A Hierarchical Patch-Enhanced Framework for the Accurate Segmentation of Oral Squamous Cell Carcinoma in Histopathological Images
Received: 15 March 2026 | Revised: 22 April 2026 | Accepted: 30 April 2026 | Online: 10 May 2026
Corresponding author: Vinaya R. Kudatarkar
Abstract
An early diagnosis of oral squamous cell carcinoma is a critical step in improving patient survival, but manual histopathological tests are still slow, labor-intensive, and subject to expert opinions. Deep learning has been applied to automated analysis of cancer, although current models have difficulties in the multi-scale and complexity of oral tumor tissue epithelia. To overcome this, this study introduces a new Hierarchical Patch-Enhanced Framework (HPEF) combining multi-scale feature extraction, multi-scale progressive knowledge distillation, and adaptive attention to achieve precise segmentation of malignant epithelial segments. In-depth experiments on two publicly available histopathological datasets, ORCA and OCDC, showed that the proposed HPEF achieved accuracy scores of 0.923 and 0.978, Dice scores of 0.878 and 0.967, and Intersection-over-Union (IoU) scores of 0.735 and 0.943, respectively, which are significantly higher than state-of-the-art CNN-based, Transformer-based, and hybrid segmentation models. These findings indicate that HPEF has the potential to be a reliable instrument to help pathologists screen early cases of oral cancer.
Keywords:
oral squamous cell carcinoma, hierarchical patch-enhanced framework, multi-scale feature extraction, knowledge distillation, attention-based segmentationDownloads
References
F. Bray et al., "Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries," CA: A Cancer Journal for Clinicians, vol. 74, no. 3, pp. 229–263, May 2024.
I. U. Haq, M. Ahmed, M. Assam, Y. Y. Ghadi, and A. Algarni, "Unveiling the Future of Oral Squamous Cell Carcinoma Diagnosis: An Innovative Hybrid AI Approach for Accurate Histopathological Image Analysis," IEEE Access, vol. 11, pp. 118281–118290, 2023.
E. Natarajan, "Oral and Oropharyngeal Cancer," in Dental Science for the Medical Professional, C. E. Niekrash, E. M. Ferneini, and M. T. Goupil, Eds. Springer International Publishing, 2023, pp. 261–301.
M. F. Kabir, M. Y. Ahmad, R. Uddin, M. Cordero, and S. Kant, "Accurate and lightweight oral cancer detection using SE-MobileViT on clinically validated image dataset," Discover Artificial Intelligence, vol. 5, no. 1, July 2025, Art. no. 173.
D. Menditti et al., "Personalized Medicine in Oral Oncology: Imaging Methods and Biological Markers to Support Diagnosis of Oral Squamous Cell Carcinoma (OSCC): A Narrative Literature Review," Journal of Personalized Medicine, vol. 13, no. 9, Sept. 2023, Art. no. 1397.
M. Á. González-Moles, M. Aguilar-Ruiz, and P. Ramos-García, "Challenges in the Early Diagnosis of Oral Cancer, Evidence Gaps and Strategies for Improvement: A Scoping Review of Systematic Reviews," Cancers, vol. 14, no. 19, Oct. 2022, Art. no. 4967.
K. Oya, K. Kokomoto, K. Nozaki, and S. Toyosawa, "Oral squamous cell carcinoma diagnosis in digitized histological images using convolutional neural network," Journal of Dental Sciences, vol. 18, no. 1, pp. 322–329, Jan. 2023.
A. A. Alanazi, M. M. Khayyat, M. M. Khayyat, B. M. Elamin Elnaim, and S. Abdel-Khalek, "Intelligent Deep Learning Enabled Oral Squamous Cell Carcinoma Detection and Classification Using Biomedical Images," Computational Intelligence and Neuroscience, vol. 2022, pp. 1–11, June 2022.
E. Albalawi et al., "Oral squamous cell carcinoma detection using EfficientNet on histopathological images," Frontiers in Medicine, vol. 10, Jan. 2024.
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, vol. 13, no. 5, Feb. 2023, Art. no. 918.
A. P. De Mortanges et al., "Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging," npj Digital Medicine, vol. 7, no. 1, July 2024, Art. no. 195.
D. I. T. M. H. Tan, X. J. Tan, L. L. Lim, K. S. Ab Rahman, and J. J. W. Siet, "A systematic review of semantic segmentation methods for histopathology images: a focused survey on breast, colon, and prostate cancers," Applied Intelligence, vol. 55, no. 16, Oct. 2025, Art. no. 1036.
A. Basu, P. Senapati, M. Deb, R. Rai, and K. G. Dhal, "A survey on recent trends in deep learning for nucleus segmentation from histopathology images," Evolving Systems, vol. 15, no. 1, pp. 203–248, Feb. 2024.
A. A. Alzahrani et al., "Deep structured learning with vision intelligence for oral carcinoma lesion segmentation and classification using medical imaging," Scientific Reports, vol. 15, no. 1, Feb. 2025, Art. no. 6610.
O. Al-Omari, O. Alkhatib, and T. Al-Omari, "CNN-Based Automated Detection of Metastatic Cancer in Histopathology Images," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 24478–24485, Aug. 2025.
M. Das, R. Dash, S. Kumar Mishra, and A. Kumar Dalai, "An Ensemble Deep Learning Model for Oral Squamous Cell Carcinoma Detection Using Histopathological Image Analysis," IEEE Access, vol. 12, pp. 127185–127197, 2024.
D. Tao et al., "MCF-UNet: Multi-level context fusion unet for immunohistochemical positive cell detection," Pattern Recognition, vol. 179, Nov. 2026, Art. no. 113630.
L. C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation," presented at the Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 801–818.
A. Mathew and M. Jossy A, "Automated oral cancer detection with histopathological images using efficient deep-learning models," Bioinspired, Biomimetic and Nanobiomaterials, vol. 15, no. 1, pp. 4–13, Dec. 2025.
F. Martino et al., "Deep Learning-Based Pixel-Wise Lesion Segmentation on Oral Squamous Cell Carcinoma Images," Applied Sciences, vol. 10, no. 22, Nov. 2020.
"ORCA dataset." [Online]. Available: https://sites.google.com/unibas.it/orca.
D. F. D. Dos Santos, P. R. De Faria, B. A. N. Travençolo, and M. Z. Do Nascimento, "Influence of Data Augmentation Strategies on the Segmentation of Oral Histological Images Using Fully Convolutional Neural Networks," Journal of Digital Imaging, vol. 36, no. 4, pp. 1608–1623, Apr. 2023.
D. Freire, P. Faria, A. Loyola, S. Cardoso, B. Travencolo, and M. do Nascimento, "H&E-stained oral squamous cell carcinoma histological images dataset." Mendeley Data, Dec. 28, 2022.
Downloads
How to Cite
License
Copyright (c) 2026 Vinaya R. Kudatarkar, Annapurna P. Patil, Savitha K. Shetty
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
