Intelligent Decision Support System Based on Deep Learning with the Whale Optimization Algorithm for Oral Cancer

Dasril  Aldo; Adanti Wido  Paramadini

doi:10.59395/ijadis.v7i1.1521

Authors

Dasril Aldo Faculty of Informatics, Telkom University, Purwokerto, Indonesia https://orcid.org/0000-0002-1709-8353
Adanti Wido Paramadini Department of Biomedical Engineering, Telkom University, Purwokerto, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i1.1521

Keywords:

Deep Learning, Hyperparameter Optimization, Whale Optimization Algorithm, Histopathological Images, Clinical Decision Support Systems

Abstract

To build an accurate and reliable clinical decision support system, this study seeks to create a classification system using deep learning as a better approach in the analysis of oral cancer histopathological images. The dataset used consisted of 10,002 images, of which the two more balanced classes were normal oral and oral squamous cell carcinoma. Some pre-trained deep learning architectures are taken as baseline models and then optimized using the Whale Optimization Algorithm to obtain the best hyperparameter configuration. Performance evaluation was carried out on test data using accuracy, precision, recall, F1-score, confusion matrix, and operational efficiency metrics as well as evaluation of a trust-based decision support system with the same mechanism as the reject option system. The models are better optimized and all models show improved performance. From the results of the experiments, the model that was best optimized with an F1-score and an accuracy of 98.73%, and also showed the best performance, was the EfficientNet B3 model. This is accompanied by a stable training process and adequate generalization. Therefore, the model shows results with adequate performance in the coverage range of 0.60 - 0.90 and still provides a reasonable inference time for use in the clinic. These results show that this model has high potential to be integrated with clinical decision support systems. Therefore, this model can be used as a diagnostic tool in clinics that is more accurate and ensures consistency in each clinical practice and can also build a better diagnostic decision support system.

1108 353

Downloads

Download data is not yet available.

References

[1] I. Perera et al., An overview of the burden of oral cancer in Sri Lanka and its inequalities in the face of contemporary economic and social malaise, Community Dent. Oral Epidemiol., vol. 51, no. 4, pp. 680696, Aug. 2023, doi: 10.1111/cdoe.12888. DOI: https://doi.org/10.1111/cdoe.12888

[2] M. D. L. G. Aguiaga et al., Tongue cancer: An overview and current update, International Journal of Applied Dental Sciences, vol. 8, no. 3, pp. 356360, Jul. 2022, doi: 10.22271/oral.2022.v8.i3d.1612. DOI: https://doi.org/10.22271/oral.2022.v8.i3d.1612

[3] Ms. M. Kudale, Epidermiology, Risk Factor and Treatment of Oral Cancer, Int. J. Res. Appl. Sci. Eng. Technol., vol. 13, no. 4, pp. 43944399, Apr. 2025, doi: 10.22214/ijraset.2025.69232. DOI: https://doi.org/10.22214/ijraset.2025.69232

[4] A. K. Jain, Oral Cancer Screening: Insights into Epidemiology, Risk Factors, and Screening Programs for Improved Early Detection, Cancer Screening and Prevention, vol. 3, no. 2, pp. 97105, Jun. 2024, doi: 10.14218/CSP.2023.00029S. DOI: https://doi.org/10.14218/CSP.2023.00029S

[5] H. Seok, Role of oral and maxillofacial surgeons in treating oral cancer, J. Korean Assoc. Oral Maxillofac. Surg., vol. 48, no. 6, pp. 329330, Dec. 2022, doi: 10.5125/jkaoms.2022.48.6.329. DOI: https://doi.org/10.5125/jkaoms.2022.48.6.329

[6] U. Tomi et al., Comparison of transepithelial cytology and histopathology in the diagnosis of potentially malignant and malignant lesions of the oral mucosa, Balkan Journal of Dental Medicine, vol. 26, no. 2, pp. 113117, 2022, doi: 10.5937/bjdm20220531-001. DOI: https://doi.org/10.5937/bjdm20220531-001

[7] C. Gupta, A. Anjum, S. Sharma, and M. Jamwal, Histopathological spectrum of lesions of oral cavity and oropharynx in a tertiary care center, Panacea Journal of Medical Sciences, vol. 15, no. 1, pp. 1417, Mar. 2025, doi: 10.18231/pjms.v.15.i.1.14-17. DOI: https://doi.org/10.18231/pjms.v.15.i.1.14-17

[8] T. Mezei, M. Kolcsr, A. Jo, and S. Gurzu, Image Analysis in Histopathology and Cytopathology: From Early Days to Current Perspectives, J. Imaging, vol. 10, no. 10, p. 252, Oct. 2024, doi: 10.3390/jimaging10100252. DOI: https://doi.org/10.3390/jimaging10100252

[9] F. Ghezloo et al., An analysis of pathologists viewing processes as they diagnose whole slide digital images, J. Pathol. Inform., vol. 13, p. 100104, 2022, doi: 10.1016/j.jpi.2022.100104. DOI: https://doi.org/10.1016/j.jpi.2022.100104

[10] M. Unger and J. N. Kather, Deep learning in cancer genomics and histopathology, Genome Med., vol. 16, no. 1, p. 44, Mar. 2024, doi: 10.1186/s13073-024-01315-6. DOI: https://doi.org/10.1186/s13073-024-01315-6

[11] V. Ramachandra, Histopathology: Deep machine learning based semantic segmentation features predict patient survival, Jan. 14, 2023. doi: 10.1101/2023.01.14.23284554. DOI: https://doi.org/10.1101/2023.01.14.23284554

[12] J. K. Sandhu, C. Sharma, A. Kaur, S. K. Pandey, A. Sinha, and J. Shreyas, Development of a clinical decision support system for breast cancer detection using ensemble deep learning, Sci. Rep., vol. 15, no. 1, p. 26098, Jul. 2025, doi: 10.1038/s41598-025-06784-2. DOI: https://doi.org/10.1038/s41598-025-06784-2

[13] H. T. N. PHAN and A. AKTER, HYBRID MACHINE LEARNING APPROACH FOR ORAL CANCER DIAGNOSIS AND CLASSIFICATION USING HISTOPATHOLOGICAL IMAGES, International Journal of Medical Science and Dental Health, vol. 11, no. 01, pp. 6376, Jan. 2025, doi: 10.55640/ijmsdh-11-01-08. DOI: https://doi.org/10.55640/ijmsdh-11-01-08

[14] Z. Yang, H. Pan, J. Shang, J. Zhang, and Y. Liang, Deep-Learning-Based Automated Identification and Visualization of Oral Cancer in Optical Coherence Tomography Images, Biomedicines, vol. 11, no. 3, p. 802, Mar. 2023, doi: 10.3390/biomedicines11030802. DOI: https://doi.org/10.3390/biomedicines11030802

[15] K. C. Figueroa et al., Interpretable deep learning approach for oral cancer classification using guided attention inference network, J. Biomed. Opt., vol. 27, no. 01, Jan. 2022, doi: 10.1117/1.JBO.27.1.015001. DOI: https://doi.org/10.1117/1.JBO.27.1.015001

[16] V. P. G. Pushparathi, S. V. NarayanS.R, P. R.S., and V. Naveen, Histopathological image analysis and enhanced diagnostic accuracy explainability for oral cancer detection, Polish Journal of Pathology, vol. 76, no. 2, pp. 120130, 2025, doi: 10.5114/pjp.2025.153973. DOI: https://doi.org/10.5114/pjp.2025.153973

[17] V. N. Thatha et al., Histopathological image based breast cancer diagnosis using deep learning and bio inspired optimization, Sci. Rep., vol. 15, no. 1, p. 19034, May 2025, doi: 10.1038/s41598-025-04136-8. DOI: https://doi.org/10.1038/s41598-025-04136-8

[18] M. K. Karuppan Perumal, R. Rajan Renuka, S. Kumar Subbiah, and P. Manickam Natarajan, Artificial intelligence-driven clinical decision support systems for early detection and precision therapy in oral cancer: a mini review, Frontiers in Oral Health, vol. 6, Apr. 2025, doi: 10.3389/froh.2025.1592428. DOI: https://doi.org/10.3389/froh.2025.1592428

[19] O. F. Altal et al., WOAENet: a whale optimization-guided ensemble deep learning with soft voting for uterine cancer diagnosis based on MRI images, Front. Artif. Intell., vol. 8, Oct. 2025, doi: 10.3389/frai.2025.1664201. DOI: https://doi.org/10.3389/frai.2025.1664201

[20] S. B. Urundai Meeran, AI-Powered Skin Lesion Diagnosis using Whale Optimization Algorithm Enhanced ResNet 50 for Cancer Prediction, Asian Pacific Journal of Cancer Prevention, vol. 26, no. 8, pp. 29192928, Aug. 2025, doi: 10.31557/APJCP.2025.26.8.2919. DOI: https://doi.org/10.31557/APJCP.2025.26.8.2919

[21] E. al. Vijay Arumugam R., Modelling of Whale Optimization Algorithm with Deep Learning for Skin Cancer Diagnosis on Dermoscopic Images, International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 10, pp. 20182026, Nov. 2023, doi: 10.17762/ijritcc.v11i10.8885. DOI: https://doi.org/10.17762/ijritcc.v11i10.8885

[22] H. S. Ali, A. I. Ismail, E. M. ElRabaie, and F. E. Abd ElSamie, Deep residual architectures and ensemble learning for efficient brain tumour classification, Expert Syst., vol. 40, no. 6, Jul. 2023, doi: 10.1111/exsy.13226. DOI: https://doi.org/10.1111/exsy.13226

[23] M. H. Abid, R. Ashraf, T. Mahmood, and C. M. N. Faisal, Multi-modal medical image classification using deep residual network and genetic algorithm, PLoS One, vol. 18, no. 6, p. e0287786, Jun. 2023, doi: 10.1371/journal.pone.0287786. DOI: https://doi.org/10.1371/journal.pone.0287786

[24] T. Zhang, Performance Analysis of Residual Networks for Pneumonia Diagnosis on Chest X-Rays, Applied and Computational Engineering, vol. 138, no. 1, pp. 104109, Mar. 2025, doi: 10.54254/2755-2721/2025.21363. DOI: https://doi.org/10.54254/2755-2721/2025.21363

[25] T. Kanimozhi et al., RWHO: A hybrid of CNN architecture and optimization algorithm to predict basal cell carcinoma skin cancer in dermoscopic images, The Scientific Temper, vol. 15, no. 02, pp. 21382142, Jun. 2024, doi: 10.58414/SCIENTIFICTEMPER.2024.15.2.25. DOI: https://doi.org/10.58414/SCIENTIFICTEMPER.2024.15.2.25

[26] A. E. Minarno, L. R. Wandani, and Y. Azhar, Classification of Breast Cancer Based on Histopathological Image Using EfficientNet-B0 on Convolutional Neural Network, International Journal of Emerging Technology and Advanced Engineering, vol. 12, no. 8, pp. 7077, Aug. 2022, doi: 10.46338/ijetae0822_09. DOI: https://doi.org/10.46338/ijetae0822_09

[27] B. Jacob, R. S. V. Kumar, and S. S. Kumar, Multiple Scaling Based EfficientNet Modelling for Liver Tumor Classification on CT Images, International Journal Bioautomation, vol. 28, no. 3, pp. 151160, Sep. 2024, doi: 10.7546/ijba.2024.28.3.001001. DOI: https://doi.org/10.7546/ijba.2024.28.3.001001

[28] A. Bruno, G. Ignesti, O. Salvetti, D. Moroni, and M. Martinelli, Efficient Lung Ultrasound Classification, Bioengineering, vol. 10, no. 5, p. 555, May 2023, doi: 10.3390/bioengineering10050555. DOI: https://doi.org/10.3390/bioengineering10050555

[29] M. Naeeni Davarani et al., Efficient segmentation of active and inactive plaques in FLAIR-images using DeepLabV3Plus SE with efficientnetb0 backbone in multiple sclerosis, Sci. Rep., vol. 14, no. 1, p. 16304, Jul. 2024, doi: 10.1038/s41598-024-67130-6. DOI: https://doi.org/10.1038/s41598-024-67130-6

[30] T.-B.-T. Nguyen, M.-V. Ngo, and V.-P. Nguyen, Histopathological Imaging Classification of Breast Tissue for Cancer Diagnosis Support Using Deep Learning Models, 2022, pp. 152164. doi: 10.1007/978-3-031-08878-0_11. DOI: https://doi.org/10.1007/978-3-031-08878-0_11

[31] S. Anjum et al., Lung Cancer Classification in Histopathology Images Using Multiresolution Efficient Nets, Comput. Intell. Neurosci., vol. 2023, no. 1, Jan. 2023, doi: 10.1155/2023/7282944. DOI: https://doi.org/10.1155/2023/7282944

[32] D. Beaulah Princiba, P. Ezhilarasi, and S. Rajeshkannan, CSMEC-based deep learning model for detection and classification of brain tumours in MR images, Neural Comput. Appl., vol. 36, no. 29, pp. 1847918498, Oct. 2024, doi: 10.1007/s00521-024-10168-4. DOI: https://doi.org/10.1007/s00521-024-10168-4

[33] K. Ding, Z. Niu, J. Hui, X. Zhou, and F. T. S. Chan, A Weld Surface Defect Recognition Method Based on Improved MobileNetV2 Algorithm, Mathematics, vol. 10, no. 19, p. 3678, Oct. 2022, doi: 10.3390/math10193678. DOI: https://doi.org/10.3390/math10193678

[34] D. Bac Da, An Intelligent and Lightweight Approach Based on MobilenetV2 Architecture for Identifying Brain Tumors, Sakarya University Journal of Computer and Information Sciences, vol. 8, no. 3, pp. 392399, Sep. 2025, doi: 10.35377/saucis...1590213. DOI: https://doi.org/10.35377/saucis...1590213

[35] F. Shahoveisi, H. Taheri Gorji, S. Shahabi, S. Hosseinirad, S. Markell, and F. Vasefi, Application of image processing and transfer learning for the detection of rust disease, Sci. Rep., vol. 13, no. 1, p. 5133, Mar. 2023, doi: 10.1038/s41598-023-31942-9. DOI: https://doi.org/10.1038/s41598-023-31942-9

[36] H. M. Whitney, K. Drukker, and M. L. Giger, Performance metric curve analysis framework to assess impact of the decision variable threshold, disease prevalence, and dataset variability in two-class classification, Journal of Medical Imaging, vol. 9, no. 03, May 2022, doi: 10.1117/1.JMI.9.3.035502. DOI: https://doi.org/10.1117/1.JMI.9.3.035502

[37] Y. J. Hong et al., Deep learning-based classification of pleural malignancy using medical thoracoscopic images, Transl. Lung Cancer Res., vol. 14, no. 10, pp. 44754484, Oct. 2025, doi: 10.21037/tlcr-2025-588. DOI: https://doi.org/10.21037/tlcr-2025-588

[38] H.-S. Ham, H.-S. Lee, J.-W. Chae, H. C. Cho, and H.-C. Cho, Improvement of Gastroscopy Classification Performance Through Image Augmentation Using a Gradient-Weighted Class Activation Map, IEEE Access, vol. 10, pp. 9936199369, 2022, doi: 10.1109/ACCESS.2022.3207839. DOI: https://doi.org/10.1109/ACCESS.2022.3207839