HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification
Abstract Optical Coherence Tomography (OCT) plays a crucial role in diagnosing ocular diseases, yet conventional CNN-based models face limitations such as high computational overhead, noise sensitivity, and data imbalance. This paper introduces HDL-ACO, a novel Hybrid Deep Learning (HDL) framework t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89961-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850039851138678784 |
|---|---|
| author | Shivani Agarwal Anand Kumar Dohare Pranshu Saxena Jagendra Singh Indrasen Singh Umesh Kumar Sahu |
| author_facet | Shivani Agarwal Anand Kumar Dohare Pranshu Saxena Jagendra Singh Indrasen Singh Umesh Kumar Sahu |
| author_sort | Shivani Agarwal |
| collection | DOAJ |
| description | Abstract Optical Coherence Tomography (OCT) plays a crucial role in diagnosing ocular diseases, yet conventional CNN-based models face limitations such as high computational overhead, noise sensitivity, and data imbalance. This paper introduces HDL-ACO, a novel Hybrid Deep Learning (HDL) framework that integrates Convolutional Neural Networks with Ant Colony Optimization (ACO) to enhance classification accuracy and computational efficiency. The proposed methodology involves pre-processing the OCT dataset using discrete wavelet transform and ACO-optimized augmentation, followed by multiscale patch embedding to generate image patches of varying sizes. The hybrid deep learning model leverages ACO-based hyperparameter optimization to enhance feature selection and training efficiency. Furthermore, a Transformer-based feature extraction module integrates content-aware embeddings, multi-head self-attention, and feedforward neural networks to improve classification performance. Experimental results demonstrate that HDL-ACO outperforms state-of-the-art models, including ResNet-50, VGG-16, and XGBoost, achieving 95% training accuracy and 93% validation accuracy. The proposed framework offers a scalable, resource-efficient solution for real-time clinical OCT image classification. |
| format | Article |
| id | doaj-art-e7b868dff6fc4a509089fbab9411593c |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e7b868dff6fc4a509089fbab9411593c2025-08-20T02:56:12ZengNature PortfolioScientific Reports2045-23222025-02-0115111210.1038/s41598-025-89961-7HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classificationShivani Agarwal0Anand Kumar Dohare1Pranshu Saxena2Jagendra Singh3Indrasen Singh4Umesh Kumar Sahu5Department of Information Technology, Ajay Kumar Garg Engineering CollegeDepartment of Information Technology, Greater Noida Institute of Technology (Engg. Institute)School of Computer Science Engineering & Technology, Bennett UniversitySchool of Computer Science Engineering & Technology, Bennett UniversitySchool of Electronics Engineering, Vellore Institute of TechnologyDepartment of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher EducationAbstract Optical Coherence Tomography (OCT) plays a crucial role in diagnosing ocular diseases, yet conventional CNN-based models face limitations such as high computational overhead, noise sensitivity, and data imbalance. This paper introduces HDL-ACO, a novel Hybrid Deep Learning (HDL) framework that integrates Convolutional Neural Networks with Ant Colony Optimization (ACO) to enhance classification accuracy and computational efficiency. The proposed methodology involves pre-processing the OCT dataset using discrete wavelet transform and ACO-optimized augmentation, followed by multiscale patch embedding to generate image patches of varying sizes. The hybrid deep learning model leverages ACO-based hyperparameter optimization to enhance feature selection and training efficiency. Furthermore, a Transformer-based feature extraction module integrates content-aware embeddings, multi-head self-attention, and feedforward neural networks to improve classification performance. Experimental results demonstrate that HDL-ACO outperforms state-of-the-art models, including ResNet-50, VGG-16, and XGBoost, achieving 95% training accuracy and 93% validation accuracy. The proposed framework offers a scalable, resource-efficient solution for real-time clinical OCT image classification.https://doi.org/10.1038/s41598-025-89961-7Optical coherence tomographyHybrid deep learningAnt colony optimizationHyperparameter tuningData ImbalanceOCT image classification |
| spellingShingle | Shivani Agarwal Anand Kumar Dohare Pranshu Saxena Jagendra Singh Indrasen Singh Umesh Kumar Sahu HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification Scientific Reports Optical coherence tomography Hybrid deep learning Ant colony optimization Hyperparameter tuning Data Imbalance OCT image classification |
| title | HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| title_full | HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| title_fullStr | HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| title_full_unstemmed | HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| title_short | HDL-ACO hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| title_sort | hdl aco hybrid deep learning and ant colony optimization for ocular optical coherence tomography image classification |
| topic | Optical coherence tomography Hybrid deep learning Ant colony optimization Hyperparameter tuning Data Imbalance OCT image classification |
| url | https://doi.org/10.1038/s41598-025-89961-7 |
| work_keys_str_mv | AT shivaniagarwal hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification AT anandkumardohare hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification AT pranshusaxena hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification AT jagendrasingh hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification AT indrasensingh hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification AT umeshkumarsahu hdlacohybriddeeplearningandantcolonyoptimizationforocularopticalcoherencetomographyimageclassification |