Deep Learning-Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.
artificial intelligence
deep learning
histopathology
image classification
image segmentation
meta‐analysis
oral squamous cell carcinoma
systematic review
Journal
Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology
ISSN: 1600-0714
Titre abrégé: J Oral Pathol Med
Pays: Denmark
ID NLM: 8911934
Informations de publication
Date de publication:
10 Sep 2024
10 Sep 2024
Historique:
received:
28
04
2024
accepted:
03
08
2024
medline:
11
9
2024
pubmed:
11
9
2024
entrez:
10
9
2024
Statut:
aheadofprint
Résumé
Artificial intelligence (AI)-based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error. This systematic review and meta-analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI-based medical image analysis studies. Diagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS-2 tool was utilized to assess quality. The meta-analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets. Of 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS-2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta-analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity. Application of AI-based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI-based models cannot replace a well-trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.
Sections du résumé
BACKGROUND
BACKGROUND
Artificial intelligence (AI)-based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error.
OBJECTIVES
OBJECTIVE
This systematic review and meta-analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI-based medical image analysis studies.
METHODS
METHODS
Diagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS-2 tool was utilized to assess quality. The meta-analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets.
RESULTS
RESULTS
Of 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS-2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta-analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity.
CONCLUSION
CONCLUSIONS
Application of AI-based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI-based models cannot replace a well-trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.
Références
S. C. Shapiro, Encyclopedia of Artificial Intelligence, 2nd ed. (New Jersey: A Wiley Interscience Publication, 1992).
H. Mohammad‐Rahimi, R. Rokhshad, S. Bencharit, J. Krois, and F. Schwendicke, “Deep Learning: A Primer for Dentists and Dental Researchers,” Journal of Dentistry 130 (2023): 104430.
S. Wong, H. Al‐Hasani, Z. Alam, and A. Alam, “Artificial Intelligence in Radiology: How Will We Be Affected?” European Radiology 29, no. 1 (2019): 141–143.
G. Litjens, T. Kooi, B. E. Bejnordi, et al., “A Survey on Deep Learning in Medical Image Analysis,” Medical Iimage Aanalysis 42 (2017): 60–88.
F. Schwendicke, W. A.‐O. Samek, and J. Krois, “Artificial Intelligence in Dentistry: Chances and Challenges,” Journal of Dental Research 99 (2020): 769–774.
H. Mohammad‐Rahimi, M. Nadimi, M. H. Rohban, E. Shamsoddin, V. Y. Lee, and S. R. Motamedian, “Machine Learning and Orthodontics, Current Trends and the Future Opportunities: A Scoping Review,” American Journal of Orthodontics and Dentofacial Orthopedics 160, no. 2 (2021): 170–192.e4.
M. Murata, Y. Ariji, Y. Ohashi, et al., “Deep‐Learning Classification Using Convolutional Neural Network for Evaluation of Maxillary Sinusitis on Panoramic Radiography,” Oral Rradiology 35, no. 3 (2019): 301–307.
H. Mohammad‐Rahimi, S. R. Motamedian, M. H. Rohban, et al., “Deep Learning for Caries Detection: A Systematic Review: DL for Caries Detection,” Journal of Dentistry 13 (2022): 104115.
S. Sadr, H. Mohammad‐Rahimi, S. R. Motamedian, et al., “Deep Learning for Detection of Periapical Radiolucent Lesions: A Systematic Review and Meta‐Analysis of Diagnostic Test Accuracy,” Journal of Endodontics 49, no. 3 (2022): 248–261.
H. Mohammad‐Rahimi, S. R. Motamedian, Z. Pirayesh, et al., “Deep Learning in Periodontology and Oral Implantology: A Scoping Review,” Journal of Periodontal Research 57, no. 5 (2022): 942–951.
American Cancer Society, Cancer Statistics Center, 2023, https://cancerstatisticscenter.cancer.org/#!/.
T. Baykul, H. Yilmaz, Ü. Aydin, M. Aydin, M. Aksoy, and D. Yildirim, “Early Diagnosis of Oral Cancer,” Journal of International Medical Research 38, no. 3 (2010): 737–749.
N. Bhatia, Y. Lalla, A. N. Vu, and C. S. Farah, “Advances in Optical Adjunctive AIDS for Visualisation and Detection of Oral Malignant and Potentially Malignant Lesions,” International Journal of Dentistry 2013 (2013): 1–17.
J. Lavallee, “Oral Cancer and Dysplasia Trends Among South Asians in British Columbia: Lesion Sites, Risk Habits, and Access to Care” (University of British Columbia, 2016).
D. J. Fischer, J. B. Epstein, T. H. Morton, and S. M. Schwartz, “Interobserver Reliability in the Histopathologic Diagnosis of Oral Pre‐Malignant and Malignant Lesions,” Journal of Oral Pathology & Medicine 33, no. 2 (2004): 65–70.
F. R. Pires, M. E. Barreto, J. G. Nunes, N. S. Carneiro, A. B. Azevedo, and T. C. Dos Santos, “Oral Potentially Malignant Disorders: Clinical‐Pathological Study of 684 Cases Diagnosed in a Brazilian Population,” Medicina Oral, Patología Oral y Cirugía Bucal 25, no. 1 (2020): e84–e88.
C. Carreras‐Torras and C. Gay‐Escoda, “Techniques for Early Diagnosis of Oral Squamous Cell Carcinoma: Systematic Review,” Medicina Oral, Patología Oral y Cirugía Bucal 20, no. 3 (2015): e305–e315.
E. A. Rakha, M. Toss, S. Shiino, et al., “Current and Future Applications of Artificial Intelligence in Pathology: A Clinical Perspective,” Journal of Clinical Pathology 74, no. 7 (2021): 409–414.
S. Kalra, H. R. Tizhoosh, S. Shah, et al., “Pan‐Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligence,” NPJ Ddigital Medicine 3, no. 1 (2020): 1–15.
D. K. Das, C. Chakraborty, S. Sawaimoon, A. K. Maiti, and S. Chatterjee, “Automated Identification of Keratinization and Keratin Pearl Area From In Situ Oral Histological Images,” Tissue & CellTissue Cell 47, no. 4 (2015): 349–358.
R. K. Gupta, M. Kaur, and J. Manhas, “Tissue Level Based Deep Learning Framework for Early Detection of Dysplasia in Oral Squamous Epithelium,” Journal of Multimedia Information System 6, no. 2 (2019): 81–86.
M. D. McInnes, D. Moher, B. D. Thombs, et al., “Preferred Reporting Items for a Systematic Review and Meta‐Analysis of Diagnostic Test Accuracy Studies: The PRISMA‐DTA Statement,” Journal of the American Medical Association 319, no. 4 (2018): 388–396.
F. Schwendicke, T. Singh, J.‐H. Lee, et al., “Artificial Intelligence in Dental Research: Checklist for Authors, Reviewers, Readers,” Journal of Dentistry 107 (2021): 103610.
P. F. Whiting, A. W. Rutjes, M. E. Westwood, et al., “QUADAS‐2: A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies,” Annals of Iinternal Mmedicine 155, no. 8 (2011): 529–536.
A. Pennisi, D. D. Bloisi, D. Nardi, S. Varricchio, and F. Merolla, “Multi‐Encoder U‐Net for Oral Squamous Cell Carcinoma Image Segmentation,” in 2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Taormina, Messina, Italy (2022).
D. F. Dos Santos, P. R. De Faria, B. A. Travencolo, and M. Z. Do Nascimento, “Automated Detection of Tumor Regions From Oral Histological Whole Slide Images Using Fully Convolutional Neural Networks,” Biomedical Signal Processing and Control 69 (2021): 102921.
J. Folmsbee, M. Brandwein‐Weber, and S. Doyle, “Whole Slide Semantic Segmentation: Large Scale Active Learning for Digital Pathology,” in Medical Imaging 2021: Digital Pathology (SPIE, 2021).
T. Saraswathi and V. M. Bhaskaran, “Classification of Oral Squamous Carcinoma Histopathological Images Using Alex Net,” in 2023 International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS), Coimbatore, India (2023).
B. Ananthakrishnan, A. Shaik, S. Kumar, S. O. Narendran, K. Mattu, and M. S. Kavitha, “Automated Detection and Classification of Oral Squamous Cell Carcinoma Using Deep Neural Networks,” Diagnostics 13, no. 5 (2023): 918.
T. Y. Rahman, L. B. Mahanta, A. K. Das, and J. D. Sarma, “Histopathological Imaging Database for Oral Cancer Analysis,” Data in Brief 29 (2020): 105114.
M. Das, R. Dash, and S. K. Mishra, “Automatic Detection of Oral Squamous Cell Carcinoma From Histopathological Images of Oral Mucosa Using Deep Convolutional Neural Network,” International Journal of Environmental Research & Public Health 20, no. 3 (2023): 2131.
S. K. Shetty and A. P. Patil, “Duck Pack Optimization With Deep Transfer Learning‐Enabled Oral Squamous Cell Carcinoma Classification on Histopathological Images,” International Journal of Grid and High Performance Computing 15, no. 2 (2023): 1–21.
S. Panigrahi, B. S. Nanda, R. Bhuyan, K. Kumar, S. Ghosh, and T. Swarnkar, “Classifying Histopathological Images of Oral Squamous Cell Carcinoma Using Deep Transfer Learning,” Heliyon 9, no. 3 (2023): e13444.
K. Bansal, R. Bathla, and Y. Kumar, “Deep Transfer Learning Techniques With Hybrid Optimization in Early Prediction and Diagnosis of Different Types of Oral Cancer,” Soft Computing 26, no. 21 (2022): 11153–11184.
S. Yang, S. Li, J. Liu, et al., “Histopathology‐Based Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning,” Journal of Dental Research 101, no. 11 (2022): 1321–1327.
Z. Xu, J. Peng, X. Zeng, H. Xu, and Q. Chen, “High‐Accuracy Oral Squamous Cell Carcinoma Auxiliary Diagnosis System Based on EfficientNet. Frontiers,” Oncology 12 (2022): 894978.
P.‐T.‐H. Nguyen, K. Sakamoto, and T. Ikeda, “Deep‐Learning Application for Identifying Histological Features of Epithelial Dysplasia of Tongue,” Journal of Oral and Maxillofacial Surgery, Medicine, and Pathology 34, no. 4 (2022): 514–522.
A.‐u. Rahman, A. Alqahtani, N. Aldhafferi, et al., “Histopathologic Oral Cancer Prediction Using Oral Squamous Cell Carcinoma Biopsy Empowered With Transfer Learning,” Sensors 22, no. 10 (2022): 3833.
K. Shankar, E. L. Lydia, S. Kumar, A. S. Abosinne, A. Abbas, and S. N. Mahmood, “Hyperparameter Tuning Bidirectional Gated Recurrent Unit Model for Oral Cancer Classification,” Computers, Materials & Continua 73, no. 3 (2022): 4541–4557.
S. Shetty and A. P. Patil, “Oral Cancer Detection Model in Distributed Cloud Environment via Optimized Ensemble Technique,” Biomedical Signal Processing and Control 81 (2023): 104311.
J. Musulin, D. Štifanić, A. Zulijani, T. Ćabov, A. Dekanić, and Z. Car, “An Enhanced Histopathology Analysis: An AI‐Based System for Multiclass Grading of Oral Squamous Cell Carcinoma and Segmenting of Epithelial and Stromal Tissue,” Cancers 13, no. 8 (2021): 1784.
D. K. Das, S. Bose, A. K. Maiti, B. Mitra, G. Mukherjee, and P. K. Dutta, “Automatic Identification of Clinically Relevant Regions From Oral Tissue Histological Images for Oral Squamous Cell Carcinoma Diagnosis,” Tissue and Cell 53 (2018): 111–119.
B. E. Bejnordi, M. Veta, P. J. Van Diest, et al., “Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer,” Journal of the American Medical Association 318, no. 22 (2017): 2199–2210.
Z. H. Khoury, M. Sultan, and A. S. Sultan, “Oral Epithelial Dysplasia Grading Systems: A Systematic Review & Meta‐Analysis,” International Journal of Surgical Pathology 30, no. 5 (2022): 499–511.
J. Zhang, Y. Peng, S. Ding, et al., “Comparison of Different Combinations of Irradiation Mode and Jaw Width in Helical Tomotherapy for Nasopharyngeal Carcinoma,” Frontiers in Oncology 10 (2020): 598.
A. Homeyer, C. Geißler, L. O. Schwen, et al., “Recommendations on Compiling Test Datasets for Evaluating Artificial Intelligence Solutions in Pathology,” Modern Pathology 35, no. 12 (2022): 1759–1769.
S. Sunny, A. Baby, B. L. James, et al., “A Smart Tele‐Cytology Point‐of‐Care Platform for Oral Cancer Screening,” PLoS One 14, no. 11 (2019): e0224885.