Colon histology slide classification with deep-learning framework using individual and fused features

Venkatesan Rajinikanth; Seifedine Kadry; Ramya Mohan; Arunmozhi Rama; Muhammad Attique Khan; Jungeun Kim; Venkatesan Rajinikanth; Seifedine Kadry; Ramya Mohan; Arunmozhi Rama; Muhammad Attique Khan; Jungeun Kim

doi:10.3934/mbe.2023861

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 11: 19454-19467. doi: 10.3934/mbe.2023861

Previous Article Next Article

Research article Special Issues

Colon histology slide classification with deep-learning framework using individual and fused features

1.
Department of Computer Science and Engineering, Division of Research and Innovation, Saveetha School of Engineering, SIMATS, Chennai 602105, India
2.
Department of Applied Data Science, Noroff University College, 4612 Kristiansand, Norway
3.
Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman 346, United Arab Emirates
4.
Department of Electrical and Computer Engineering, Lebanese American University, Byblos 1401, Lebanon
5.
Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon
6.
Department of Software, Kongju National University, Cheonan, 31080, Korea

Academic Editor: Sokratis Makrogiannis

Received: 07 March 2023 Revised: 02 September 2023 Accepted: 18 September 2023 Published: 20 October 2023

Cancer occurrence rates are gradually rising in the population, which reasons a heavy diagnostic burden globally. The rate of colorectal (bowel) cancer (CC) is gradually rising, and is currently listed as the third most common cancer globally. Therefore, early screening and treatments with a recommended clinical protocol are necessary to trat cancer. The proposed research aim of this paper to develop a Deep-Learning Framework (DLF) to classify the colon histology slides into normal/cancer classes using deep-learning-based features. The stages of the framework include the following: (ⅰ) Image collection, resizing, and pre-processing; (ⅱ) Deep-Features (DF) extraction with a chosen scheme; (ⅲ) Binary classification with a 5-fold cross-validation; and (ⅳ) Verification of the clinical significance. This work classifies the considered image database using the follwing: (ⅰ) Individual DF, (ⅱ) Fused DF, and (ⅲ) Ensemble DF. The achieved results are separately verified using binary classifiers. The proposed work considered 4000 (2000 normal and 2000 cancer) histology slides for the examination. The result of this research confirms that the fused DF helps to achieve a detection accuracy of 99% with the K-Nearest Neighbor (KNN) classifier. In contrast, the individual and ensemble DF provide classification accuracies of 93.25 and 97.25%, respectively.
- colorectal cancer,
- histology slide,
- fused features,
- ensemble features,
- classification
Citation: Venkatesan Rajinikanth, Seifedine Kadry, Ramya Mohan, Arunmozhi Rama, Muhammad Attique Khan, Jungeun Kim. Colon histology slide classification with deep-learning framework using individual and fused features[J]. Mathematical Biosciences and Engineering, 2023, 20(11): 19454-19467. doi: 10.3934/mbe.2023861

Related Papers:

Abstract

Cancer occurrence rates are gradually rising in the population, which reasons a heavy diagnostic burden globally. The rate of colorectal (bowel) cancer (CC) is gradually rising, and is currently listed as the third most common cancer globally. Therefore, early screening and treatments with a recommended clinical protocol are necessary to trat cancer. The proposed research aim of this paper to develop a Deep-Learning Framework (DLF) to classify the colon histology slides into normal/cancer classes using deep-learning-based features. The stages of the framework include the following: (ⅰ) Image collection, resizing, and pre-processing; (ⅱ) Deep-Features (DF) extraction with a chosen scheme; (ⅲ) Binary classification with a 5-fold cross-validation; and (ⅳ) Verification of the clinical significance. This work classifies the considered image database using the follwing: (ⅰ) Individual DF, (ⅱ) Fused DF, and (ⅲ) Ensemble DF. The achieved results are separately verified using binary classifiers. The proposed work considered 4000 (2000 normal and 2000 cancer) histology slides for the examination. The result of this research confirms that the fused DF helps to achieve a detection accuracy of 99% with the K-Nearest Neighbor (KNN) classifier. In contrast, the individual and ensemble DF provide classification accuracies of 93.25 and 97.25%, respectively.

References

[1]	S. Meyer, W. A. Groenewald, R. D. Pitcher, Diagnostic reference levels in low-and middle-income countries: early "ALARAm" bells?, Acta Radiol., 58 (2017), 442–448. https://doi.org/10.1177/0284185116658681 doi: 10.1177/0284185116658681
[2]	H. Yadav, D. Shah, S. Sayed, S. Horton, L. F. Schroeder, Availability of essential diagnostics in ten low-income and middle-income countries: results from national health facility surveys, Lancet Global Health, 9 (2021), e1553–e1560. https://doi.org/10.1016/S2214-109X(21)00442-3 doi: 10.1016/S2214-109X(21)00442-3
[3]	J. Naz, M. A. Khan, M. Alhaisoni, S. Kadry, Segmentation and classification of stomach abnormalities using deep learning, Comput. Mater. Continua, 69 (2021), 607–625. https://doi.org/10.32604/cmc.2021.017101 doi: 10.32604/cmc.2021.017101
[4]	M. A. Khan, M. S. Sarfraz, M. Alhaisoni, I. Ashraf, StomachNet: Optimal deep learning features fusion for stomach abnormalities classification, IEEE Access, 8 (2020), 197969–197981. https://doi.org/10.1109/ACCESS.2020.3034217 doi: 10.1109/ACCESS.2020.3034217
[5]	World Health Organization, Cancer, 2022. Available from: https://www.who.int/news-room/fact-sheets/detail/cancer.
[6]	Colorectal cancer statistics, 2020. Available from: https://www.wcrf.org/cancer-trends/colorectal-cancer-statistics/.
[7]	M. A. Khan, I. M. Nasir, Y. Nam, A blockchain based framework for stomach abnormalities recognition, Comput. Mater. Continua, 67 (2021), 141–158. https://doi.org/10.32604/cmc.2021.013217 doi: 10.32604/cmc.2021.013217
[8]	A. Majid, M. A. Khan, M. Yasmin, U. Tariq, Classification of stomach infections: a paradigm of convolutional neural network along with classical features fusion and selection, Microsc. Res. Tech., 83 (2020), 562–576. https://doi.org/10.1002/jemt.23447 doi: 10.1002/jemt.23447
[9]	Y. Jiao, J. Li, C. Qian, S. Fei, Deep learning-based tumor microenvironment analysis in colon adenocarcinoma histopathological whole-slide images, Comput. Methods Programs Biomed., 204 (2021), 106047. https://doi.org/10.1016/j.cmpb.2021.106047 doi: 10.1016/j.cmpb.2021.106047
[10]	Tissue Image Analytics Centre. Available from: https://warwick.ac.uk/fac/cross_fac/tia/data/glascontest/.
[11]	K. Sirinukunwattana, J. P. Pluim, H. Chen, A. Böhm, Gland segmentation in colon histology images: the glas challenge contest, Med. Image Anal., 35 (2017), 489–502. https://doi.org/10.1016/j.media.2016.08.008 doi: 10.1016/j.media.2016.08.008
[12]	S. U. K. Bukhari, A. Syed, S. K. A. Bokhari, S. S. H. Shah, The histological diagnosis of colonic adenocarcinoma by applying partial self supervised learning, MedRxiv, 2 (2020), 1–11. https://doi.org/10.1101/2020.08.15.20175760 doi: 10.1101/2020.08.15.20175760
[13]	S. Mangal, A.Chaurasia, A. Khajanchi, Convolution neural networks for diagnosing colon and lung cancer histopathological images, preprint, arXiv: 2009.03878.
[14]	M. Masud, N.Sikder, A. A.Nahid, M. A. AlZain, A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework, Sensors, 21 (2021), 748. https://doi.org/10.3390/s21030748 doi: 10.3390/s21030748
[15]	M. Ali, R. Ali, Multi-input dual-stream capsule network for improved lung and colon cancer classification, Diagnostics, 11 (2021), 1485. https://doi.org/10.3390/diagnostics11081485 doi: 10.3390/diagnostics11081485
[16]	D. Sarwinda, R. H. Paradisa, A. Bustamam, P. Anggia, Deep learning in image classification using residual network (ResNet) variants for detection of colorectal cancer, Proc. Comput. Sci., 179 (2021), 423–431. https://doi.org/10.1016/j.procs.2021.01.025 doi: 10.1016/j.procs.2021.01.025
[17]	A. B. Hamida, M. Devanne, J. Weber, C.Truntzer, C. Wemmert, Deep learning for colon cancer histopathological images analysis, Comput. Biol. Med., 136 (2021), 104730. https://doi.org/10.1016/j.compbiomed.2021.104730 doi: 10.1016/j.compbiomed.2021.104730
[18]	E. F. Ohata, J. V. S. D. Chagas, G. M.Bezerra, V. H. C. de Albuquerque, A novel transfer learning approach for the classification of histological images of colorectal cancer, J. Supercomput., 77 (2021), 9494–9519. https://doi.org/10.1007/s11227-020-03575-6 doi: 10.1007/s11227-020-03575-6
[19]	J. Fan, J. Lee, Y. Lee, A transfer learning architecture based on a support vector machine for histopathology image classification, Appl. Sci., 11 (2021), 6380. https://doi.org/10.3390/app11146380 doi: 10.3390/app11146380
[20]	V. Siripoppohn, R. Pittayanon, K. Tiankanon, N. Faknak, R. Rerknimitr, Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach, Clin Endoscopy, 55 (2022), 390–400. https://doi.org/10.5946/ce.2022.005 doi: 10.5946/ce.2022.005
[21]	V. de Almeida Thomaz, C. A. Sierra-Franco, A. B. Raposo, Training data enhancements for improving colonic polyp detection using deep convolutional neural networks, Artif. Intell. Med., 111 (2021), 101988. https://doi.org/10.1016/j.artmed.2020.101988 doi: 10.1016/j.artmed.2020.101988
[22]	A. A. Borkowski, M. M. Bui, L. B. Thomas, S. M. Mastorides, Lung and colon cancer histopathological image dataset (lc25000), Preprint, arXiv: 1912.12142.
[23]	S. Kadry, V. Rajinikanth, D. Taniar, X. P. B. Valencia, Automated segmentation of leukocyte from hematological images—a study using various CNN schemes, J. Supercomput., 78 (2022), 6974–6994. https://doi.org/10.1007/s11227-021-04125-4 doi: 10.1007/s11227-021-04125-4
[24]	M. A. Khan, M. Azhar, K. Ibrar, Y. J. Kim, B. Chang, COVID-19 classification from chest X-ray images: a framework of deep explainable artificial intelligence, Comput. Intell. Neurosci., 2022 (2022). https://doi.org/10.1155/2022/4254631 doi: 10.1155/2022/4254631
[25]	S. Kadry, G. Srivastava, V. Rajinikanth, Y. Kim, Tuberculosis detection in chest radiographs using spotted hyena algorithm optimized deep and handcrafted features, Comput. Intell. Neurosci., 2022 (2022). https://doi.org/10.1155/2022/9263379 doi: 10.1155/2022/9263379
[26]	R. Biju, W. Patel, V. Rajinikanth, Framework for classification of chest x-rays into normal/covid-19 using Brownian-mayfly-algorithm selected hybrid features, Math. Probl. Eng., 2022 (2022). https://doi.org/10.1155/2022/6475808 doi: 10.1155/2022/6475808
[27]	F. Afza, M. Sharif, M. A. Khan, J. Cha, Multiclass skin lesion classification using hybrid deep features selection and extreme learning machine, Sensors, 22 (2022), 799. https://doi.org/10.3390/s22030799 doi: 10.3390/s22030799
[28]	M. Sharif, T. Akram, M. Raza, A. Rehman, Hand-crafted and deep convolutional neural network features fusion and selection strategy: An application to intelligent human action recognition, Appl. Soft Comput., 87 (2020), 105986. https://doi.org/10.1016/j.asoc.2019.105986 doi: 10.1016/j.asoc.2019.105986
[29]	M. Arshad, U. Tariq, A. Armghan, F. Alenezi, M. Younus Javed, A Computer-aided diagnosis system using deep learning for multiclass skin lesion classification, Comput. Intell. Neurosci., 21 (2021), 1–23. https://doi.org/10.1155/2021/9619079 doi: 10.1155/2021/9619079
[30]	M. Sharif, T. Akram, M. Raza, T. Saba, A. Rehman, Hand-crafted and deep convolutional neural network features fusion and selection strategy: An application to intelligent human action recognition, Appl. Soft Comput., 87 (2020), 105986. https://doi.org/10.1016/j.asoc.2019.105986 doi: 10.1016/j.asoc.2019.105986

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)