Deep Convolutional Multi-Feature Fusion Approach for Early Laryngeal Carcinoma Detection using Narrow-Band Medical Imaging
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 Dey 2026
https://doi.org/10.22037/ijmtfm.v16.52406
Abstract
Background: Laryngeal carcinoma (LC) is one of the major cancers affecting the head and neck region, where delayed diagnosis can reduce survival rate and affect vocal function. Although medical image-based automated detection systems are useful and accurate, LC detection remains challenging due to variations in inter-class differences, unclear lesion boundaries, noise, and the distinct appearance of malignant tissues. The current state of the art in deep learning models relies on single-network feature extraction approaches, which restricts the ability to derive spatial and semantic representations from complex laryngeal images.
Methods: To address these issues, this paper presents an Artificial Intelligence-based Deep Convolutional Feature Fusion Model (AI-DCFFM) for Robust LC Detection using Medical Imaging. The presented method extracts deep features using MobileNetV2, DenseNet, and CapsNet architectures. Further, a parallel maximum covariance (PMC) based fusion strategy is introduced to combine the complementary feature representations obtained from the multiple DL models.
Results: For classification, a deep belief network (DBN) classifier is used to differentiate healthy and cancerous tissues. Additionally, the zebra optimization algorithm (ZOA) has been employed for optimal tuning of DBN hyperparameters to enhance the detection performance. The proposed model can be assessed by utilizing the benchmark laryngeal image dataset containing four tissue classes.
Conclusion: Experimental outcomes indicate that the proposed technique accomplishes boosted classification performance with an accuracy of 99.35%, outperforming existing methods under different evaluation metrics. The experimentation outcomes highlight the efficiency of the proposed method for reliable computer-aided LC diagnosis.
- Laryngeal Carcinoma, Deep Feature Fusion, Medical Image Analysis, Artificial Intelligence, Computer-aided diagnosis
How to Cite
References
[1] Sahoo PK, Mishra S, Panigrahi R, Bhoi AK, Barsocchi P. An improvised deep-learning-based mask R-CNN model for laryngeal cancer detection using CT images. Sensors. 2022;22(22):8834. [DOI: 10.3390/s22228834]
[2] Wellenstein DJ, Woodburn J, Marres HA, van den Broek GB. Detection of laryngeal carcinoma during endoscopy using artificial intelligence. Head Neck. 2023;45(9):2217-26. [DOI: 10.1002/hed.27441]
[3] Lee JC. Application of Artificial Intelligence (AI) in Laryngeal Cancer. J Clin Otolaryngol Head Neck Surg. 2023;34(2):27-35. [DOI: 10.35420/jcohns.2023.34.2.27]
[4] Nie X, Zhang X, Wang D, Liu Y, Xing L, Liu W. Laryngeal cancer diagnosis based on an improved YOLOv8 algorithm. Mach Learn Sci Technol. 2025;6(1):015011. [DOI: 10.1088/2632-2153/ada2d9]
[5] Al Khulayf AMF, Alamgeer M, Obayya M, Alqahtani M, Ebad SA, Aljehane NO, et al. Mathematical fusion of efficient transfer learning with a fine-tuning model for laryngeal cancer detection and classification in the throat region using biomedical images. Alex Eng J. 2025;129:658-671. [DOI: 10.1016/j.aej.2025.06.044]
[6] Joseph JS, Vidyarthi A, Singh VP. An improved approach for initial stage detection of laryngeal cancer using effective hybrid features and an ensemble learning method. Multimedia Tools Appl. 2024;83(6):17897-919. [DOI: 10.1007/s11042-023-16077-3]
[7] Alzakari SA, Maashi M, Alahmari S, Arasi MA, Alharbi AA, Sayed A. Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images. Sci Rep. 2024;14(1):19713. [DOI: 10.1007/s11042-023-16077-3]
[8] Joseph JS, Vidyarthi A. Dual deep learning and feature-based models for classification of laryngeal squamous cell carcinoma using narrow-band imaging. Trait Signal. 2024;41(1):237. [DOI: 10.18280/ts.410119]
[9] Naga Padmavathi P, Sree Devi M, Maheswara Rao VVR, Gopala Gupta AS. Construction of Cascaded Deep Neural Network with Optimization-Based Feature Selection in CT Images for Detecting Laryngeal Cancer. In: Innovative Product Design and Intelligent Manufacturing Systems. Singapore: Springer Nature Singapore; 2023. p. 459-72. [DOI: 10.18280/ts.410119]
[10] Luo J, Huang P, He P, Wei B, Guo X, Xiao H, et al. DCA-DAFFNet: An end-to-end network with deformable fusion attention and deep adaptive feature fusion for laryngeal tumor grading from histopathology images. IEEE Trans Instrum Meas. 2023;72:1-15. [DOI: 10.1109/TIM.2023.3328088]
[11] Bu Z, Zheng Y, Zheng Y, Yang L, Liao K, Liu T, et al. MIFRL: A Model for Automatic Diagnosis of Laryngeal Diseases Based on Multi-Modal Information Fusion. In: 2023 8th International Conference on Communication, Image and Signal Processing (CCISP). IEEE; 2023. p. 148-52. [DOI: 10.1109/CCISP59915.2023.10355778]
[12] Hajian M. Laryngeal Dataset [Internet]. Kaggle; 2023 [cited 2026 Aug 1]. [Link]
[13] Mohammad F, Al-Razgan M. Deep feature fusion and optimization-based approach for stomach disease classification. Sensors. 2022;22(7):2801. [DOI: 10.3390/s22072801]
[14] Andhare MS, Vijayan T, Karthik B, Urooj S. A Novel Optimized Hybrid Deep Learning Framework for Mental Stress Detection Using Electroencephalography. Brain Sci. 2025;15(8):835. [DOI: 10.3390/brainsci15080835]
[15] Ramadhani A, Robandi I, Djalal MR, Prakasa MA. Improving the Energy Management System with the Interval Type-2 Fuzzy Inference System–Zebra Optimization Algorithm (IT2FIS-ZOA) for Predicting the Load Consumption of Healthcare Facilities in the National Holiday Season. Eng Technol Appl Sci Res. 2025;15(4):25878-88. [DOI: 10.48084/etasr.12043]
[16] Xu ZH, Fan DG, Huang JQ, Wang JW, Wang Y, Li YZ. Computer-aided diagnosis of laryngeal cancer based on deep learning with laryngoscopic images. Diagnostics. 2023;13(24):3669. [DOI: 10.3390/diagnostics13243669]
[17] Ramamurthy K, George TT, Shah Y, Sasidhar P. A novel multi-feature fusion method for classification of gastrointestinal diseases using endoscopy images. Diagnostics. 2022;12(10):2316. [DOI: 10.3390/diagnostics12102316]
- Abstract Viewed: 167 times
- PDF Downloaded: 112 times