Classification of Microscopy Sputum Image Using Probabilistic Bayesian Neural Network
DOI:
https://doi.org/10.52575/2687-0932-2022-49-3-575-581Keywords:
light microscopy, Bayesian neural networks, variational inference, reparametrization, aleatoric and epistemic uncertaintyAbstract
Probabilistic and deep learning methods are fundamental for recognizing complex structures in data sets, searching for small objects in noisy conditions, and are widely used for classifying medical images. Light microscopy medical images used to detect pathological processes are characterized by fuzziness in the representation of objects of interest, blurred borders, noise, small sized objects of interest, and low spatial resolution. The authors illustrate the implementation of a classification procedure based on probabilistic Bayesian neural networks for classifying light microscopic images of sputum samples stained by Ziehl-Neelsen method. The authors conduct an experiment with various network structures of a probabilistic Bayesian network and input datasets, and search for a model with the smallest learning error. The model containing convolutional deterministic layers and focused on the assessment of aleatoric uncertainty showed the best results in terms of accuracy and test error on the experimental data set.
Downloads
References
Brosse N., Riquelme C., Martin A. Gelly S., Moulines E. 2020. On Last-layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation – arXiv preprint arXiv: 2001.08049.
Chang D.T. 2021. Probabilistic Deep Learning with Probabilistic Neural Networks and Deep Probabilistic Models – arXiv preprint arXiv:2106.00120.
Der Kiureghian A., Ditlevsen O. 2009. Aleatory or epistemic? does it matter? Structural Safety, 31: 105–112.
Hinton G.E.D., Camp V. 1993. Keeping the neural networks simple by minimizing the description length of the weights. In Proceedings of the sixth annual conference on Computational learning theory: 5–13.
Hüllermeier E., Waegeman W. 2021. Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Machine Learning, 110: 457–506.
Jospin L.V., Buntine W., Boussaid F., Laga H., Bennamoun M. 2020. Hands-on Bayesian Neural Networks – a Tutorial for Deep Learning Users. ACM Computing Surveys, 1 (1): 1–36.
Kisantal M., Wojna Z., Murawski J., Naruniec J., Cho K. 2019. Augmentation for small object detection – preprint arXiv: 1902.07296
Manaswi, N.K. 2018. Deep Learning with Applications Using Python. Springer Science – Business Media, New York, 219 p.
Salama K. 2021. Probabilistic Bayesian Neural Network. Keras Documentation – https://keras.io/examples/keras_recipes/bayesian_neural_networks.
Serrao M.K.M., Costa M.G.F., Fujimoto L.B. Ogusku M.M., Filho C.F.F.C. 2020. Automatic Bacillus Detection in Light Field Microscopy Images Using Convolutional Neural Networks and Mosaic Imaging Approach. Annual International Conference of the IEEE Engineering in Medicine and Biology Society: 1903–1906.
Shelomentseva I.G., Chentsov S.V. 2020. Classification of Microscopy Image Staned By Ziehl-Neelsen Method Using Different Architectures of Convolution Neural Nerwork. Studies in Computational Intelligence, 925: 269–275.
Shin H., Roth H.R., Gao M. Lu L., Xu Z., Nogues I., Yao J., Mollura D., Summers R.M. 2016. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning IEEE Transactions on Medical Imaging, 35(5): 1207–1216.
Snoek J., Larochelle H., Adams R.P. 2012. Practical Bayesian Optimization of Machine Learning Algorithms. Proceedings of Advances in Neural Information Processing Systems Conference: 2951–2959.
TensorFlow Probability (https://www.tensorflow.org/probability)
Udegova E.S., Shelomentseva I.G., Chentsov S.V. 2021. Optimizing Convolution Neural Network Architecture for Microscopy Image Recognition for Tuberculosis Diagnosis. Advances in Neural Computation, Machine Learning, and Cognitive Research V. NEUROINFORMATICS 2021. Studies in Computational Intelligence, 1008: 204–209.
Vladimirova M., Verbeek J., Mesejo P., Arbel J. 2019. Understanding Priors in Bayesian Neural Networks at the Unit Level. International Conference on Machine Learning: 6458–6467.
Wan Q., Fu X. 2020. Fast-BCNN: Massive Neuron Skipping in Bayesian Convolutional Neural Networks. 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO): 229–240.
Wang Z., Hutter F., Zoghi M., Matheson D., de Freitas N. 2016. Bayesian Optimization in a Billion Dimensions via Random Embeddings. Journal of Artificial Intelligence Research, 55: 361–387.
Zeng J., Lesnikowski A., Alvarez J.M. 2018. The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning – arXiv preprint arXiv:1811.12535.
Zhang X., Zou J., He K., Sun J. 2019. Accelerating Very Deep Convolutional Networks for Classification and Detection – preprint arXiv: 1505.06798.
Abstract views: 103
Share
Published
How to Cite
Issue
Section
Copyright (c) 2022 ECONOMICS. INFORMATION TECHNOLOGIES
This work is licensed under a Creative Commons Attribution 4.0 International License.
