Automatic chronic degenerative diseases identification using enteric nervous system images
Tóm tắt
Studies recently accomplished on the Enteric Nervous System have shown that chronic degenerative diseases affect the Enteric Glial Cells (EGC) and, thus, the development of recognition methods able to identify whether or not the EGC are affected by these type of diseases may be helpful in its diagnoses. In this work, we propose the use of pattern recognition and machine learning techniques to evaluate if a given animal EGC image was obtained from a healthy individual or one affect by a chronic degenerative disease. In the proposed approach, we have performed the classification task with handcrafted features and deep learning-based techniques, also known as non-handcrafted features. The handcrafted features were obtained from the textural content of the ECG images using texture descriptors, such as the Local Binary Pattern (LBP). Moreover, the representation learning techniques employed in the approach are based on different Convolutional Neural Network (CNN) architectures, such as AlexNet and VGG16, with and without transfer learning. The complementarity between the handcrafted and non-handcrafted features was also evaluated with late fusion techniques. The datasets of EGC images used in the experiments, which are also contributions of this paper, are composed of three different chronic degenerative diseases: Cancer, Diabetes Mellitus, and Rheumatoid Arthritis. The experimental results, supported by statistical analysis, show that the proposed approach can distinguish healthy cells from the sick ones with a recognition rate of 89.30% (Rheumatoid Arthritis), 98.45% (Cancer), and 95.13% (Diabetes Mellitus), being achieved by combining classifiers obtained on both feature scenarios.
Tài liệu tham khảo
Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1798–1828
Bossolani GDP et al (2019) Rheumatoid arthritis induces enteric neurodegeneration and jejunal inflammation, and quercetin promotes neuroprotective and anti-inflammatory actions. Life Sci
Chang C, Lin C (2013) Libsvm: a library for support vector machines. National Taiwan University, Taipei
Charte F, Rivera A, del Jesus M, Herrera F (2015) MLSMOTE: approaching imbalanced multilabel learning through synthetic instance generation. Knowl Based Syst 89:385–397
Chen, J, et al. (2013) RLBP: Robust local binary pattern, Center for machine vision research. University of Oulu, Oulu
Chollet F, et al. (2015) Keras. https://keras.io
Costa YMG (2013) Reconhecimento de gêneros musicais utilizando espectrogramas com combinação de classificadores. Ph.D. thesis, Federal University of Paraná, Curitiba, Brasil
Costa YMG, Oliveira LES, Koerich AL, Gouyon F, Martins JG (2012) Music genre classification using lbp textural features. Sig Process 92(11):2723–2737
Costa YMG, Oliveira LES, Silla CN Jr (2017) An evaluation of convolutional neural networks for music classification using spectrograms. Appl Soft Comput 52:28–38
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: CVPR09, p. 8
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, New York
Felipe GZ, Aguiat RL, Costa YMG, Silla CN, Brahnam S, Nanni L, McMurtrey S (2019) Identification of infants’ cry motivation using spectrograms. In: Proceedings of the international conference on systems, signals and image processing, pp. 181–186
Felipe GZ, Costa YMG, Helal LG (2017) Acoustic scene classification using spectrograms. In: Proceedings of the international conference of the Chilean computer science society, p. 7
Freitas GK, Costa YMG, Aguiar RL (2016) Using spectrogram to detect north atlantic right whale calls from audio recordings. In: Proceedings of the international conference of the Chilean computer science society, pp. 1–6
Frez FCV et al (2017) Restoration of density of interstitial cells of cajal in the jejunum of diabetic rats after quercetin supplementation. Rev Esp Enferm Dig 109:190–195
Furness JB (2006) The enteric nervous system. Blackwell Publishing, New Jersey, p 290
Giorgio RD et al (2012) Enteric glia and neuroprotection: basic and clinical aspects. Am J Physiol Gastrointest Liver Physiol 303:G887–G893
Gulbransen B, Sharkey K (2012) Novel functional roles for enteric glia in the gastrointestinal tract. Gastroenterol Hepatol. Vol, Nature reviews, p 9
Ho TK (1995) Random decision forests. In: Proceedings of the international conference on document analysis and recognition, pp. 278–282
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: Proceedings of the international conference for learning representations, p. 15
Kittler J, Hatef M, Duin RP, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20(3):226–239
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJS, Bottou L, Weinberger KQ (Eds) Advances in Neural information processing systems, pp. 1097–1105. Curran Associates, Inc
Lecun Y (1989) Generalization and network design strategies. In: Pfeifer R, Schreter Z, Fogelman F, Steels L (eds) Connectionism in perspective. Elsevier, Amsterdam
Lecun Y et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551
Liu T, Fang S, Zhao Y, Zhang J (2015) Implementation of training convolutional neural networks. Computing Research Repository (CoRR) abs/1506.01195
Mäenpää TI (2013) The local binary pattern approach to texture analysis: extensions and applications. Ph.D. thesis, University of Oulu, Oulu
Matsushita GHG, Sugi AH, Costa YMG, Gomez-A A, Da Cunha C, Oliveira LES (2019) Phasic dopamine release identification using convolutional neural network. Comput Biol Med 114:103466
Nanni L, Costa YMG, Lucio DR, Silla CN, Brahnam S (2016) Combining visual and acoustic features for bird species classification. In: Proceedings of the IEEE international conference on tools with artificial intelligence, pp. 396–401
Nanni L, Ghidoni S, Brahnam S (2017) Handcrafted vs non-handcrafted features for computer vision classitcation. Pattern Recogn 71:158–172. https://doi.org/10.1016/j.patcog.2017.05.025
Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobotics 7:21
Ojala T, Pietikäinen M, Mäenpää T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987
Ojansivu V, Heikkilä J (2008) Blur insensitive texture classification using local phase quantization. Image and Signal Processing pp. 236–243
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Panizzon CPNB et al (2016) Desired and side effects of the supplementation with l-glutamine and l-glutathione in enteric glia of diabetic rats. Acta Histochem 118:625–631
Panizzon CPNB et al (2019) Ethyl acetate fraction from trichilia catigua confers partial neuroprotection in components of the enteric innervation of the jejunum in diabetic rats. Cell Physiol Biochem 53:76–86
Paulino MAD, Britto Junior AS, Svaigen, AR, Aylon LBR, Oliveira LES, Costa YMG (2018) A brazilian speech database. In: Proceedings of the IEEE international conference on tools with artificial intelligence, pp. 234–241
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Pereira RM, Bertolini D, Teixeira LO, Silla CN Jr, Costa YMG (2020) Covid-19 identification in chest x-ray images on flat and hierarchical classification scenarios. Comput Methods Programs Biomed 194:105532
Pereira RV et al (2011) L-glutamine supplementation prevents myenteric neuron loss and has gliatrophic effects in the ileum of diabetic rats. Dig Dis Sci 56:3507–3516
Roecker MN, Costa YMG, Almeida JLR, Matsushita G (2018) Automatic vehicle type classification with convolutional neural networks. In: Proceedings of the international conference on systems, signals and image processing, pp. 1–5
Ruhl A (2005) Glial cells in the gut. Neurogastroenterol Motil 17:777–790
Russell SJ, Norvig P (2010) Artificial intelligence: a modern approach, 3rd edn. Pearson Education, London
Schapire RE (1999) A brief introduction to boosting. In: Proceedings of the 16th international joint conference on artificial intelligence - Volume 2, IJCAI’99, p. 1401–1406. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA
Sharkey KA (2015) Emerging roles for enteric glia in gastrointestinal disorders. J Clin Investig 125
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. Computing Research Repository (CoRR) abs/1409.1556
Souza ID et al (2011) Analysis of myosin-v immunoreactive myenteric neurons from arthritic rats. Arq Gastroenterol 48:205–210
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Szegedy C, Ioffe S, Vanhoucke V (2016) Inception-v4, inception-resnet and the impact of residual connections on learning. Comput Res Repos (CoRR) abs/1602.07261
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. Comput Res Repos (CoRR) abs/1512.00567
Vargas ACG, Paes AVCN (2016) Um estudo sobre redes neurais convolucionais e sua aplicação em detecção de pedestres. In: Proceedings of the conference on graphics, patterns and images, p. 4
Vicentini GE et al (2017) Does l-glutamine-supplemented diet extenuate no-mediated damage on myenteric plexus of walker 256 tumor-bearing rats? Food Res Int 101:24–34
Zhao Y, Jia W, Hu RX, Min H (2013) Completed robust local binary pattern for texture classification. Neurocomputing 106:68–76