfer learning and data augmentation techniques. The proposed approach of unfreezing different numbers of convolutional layers at the feature extraction stage and introducing different structures of newly trained fully connected layers at the classification stage, enable to better fine-tune the selected networks. The adjusted CNNs, as featured in this paper, have been compared with other state-of-art methods. In anti-aging drug research, the proposed CNNs would serve as a very fast and effective age determination method, thus leading to reductions in time and costs of laboratory research.

Słowa kluczowe

EN

biomedical imaging; Caenorhabditis elegans muscle aging; convolutional neural networks; deep learning; machine learning

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2022
• Tom: nr 4
• Strony: 85--94
• Opis fizyczny: Bibliogr. 41 poz., rys., wykr.

Twórcy

autor

Czaplewski Bartosz

• Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, Department of Teleinformation Networks, Poland

• https://orcid.org/0000-0001-7904-5567

autor

Dzwonkowski Mariusz

• Gdańsk University of Technology, Faculty of Electronics, Telecommunications and Informatics, Department of Teleinformation Networks, Poland
• Medical University of Gdańsk, Faculty of Health Sciences, Department of Radiology Informatics and Statistics, Poland

• https://orcid.org/0000-0003-3580-7448

autor

Panas Damian

• Institute of Animal Reproduction and Food Research of the Polish Academy of Sciences, Molecular Biology Laboratory, Poland

• https://orcid.org/0000-0003-2181-2414

Bibliografia

• [1] A.G. Alexander, et al., “Use of Caenorhabditis elegans as a model to study Alzheimer’s disease and other neurodegenerative diseases”, Front. Genet., vol. 5, 2014 (DOI: 10.3389/fgene.2014.00279).
• [2] E. Moreno-Arriola, et al., “Caenorhabditis elegans: A useful model for studying metabolic disorders in which oxidative stress is a contributing factor”, Oxid. Med. Cell. Longev., vol. 2014, 2014 (DOI: 10.1155/2014/705253).
• [3] A.E. Apostolakou, et al., “Exploring the conservation of Alzheimer related pathways between H. sapiens and C. elegans: a network alignment approach”, Sci. Rep., vol. 11, no. 1, 2021 (DOI: 10.1038/s41598- 021-83892-9).
• [4] K. Podshivalova, et al., “How a mutation that slows aging can also disproportionately extend end-of-life decrepitude”, Cell Rep., vol. 19, no. 3, pp. 441–450, 2017 (DOI: 10.1016/j.celrep.2017.03.062).
• [5] M.M. Abdelsamea, “A semi-automated system based on level sets and invariant spatial interrelation shape features for Caenorhabditis elegans phenotypes”, J. Vis. Commun. Image Represent., vol. 41, pp. 314–323, 2016 (DOI: 10.1016/j.jvcir.2016.10.011).
• [6] H.A. Tissenbaum, “Using C. elegans for aging research”, Invertebr. Reprod. Dev., vol. 59, no. sup1, pp. 59–63, 2015 (DOI: 10.1080/07924259.2014.940470).
• [7] S. Zhang, F. Li, T. Zhou, G. Wang, and Z. Li, “Caenorhabditis elegans as a useful model for studying aging mutations”, Front. Endocrinol. (Lausanne), vol. 11, 2020 (DOI: 10.3389/fendo.2020.554994).
• [8] J.J. Collins et al., “The measurement and analysis of age-related changes in Caenorhabditis elegans”, WormBook: The Online Review of C. elegans Biology. Pasadena, CA, WormBook, 2005–2018 (URL: https://www.ncbi.nlm.nih.gov/books/NBK116075/). \
• [9] D.S. Wilkinson, R.C. Taylor, and A. Dillin, “Analysis of aging in Caenorhabditis elegans”, Methods Cell Biol., vol. 107, pp. 353–381, 2012 (DOI: 10.1016/B978-0-12-394620-1.00012-6).
• [10] L.A. Herndon, et al., “Stochastic and genetic factors influence tissue specific decline in ageing C. elegans”, Nature, vol. 419, no. 6909, pp. 808–814, 2002 (DOI: 10.1038/nature01135).
• [11] H.G. Son, O. Altintas, E.J.E. Kim, S. Kwon, and S-J.V. Lee, “Age dependent changes and biomarkers of aging in Caenorhabditis elegans”, Aging Cell, vol. 18, no. 2, 2019 (DOI: 10.1111/acel.12853).
• [12] G.J. Lithgow, “The Future of Worm Ageing”, Ageing: Lessons from C. elegans. Healthy Ageing and Longevity, A. Olsen, M. Gill, Eds., Switzerland, Cham: Springer International Publishing, A. Olsen, M. Gill (eds) Ageing: Lessons from C. elegans. Healthy Ageing and Longevity. Springer, Cham., pp. 431–435 2017 (DOI: 10.1007/978- 3-319-44703-2_19).
• [13] A. Olsen and M.S. Gill, “Introduction in Ageing: Lessons from C. elegans. Healthy Ageing and Longevity, A. Olsen, M. Gill, Eds., Switzerland, Cham: Springer International Publishing, pp. 1–7, 2017 (DOI: 10.1007/978-3-319-44703-2_1).
• [14] D. Gems and L. Partridge, “Genetics of longevity in model organisms: debates and paradigm shifts”, Annu. Rev. Physiol., vol. 75, pp. 621– 644, 2013 (DOI: 10.1146/annurev-physiol-030212-183712).
• [15] S.S. Yadav and S.M. Jadhav, “Deep convolutional neural network based medical image classification for disease diagnosis”, J. Big Data, vol. 6, no. 133, 2019 (DOI: 10.1186/s40537-019-0276-2).
• [16] B. Czaplewski and M. Dzwonkowski, “A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification”, ISA Transactions, vol. 119, pp. 1–16, 2022 (DOI: 10.1016/j.isatra.2021.02.030).
• [17] B. Czaplewski, “An improved convolutional neural network for steganalysis in the scenario of reuse of the stego-key”, I. Tetko, V. Kåurková, P. Karpov, F. Theis (eds) Artificial Neural Networks and Machine Learning – ICANN 2019, Lecture Notes in Computer Science, vol. 11729, Springer, Cham. 2019 (DOI: 10.1007/978-3-030-30508- 6_7).
• [18] J. Zhang, K. Shao, and X. Luo, “Small sample image recognition using improved Convolutional Neural Network”, J. Vis. Commun. Image Represent., vol. 55, pp. 640–647, 2018 (DOI: 10.1016/j.jvcir.2018.07.011).
• [19] M. Claro, et al., “An hybrid feature space from texture information and transfer learning for glaucoma classification”, J. Vis. Commun. Image Represent., vol. 64, 102597, 2019 (DOI: 10.1016/j.jvcir.2019.102597).
• [20] C. Restif and D. Metaxas, “Tracking the Swimming Motions of C. elegans Worms with Applications in Aging Studies”, Med. Image Comput. Comput. Assist. Interv., D. Metaxas et al. Eds., Germany, Berlin, Heidelberg: Springer, vol. 5241, pp. 35–42, 2008 (DOI: 10.1007/978- 3-540-85988-8_5).
• [21] J. Johnston, W.B. Iser, D.K. Chow, I.G. Goldberg, and C.A. Wolkow, “Quantitative image analysis reveals distinct structural transitions during aging in Caenorhabditis elegans tissues”, PLoS One, vol. 3, no. 7, 2008 (DOI: 10.1371/journal.pone.0002821).
• [22] J-L. Lin, W.-L. Kuo, Y-H. Huang, T-L. Jong, A-L. Hsu, and W-H. Hsu, “Using convolutional neural networks to measure the physiological age of Caenorhabditis elegans”, IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 18, no. 6, pp. 2724–2732, 2021 (DOI: 10.1109/TCBB.2020.2971992).
• [23] L. Shamir, N. Orlov, D.M. Eckley, T. Macura, J. Johnston, and I.G. Goldberg, “Wndchrm – an open source utility for biological image analysis”, Source Code Biol. Med., vol. 3, no. 13, 2008 (DOI: 10.1186/1751-0473-3-13).
• [24] N. Orlov, L. Shamir, T. Macura, J. Johnston, D.M. Eckley, and I.G. Goldberg, “WND-CHARM: Multi-purpose image classification using compound image transforms”, Pattern Recognit. Lett., vol. 29, no. 11, pp. 1684–1693, 2008 (DOI: 10.1016/j.patrec.2008.04.013).
• [25] J. Zhou, S. Lamichhane, G. Sterne, B. Ye, and H. Peng, “BIOCAT: a pattern recognition platform for customizable biological image classification and annotation”, BMC Bioinformatics, vol. 14, no. 291, 2013 (DOI: 10.1186/1471-2105-14-291).
• [26] K.K. Siji, B.S. Mathew, R. Chandran, B.S. Shajeemohan, and K.S. Shanthini, “Feature selection, optimization and performance analysis of classifiers for biological images”, 2014 IEEE National Conference on Communication, Signal Processing and Networking (NCCSN), pp. 1–5, 2014 (DOI: 10.1109/NCCSN.2014.7001150).
• [27] Y. Song, W. Cai, H. Huang, D. Feng, Y. Wang, and M. Chen, “Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors”, BMC Bioinformatics, vol. 17, no. 465, 2016 (DOI: 10.1186/s12859-016-1318-9).
• [28] B.S. Shajee Mohan and C.C. Sekhar, “Distance metric learnt kernel based SVMs for semi-supervised pattern classification”, 2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), pp. 1–6, 2017 (DOI: 10.1109/ICAPR.2017.8592956).
• [29] L. Nanni, S. Ghidoni, and S. Brahnam, “Handcrafted vs. non-handcrafted features for computer vision classification”, Pattern Recognit., vol. 71, pp. 158–172, 2017 (DOI: 10.1016/j.patcog.2017.05.025).
• [30] L. Nanni, S. Brahnam, S. Ghidoni, and A. Lumini, “Bioimage classification with handcrafted and learned features”, IEEE/ACM Trans. Comput. Biol. Bioinform., vol. 16, no. 3, pp. 874–885, 2019 (DOI: 10.1109/TCBB.2018.2821127).
• [31] L. Nanni, S. Ghidoni, and S. Brahnam, “Ensemble of convolutional neural networks for bioimage classification”, Appl. Comput. Inform., vol. 17, no. 1, 2020 (DOI: 10.1016/j.aci.2018.06.002).
• [32] C.K. Ahn, C. Heo, and H. Jin, “A novel deep learning-based approach to high accuracy breast density estimation in digital mammography”, Med. Imaging: Computer-Aided Diagnosis, vol. 10134, SPIE, 2017 (DOI: 10.1117/12.2254264).
• [33] X. Li, Y. Quin, Z. Liu, “Pretraining improves deep learning based tissue microstructure estimation”, Computational Diffusion MRI, Springer, Cham, 173–185, 2021 (DOI: 10.1007/978-3-030-73018- 5_14).
• [34] –, IICBU dataset website, 2008 (URL: https://ome.irp.nia.n ih.gov/iicbu2008/).
• [35] L. Shamir, N. Orlov, D.M. Eckley, T. Macura, and I.G. Goldberg, “IICBU 2008: a proposed benchmark suite for biological image analysis”, Med. Biol. Eng. Comput., vol. 46, no. 9, pp. 943–947, 2008 (DOI: 10.1007/s11517-008-0380-5).
• [36] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition”, 2014 (DOI: 10.48550/arXiv.1409.1556).
• [37] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826, 2016 (DOI: 10.1109/CVPR.2016.308).
• [38] C. Szegedy, S. Ioffe, V. Vanhoucke, and A.A. Alemi., “Inception-v4, Inception-ResNet and the impact of residual connections on learning”, Proc. Conf. AAAI Artif. Intell., vol. 31, no. 1, pp. 4278–4284, 2017 (DOI: 10.1609/aaai.v31i1.11231).
• [39] –, ImageNet – image database, 2021 (URL: http://www.image-net.org).
• [40] C. Shorten and T.M. Khoshgoftaar, “A survey on image data augmentation for deep learning”, Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019 (DOI: 10.1186/s40537-019-0197-0).
• [41] A. Pratondo, C-K. Chui, and S-H. Ong, “Integrating machine learning with region-based active contour models in medical image segmentation”, Journal of Visual Communication and Image Representation, vol. 43, pp. 1–9, 2017 (DOI: 10.1016/j.jvcir.2016.11.019

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).