Evaluation of normalization technique on classification with deep learning features
Resumo
Cancer is one of the diseases with the highest mortality rate in the world. Dysplasia is a difficult-to-diagnose precancerous lesion, which may not have a good Hematoxylin and Eosin (H&E) stain ratio, making it difficult for the histology specialist to diagnose. In this work, a method for normalizing H&E stains in histological images was investigated. This method uses a generative neural network based on a U-net for image generation and a PatchGAN architecture for information discrimination. Then, the normalized histological images were employed in classification algorithms to investigate the detection of the level of dysplasia present in the histological tissue of the oral cavity. The CNN models as well as hybrid models based on learning features and machine learning algorithms were evaluated. The employment of the ResNet-50 architecture and the Random Forest algorithm provided results with an accuracy rate around 97% for the images normalized with the investigated method.
Referências
J. A. A. Jothi and V. M. A. Rajam, “A survey on automated cancer diagnosis from histopathology images,” Artificial Intelligence Review, vol. 48, no. 1, pp. 31–81, 2017.
T. Fonseca-Silva, M. G. Diniz, S. F. Sousa, R. S. Gomez, and C. C. Gomes, “Association between histopathological features of dysplasia in oral leukoplakia and loss of heterozygosity,” Histopathology, vol. 68, no. 3, pp. 456–460, 2016.
A. Ham and D. H. Cormack, “Histologia,” in Histologia, 1983, pp. 906–906.
Anonymous, “Métodos computacionais para análise e classificação de displasias em imagens da cavidade bucal,” Master’s thesis, Universidade Federal de Uberlândia - Faculdade de Computação, 2019.
Roberto, G. F. Lumini, A. Neves, L. A. do Nascimento, and M. Zanchetta, “Fractal neural network: A new ensemble of fractal geometry and convolutional neural networks for the classification of histology images,” Expert Systems with Applications, vol. 166, p. 114103, 2021.
W. Li, J. Li, K. V. Sarma, K. C. Ho, S. Shen, B. S. Knudsen, A. Gertych, and C. W. Arnold, “Path r-cnn for prostate cancer diagnosis and gleason grading of histological images,” IEEE transactions on medical imaging, vol. 38, no. 4, pp. 945–954, 2018.
R. C. Gonzalez and R. Woods, “Digital image processing,” 2018.
M. Salvi, U. R. Acharya, F. Molinari, and K. M. Meiburger, “The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis,” Computers in Biology and Medicine, p. 104129, 2020.
C.-M. Chen, Y.-S. Huang, P.-W. Fang, C.-W. Liang, and R.-F. Chang, “A computer-aided diagnosis system for differentiation and delineation of malignant regions on whole-slide prostate histopathology image using spatial statistics and multidimensional densenet,” Medical physics, vol. 47, no. 3, pp. 1021–1033, 2020.
P. Salehi and A. Chalechale, “Pix2pix-based stain-to-stain translation: A solution for robust stain normalization in histopathology images analysis,” 2020 International Conference on Machine Vision and Image Processing (MVIP), 2020.
T. A. A. Tosta, P. R. de Faria, L. A. Neves, and M. Z. do Nascimento, “Computational normalization of h&e-stained histological images: Progress, challenges and future potential,” Artificial intelligence in medicine, vol. 95, pp. 118–132, 2019.
A. BenTaieb and G. Hamarneh, “Adversarial stain transfer for histopathology image analysis,” IEEE transactions on medical imaging, vol. 37, no. 3, pp. 792–802, 2017.
M. Mirza and S. Osindero, “Conditional generative adversarial nets,” arXiv preprint arXiv:1411.1784, 2014.
C. Y. S. W. P. S. M. S. N. B. C. V. E. A. A. S. A. Md Zahangir Alom, Tarek M. Taha and V. K. Asari, “The history began from alexnet: A comprehensive survey on deep learning approaches,” arXiv.org, 2018.
Q. Z. D. A. M. J. D. Hang Yu, Laurence T. Yang, “Convolutional neural networks for medical image analysis: State-of-the- art, comparisons, improvement and perspectives,” Elsevier, 2021.
V. Vapnik, “An overview of statistical learning theory,” Neural Networks, IEEE Transactions on, vol. 10, no. 5, pp. 988–999, 1999.
