Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques
Abstract
:Simple Summary
Abstract
1. Introduction
- Enhance histological images of oral cancer using two distinct filters for improved image quality and feature extraction.
- Fine-tune hyperparameters of convolutional neural network (CNN) models to optimize classification performance and enhance model accuracy.
- Oral cancer cell histology images can be effectively diagnosed with a hybrid technique utilizing CNN models and the SVM algorithm.
- The PCA algorithm was utilized to reduce the number of features in the high-dimensional OSCC dataset.
- The diagnosis of the histological images of OSCC cells using the SVM algorithm, which is based on the hybrid features extracted by the CNN model; it combines these characteristics with the color, texture, and shape data extracted using the GLCM, HOG, and LBP algorithms.
2. Related Work
3. Materials and Methods
3.1. Dataset Description
3.2. Pre-Processing of Histological Images
3.3. Deep Learning Model
3.3.1. Convolution Layer
3.3.2. Pooling Layer
3.3.3. Fully Connected Layer
3.4. Hybridization of CNN with SVM
3.4.1. Extracting Deep Features
3.4.2. Support Vector Machine (SVM)
3.5. SVM-Based Hybrid CNN Deep Features with GLCM, HOG, and LBP
4. Evaluation Tools
4.1. Confusion Matrics
4.2. Receiver Operating Characteristic (ROC)
4.3. Area under the Curve (AUC)
4.4. Training and Validation Accuracy/Loss
4.5. Data Augmentation
5. Results
5.1. Analysis and Insights Results of Deep Learning Models
5.2. Performance Evaluation of the Combined CNN–SVM Method: Experimental Results
5.3. Performance Evaluation of Hybrid Deep Feature Model with GLCM, HOG, and LBP
5.4. Receiver Operating Characteristic (ROC) and AUC
6. Discussion of Proposed Methods
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
OSCC | Oral squamous cell carcinoma |
PCA | Principal component analysis |
CNN | Convolutional neural network |
DL | Deep learning |
SVM | Support vector machine |
LBP | Local Binary Pattern |
HOG | Histogram of Oriented Gradients |
GLCM | Gray-Level Co-Occurrence Matrix |
References
- Du, M.; Nair, R.; Jamieson, L.; Liu, Z.; Bi, P. Incidence trends of lip, oral cavity, and pharyngeal cancers: Global burden of disease 1990–2017. J. Dent. Res. 2020, 99, 143–151. [Google Scholar] [CrossRef] [PubMed]
- Warnakulasuriya, S.; Greenspan, J.S. Epidemiology of oral and oropharyngeal cancers. In Textbook of Oral Cancer; Springer: Berlin/Heidelberg, Germany, 2020; pp. 5–21. [Google Scholar]
- World Cancer Research Fund International. Mouth and Oral Cancer Statistics. 2020. Available online: https://www.wcrf.org/cancer-trends/mouth-and-oral-cancer-statistics/ (accessed on 21 October 2023).
- World Health Organization. International Agency for Research on Cancer. 2021. Available online: https://gco.iarc.fr/today/online-analysis-table (accessed on 21 October 2023).
- World Health Organization. International Agency for Research on Cancer. 2021. Available online: https://gco.iarc.fr/today/data/factsheets/populations/586-pakistan-fact-sheets.pdf (accessed on 21 October 2023).
- Sung, H.; Ferlay, J.; Siegel, R.L.; Laversanne, M.; Soerjomataram, I.; Jemal, A.; Bray, F. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 2021, 71, 209–249. [Google Scholar] [CrossRef] [PubMed]
- Warnakulasuriya, S. Oral potentially malignant disorders: A comprehensive review on clinical aspects and management. Oral Oncol. 2020, 102, 104550. [Google Scholar] [CrossRef] [PubMed]
- Mccormick, N.J.; Thomson, P.J.; Carrozzo, M. The clinical presentation of oral potentially malignant disorders. Prim. Dent. J. 2016, 5, 52–57. [Google Scholar] [CrossRef]
- Chen, S.W.; Zhang, Q.; Guo, Z.M.; Chen, W.K.; Liu, W.W.; Chen, Y.F.; Li, Q.L.; Liu, X.K.; Li, H.; Ou-Yang, D.; et al. Trends in clinical features and survival of oral cavity cancer: Fifty years of experience with 3362 consecutive cases from a single institution. Cancer Manag. Res. 2018, 10, 4523–4535. [Google Scholar] [CrossRef]
- Listl, S.; Jansen, L.; Stenzinger, A.; Freier, K.; Emrich, K.; Holleczek, B.; Katalinic, A.; Gondos, A.; Brenner, H.; Group, G.C.S.W. Survival of patients with oral cavity cancer in Germany. PLoS ONE 2013, 8, e53415. [Google Scholar] [CrossRef]
- Speight, P.; Palmer, S.; Moles, D.; Downer, M.; Smith, D.; Henriksson, M.; Augustovski, F. The cost-effectiveness of screening for oral cancer in primary care. Health Technol. Assess. 2006, 10, 1–144. [Google Scholar] [CrossRef]
- Cao, R.; Wu, Q.; Li, Q.; Yao, M.; Zhou, H. A 3-mRNA-based prognostic signature of survival in oral squamous cell carcinoma. PeerJ 2019, 7, e7360. [Google Scholar] [CrossRef]
- Muzio, L.L.; D’Angelo, M.; Procaccini, M.; Bambini, F.; Calvino, F.; Florena, A.M.; Franco, V.; Giovannelli, L.; Ammatuna, P.; Campisi, G. Expression of cell cycle markers and human papillomavirus infection in oral squamous cell carcinoma: Use of fuzzy neural networks. Int. J. Cancer 2005, 115, 717–723. [Google Scholar] [CrossRef]
- Brickley, M.; Cowpe, J.; Shepherd, J. Performance of a computer simulated neural network trained to categorise normal, premalignant and malignant oral smears. J. Oral Pathol. Med. 1996, 25, 424–428. [Google Scholar] [CrossRef]
- López-Cortés, X.A.; Matamala, F.; Venegas, B.; Rivera, C. Machine-learning applications in oral cancer: A systematic review. Appl. Sci. 2022, 12, 5715. [Google Scholar] [CrossRef]
- Steinkraus, D.; Buck, I.; Simard, P.Y. Using GPUs for machine learning algorithms. In Proceedings of the Eighth International Conference on Document Analysis and Recognition (ICDAR’05), Seoul, Republic of Korea, 31 August –1 September 200 5; IEEE: New York, NY, USA, 2005; pp. 1115–1120. [Google Scholar]
- Rahman, A.u.; Alqahtani, A.; Aldhafferi, N.; Nasir, M.U.; Khan, M.F.; Khan, M.A.; Mosavi, A. Histopathologic oral cancer prediction using oral squamous cell carcinoma biopsy empowered with transfer learning. Sensors 2022, 22, 3833. [Google Scholar] [CrossRef] [PubMed]
- Amin, I.; Zamir, H.; Khan, F.F. Histopathological image analysis for oral squamous cell carcinoma classification using concatenated deep learning models. medRxiv 2021. [Google Scholar] [CrossRef]
- Rahman, T.Y.; Mahanta, L.B.; Choudhury, H.; Das, A.K.; Sarma, J.D. Study of morphological and textural features for classification of oral squamous cell carcinoma by traditional machine learning techniques. Cancer Rep. 2020, 3, e1293. [Google Scholar] [CrossRef]
- Rahman, T.Y.; Mahanta, L.B.; Das, A.K.; Sarma, J.D. Automated oral squamous cell carcinoma identification using shape, texture and color features of whole image strips. Tissue Cell 2020, 63, 101322. [Google Scholar] [CrossRef]
- Shavlokhova, V.; Sandhu, S.; Flechtenmacher, C.; Koveshazi, I.; Neumeier, F.; Padrón-Laso, V.; Jonke, Ž.; Saravi, B.; Vollmer, M.; Vollmer, A.; et al. Deep learning on oral squamous cell carcinoma ex vivo fluorescent confocal microscopy data: A feasibility study. J. Clin. Med. 2021, 10, 5326. [Google Scholar] [CrossRef]
- Martino, F.; Bloisi, D.D.; Pennisi, A.; Fawakherji, M.; Ilardi, G.; Russo, D.; Nardi, D.; Staibano, S.; Merolla, F. Deep learning-based pixel-wise lesion segmentation on oral squamous cell carcinoma images. Appl. Sci. 2020, 10, 8285. [Google Scholar] [CrossRef]
- Halicek, M.; Dormer, J.D.; Little, J.V.; Chen, A.Y.; Myers, L.; Sumer, B.D.; Fei, B. Hyperspectral imaging of head and neck squamous cell carcinoma for cancer margin detection in surgical specimens from 102 patients using deep learning. Cancers 2019, 11, 1367. [Google Scholar] [CrossRef]
- Musulin, J.; Štifanić, D.; Zulijani, A.; Ćabov, T.; Dekanić, A.; Car, Z. An enhanced histopathology analysis: An ai-based system for multiclass grading of oral squamous cell carcinoma and segmenting of epithelial and stromal tissue. Cancers 2021, 13, 1784. [Google Scholar] [CrossRef]
- Paderno, A.; Piazza, C.; Del Bon, F.; Lancini, D.; Tanagli, S.; Deganello, A.; Peretti, G.; De Momi, E.; Patrini, I.; Ruperti, M.; et al. Deep learning for early segmentation of oral and oropharyngeal cancer using narrow band imaging: Preliminary experience in a clinical perspective. Front. Oncol. 2021, 11, 626602. [Google Scholar] [CrossRef]
- Gupta, R.K.; Kaur, M.; Manhas, J. Tissue level based deep learning framework for early detection of dysplasia in oral squamous epithelium. J. Multimed. Inf. Syst. 2019, 6, 81–86. [Google Scholar] [CrossRef]
- Chan, C.H.; Huang, T.T.; Chen, C.Y.; Lee, C.C.; Chan, M.Y.; Chung, P.C. Texture-map-based branch-collaborative network for oral cancer detection. IEEE Trans. Biomed. Circuits Syst. 2019, 13, 766–780. [Google Scholar] [CrossRef] [PubMed]
- Lalithmani, K.; Punitha, A. Detection of oral cancer using deep neural-based adaptive fuzzy system in data mining techniques. Int. J. Rec. Tech. Eng. 2019, 7, 397–404. [Google Scholar]
- Palaskar, R.; Vyas, R.; Khedekar, V.; Palaskar, S.; Sahu, P. Transfer learning for oral cancer detection using microscopic images. arXiv 2020, arXiv:2011.11610. [Google Scholar]
- dos Santos, D.F.; Tosta, T.A.; Silva, A.B.; de Faria, P.R.; Travençolo, B.A.; do Nascimento, M.Z. Automated nuclei segmentation on dysplastic oral tissues using cnn. In Proceedings of the 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Niteroi, Brazil, 1–3 July 2020; IEEE: New York, NY, USA, 2020; pp. 45–50. [Google Scholar]
- Gupta, R.K.; Kaur, M.; Manhas, J. Cellular level based deep learning framework for early detection of dysplasia in oral squamous epithelium. In Proceedings of ICRIC 2019: Recent Innovations in Computing; Springer: Berlin/Heidelberg, Germany, 2020; pp. 137–149. [Google Scholar]
- Alhazmi, A.; Alhazmi, Y.; Makrami, A.; Masmali, A.; Salawi, N.; Masmali, K.; Patil, S. Application of artificial intelligence and machine learning for prediction of oral cancer risk. J. Oral Pathol. Med. 2021, 50, 444–450. [Google Scholar] [CrossRef]
- Chu, C.S.; Lee, N.P.; Adeoye, J.; Thomson, P.; Choi, S.W. Machine learning and treatment outcome prediction for oral cancer. J. Oral Pathol. Med. 2020, 49, 977–985. [Google Scholar] [CrossRef]
- Welikala, R.A.; Remagnino, P.; Lim, J.H.; Chan, C.S.; Rajendran, S.; Kallarakkal, T.G.; Zain, R.B.; Jayasinghe, R.D.; Rimal, J.; Kerr, A.R.; et al. Automated detection and classification of oral lesions using deep learning for early detection of oral cancer. IEEE Access 2020, 8, 132677–132693. [Google Scholar] [CrossRef]
- Kaggle. Datasets. Available online: https://www.kaggle.com/datasets (accessed on 1 April 2022).
- Al-Mekhlafi, Z.G.; Senan, E.M.; Rassem, T.H.; Mohammed, B.A.; Makbol, N.M.; Alanazi, A.A.; Almurayziq, T.S.; Ghaleb, F.A. Deep learning and machine learning for early detection of stroke and hemorrhage. Comput. Mater. Contin. 2022, 72, 775–796. [Google Scholar]
- Chu, C.S.; Lee, N.P.; Ho, J.W.; Choi, S.W.; Thomson, P.J. Deep learning for clinical image analyses in oral squamous cell carcinoma: A review. JAMA Otolaryngol.-Neck Surg. 2021, 147, 893–900. [Google Scholar] [CrossRef]
- Nekkalapu, V.S.; Yammada, V.A.; Kapoor, M.; Ponugoti, S.S.; Pudota, S. GC-308 Heart Disease Prediction and Analysis by Machine Learning. 2022. Available online: https://digitalcommons.kennesaw.edu/cday/Fall_2022/Graduate_Capstone/6/ (accessed on 21 October 2023).
- Galanis, N.I.; Vafiadis, P.; Mirzaev, K.G.; Papakostas, G.A. Convolutional Neural Networks: A Roundup and Benchmark of Their Pooling Layer Variants. Algorithms 2022, 15, 391. [Google Scholar] [CrossRef]
- Krichen, M. Convolutional neural networks: A survey. Computers 2023, 12, 151. [Google Scholar] [CrossRef]
- ElAraby, M.E.; Elzeki, O.M.; Shams, M.Y.; Mahmoud, A.; Salem, H. A novel Gray-Scale spatial exploitation learning Net for COVID-19 by crawling Internet resources. Biomed. Signal Process. Control 2022, 73, 103441. [Google Scholar] [CrossRef] [PubMed]
Training Phase | ||
---|---|---|
Classes | Before Augmentation | After Augmentation |
Normal | 2436 | 12,180 |
OSCC | 2511 | 12,555 |
Measures | Xception | InceptionV3 | InceptionResNetV2 | NASNetLarge | DenseNet201 |
---|---|---|---|---|---|
Accuracy (%) | 90.47 | 91.26 | 92.85 | 94.44 | 93.65 |
Precision (%) | 90.32 | 87.09 | 87.09 | 90.32 | 96.77 |
Sensitivity (%) | 75.67 | 79.41 | 84.37 | 87.52 | 81.01 |
Specificity (%) | 96.62 | 95.65 | 95.74 | 95.80 | 98.87 |
F1 Score (%) | 82.34 | 83.07 | 85.70 | 88.88 | 88.23 |
AUC (%) | 89.4 | 89.90 | 90.90 | 93.10 | 94.70 |
Measures | Xception | InceptionV3 | InceptionResNetV2 | NASNetLarge | DenseNet201 |
---|---|---|---|---|---|
+ SVM | + SVM | + SVM | + SVM | + SVM | |
Accuracy (%) | 92.06 | 92.85 | 94.44 | 95.23 | 96.03 |
Precision (%) | 87.09 | 90.32 | 93.54 | 90.32 | 90.32 |
Sensitivity (%) | 81.81 | 82.35 | 85.29 | 90.32 | 93.33 |
Specificity (%) | 95.69 | 96.73 | 97.82 | 96.84 | 96.87 |
F1 Score (%) | 84.36 | 86.15 | 89.22 | 90.32 | 91.80 |
AUC (%) | 90.40 | 92.00 | 94.10 | 92.50 | 94.10 |
Measures | Xception | InceptionV3 | InceptionResNetV2 | NASNetLarge | DenseNet201 |
---|---|---|---|---|---|
GLCM, HOG | GLCM, HOG | GLCM, HOG | GLCM, HOG | GLCM, HOG | |
&, LBP, SVM | &, LBP, SVM | &, LBP, SVM | &, LBP, SVM | &, LBP, SVM | |
Accuracy (%) | 93.65 | 94.44 | 95.23 | 96.03 | 97.00 |
Precision (%) | 90.32 | 90.32 | 96.77 | 90.32 | 96.77 |
Sensitivity (%) | 84.84 | 87.53 | 85.71 | 93.33 | 90.90 |
Specificity (%) | 96.77 | 96.80 | 98.90 | 96.87 | 98.92 |
F1 score (%) | 87.49 | 88.88 | 90.90 | 91.80 | 93.74 |
AUC (%) | 92.50 | 94.10 | 95.80 | 94.10 | 96.80 |
Strategies | Models | Accuracy(%) |
---|---|---|
Deep Learning Model | Xception | 90.47 |
InceptionV3 | 91.26 | |
InceptionResNetV2 | 92.85 | |
NASNetLarge | 94.44 | |
DenseNet201 | 93.65 | |
Hybrid Features of CNN with SVM | Xception + SVM | 92.06 |
InceptionV3 + SVM | 92.85 | |
InceptionResNetV2 + SVM | 94.44 | |
NASNetLarge + SVM | 95.23 | |
DenseNet201 + SVM | 96.03 | |
Hybrid Features Fusion of CNN with GLCM, HOG, and, LBP + SVM | Xception + GLCM, HOG, LBP + SVM | 93.65 |
InceptionV3 + GLCM, HOG, LBP + SVM | 94.44 | |
InceptionResNetV2 + GLCM, HOG, LBP + SVM | 95.23 | |
NASNetLarge + GLCM, HOG, LBP + SVM | 96.03 | |
DenseNet201 + GLCM, HOG, LBP + SVM | 97.00 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ahmad, M.; Irfan, M.A.; Sadique, U.; Haq, I.u.; Jan, A.; Khattak, M.I.; Ghadi, Y.Y.; Aljuaid, H. Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques. Cancers 2023, 15, 5247. https://doi.org/10.3390/cancers15215247
Ahmad M, Irfan MA, Sadique U, Haq Iu, Jan A, Khattak MI, Ghadi YY, Aljuaid H. Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques. Cancers. 2023; 15(21):5247. https://doi.org/10.3390/cancers15215247
Chicago/Turabian StyleAhmad, Mehran, Muhammad Abeer Irfan, Umar Sadique, Ihtisham ul Haq, Atif Jan, Muhammad Irfan Khattak, Yazeed Yasin Ghadi, and Hanan Aljuaid. 2023. "Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques" Cancers 15, no. 21: 5247. https://doi.org/10.3390/cancers15215247
APA StyleAhmad, M., Irfan, M. A., Sadique, U., Haq, I. u., Jan, A., Khattak, M. I., Ghadi, Y. Y., & Aljuaid, H. (2023). Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques. Cancers, 15(21), 5247. https://doi.org/10.3390/cancers15215247