An Optuna-Based Metaheuristic Optimization Framework for Biomedical Image Analysis
Received: 31 March 2025 | Revised: 29 April 2025 | Accepted: 4 May 2025 | Online: 25 May 2025
Corresponding author: Thavavel Vaiyapuri
Abstract
The success of Deep Learning (DL) in biomedical imaging heavily relies on optimal hyperparameter selection, which remains a complex and computationally intensive challenge. This paper introduces a metaheuristic-inspired Optuna framework for efficient hyperparameter optimization and validates its effectiveness using U-Net as a case study for brain MRI segmentation, leveraging Bayesian Optimization (BO) with adaptive pruning and Tree-structured Parzen Estimator (TPE). The proposed framework dynamically searches the hyperparameter space to maximize segmentation accuracy while reducing training overhead. The proposed framework adjusts key architectural, training, and regularization parameters, including the number of filters, optimizer, learning rate, and dropout rate, using a well-defined search space. Experimental results on a brain MRI dataset demonstrate that the proposed framework achieved mean scores of 0.941, 0.8763, and 0.983 for Dice Coefficient (DC), Intersection over Union (IoU), and Structural Similarity Index (SSIM), respectively, with 95% confidence intervals. These results confirm Optuna's effectiveness over traditional and metaheuristic baselines and demonstrate its scalability for broader biomedical AI applications.
Keywords:
hyperparameter optimization, metaheuristic algorithms, Bayesian optimization, Optuna framework, lightweight U-Net, biomedical image analysis, brain MRI segmentationDownloads
References
E. H. Houssein, E. Saber, A. A. Ali, and Y. M. Wazery, "Integrating metaheuristics and artificial intelligence for healthcare: basics, challenging and future directions," Artificial Intelligence Review, vol. 57, no. 8, Jul. 2024, Art. no. 205. DOI: https://doi.org/10.1007/s10462-024-10822-2
M. J. Tsai, C. H. Lin, J. P. Lai, and P. F. Pai, "Using Deep Learning, Optuna, and Digital Images to Identify Necrotizing Fasciitis," Electronics, vol. 13, no. 22, Jan. 2024, Art. no. 4421. DOI: https://doi.org/10.3390/electronics13224421
H. Sun et al., "Brain tumor image segmentation based on improved FPN," BMC Medical Imaging, vol. 23, no. 1, Oct. 2023, Art. no. 172. DOI: https://doi.org/10.1186/s12880-023-01131-1
T. H. Tran, P. A. Nguyen, L. A. Ngoc, D. T. Tran, and M. T. Pham, "Optimal CNN Model for Obstructive Sleep Apnea Detection using Particle Swarm Optimization," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19553–19560, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9154
M. A. Ottom, H. A. Rahman, and I. D. Dinov, "Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation," IEEE Journal of Translational Engineering in Health and Medicine, vol. 10, pp. 1–8, 2022. DOI: https://doi.org/10.1109/JTEHM.2022.3176737
S. Adamu et al., "Unleashing the power of Manta Rays Foraging Optimizer: A novel approach for hyper-parameter optimization in skin cancer classification," Biomedical Signal Processing and Control, vol. 99, Jan. 2025, Art. no. 106855. DOI: https://doi.org/10.1016/j.bspc.2024.106855
M. Sreevani and R. Latha, "A Deep Learning with Metaheuristic Optimization-Driven Breast Cancer Segmentation and Classification Model using Mammogram Imaging," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20342–20347, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9406
M. Aljohani et al., "An automated metaheuristic-optimized approach for diagnosing and classifying brain tumors based on a convolutional neural network," Results in Engineering, vol. 23, Sep. 2024, Art. no. 102459. DOI: https://doi.org/10.1016/j.rineng.2024.102459
T. Vaiyapuri, "Utilizing Explainable AI and Biosensors for Clinical Diagnosis of Infectious Vector-Borne Diseases," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18640–18648, Dec. 2024. DOI: https://doi.org/10.48084/etasr.9026
L. Zhang, Z. Qiao, and L. Li, "An Evolutionary Deep Learning Method Based on Improved Heap-Based Optimization for Medical Image Classification and Diagnosis," IEEE Access, vol. 12, pp. 102745–102773, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3433483
T. Vaiyapuri, H. Alaskar, Z. Sbai, and S. Devi, "GA-based multi-objective optimization technique for medical image denoising in wavelet domain," Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 1575–1588, Aug. 2021. DOI: https://doi.org/10.3233/JIFS-210429
P. Deepan, G. Prabhakar Reddy, M. Arsha Reddy, R. Vidya, and S. Dhiravidaselvi, "Maximizing Accuracy in Alzheimer’s Disease Prediction: A Optuna Hyper Parameter Optimization Strategy Using MRI Images," in Revolutionizing Healthcare 5.0: The Power of Generative AI: Advancements in Patient Care Through Generative AI Algorithms, P. Bhattacharya, H. Liu, P. K. Dutta, J. J. P. C. Rodrigues, and G. Sethi, Eds. Springer Nature Switzerland, 2024, pp. 77–91. DOI: https://doi.org/10.1007/978-3-031-75771-6_5
S. Thirumalaisamy et al., "Breast Cancer Classification Using Synthesized Deep Learning Model with Metaheuristic Optimization Algorithm," Diagnostics, vol. 13, no. 18, Jan. 2023, Art. no. 2925. DOI: https://doi.org/10.3390/diagnostics13182925
J. D. Dorathi Jayaseeli et al., "An intelligent framework for skin cancer detection and classification using fusion of Squeeze-Excitation-DenseNet with Metaheuristic-driven ensemble deep learning models," Scientific Reports, vol. 15, no. 1, Mar. 2025, Art. no. 7425. DOI: https://doi.org/10.1038/s41598-025-92293-1
M. K. Bohmrah and H. Kaur, "Advanced Hybridization and Optimization of DNNs for Medical Imaging: A Survey on Disease Detection Techniques," Artificial Intelligence Review, vol. 58, no. 4, Feb. 2025, Art. no. 122. DOI: https://doi.org/10.1007/s10462-024-11049-x
Q. S. Hamad, H. Samma, and S. A. Suandi, "Optimization of Convolutional Neural Network Hyperparameter for Medical Image Diagnosis using Metaheuristic Algorithms: A short Recent Review (2019-2022)." arXiv, Dec. 23, 2024.
J. Nithisha et al., "Fuzzy Hybrid Meta-optimized Learning-based Medical Image Segmentation System for Enhanced Diagnosis," International Journal of Information Technology and Computer Science, vol. 17, no. 1, pp. 47–66, Feb. 2025. DOI: https://doi.org/10.5815/ijitcs.2025.01.04
N. Bansal and A. Vidyarthi, "Hierarchical Meta-Heuristic Encoder-Decoder Architecture With Next-Generation Imaging for Consumer-Centric Segmentation of Diabetic Foot Ulcers," IEEE Transactions on Consumer Electronics, pp. 1–1, 2025. DOI: https://doi.org/10.1109/TCE.2025.3532639
H. M. Balaha et al., "AOA-guided hyperparameter refinement for precise medical image segmentation," Alexandria Engineering Journal, vol. 120, pp. 547–560, May 2025. DOI: https://doi.org/10.1016/j.aej.2025.02.037
A. Hamza et al., "A chaotic variant of the Golden Jackal Optimizer and its application for medical image segmentation," Applied Intelligence, vol. 55, no. 4, Jan. 2025, Art. no. 295. DOI: https://doi.org/10.1007/s10489-024-06084-8
P. K. Sahu and T. Fatma, "Optimized Breast Cancer Classification Using PCA-LASSO Feature Selection and Ensemble Learning Strategies With Optuna Optimization," IEEE Access, vol. 13, pp. 35645–35661, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3539746
K. Clark et al., "The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository," Journal of Digital Imaging, vol. 26, no. 6, pp. 1045–1057, Dec. 2013. DOI: https://doi.org/10.1007/s10278-013-9622-7
M. Buda, A. Saha, and M. A. Mazurowski, "Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm," Computers in Biology and Medicine, vol. 109, pp. 218–225, Jun. 2019. DOI: https://doi.org/10.1016/j.compbiomed.2019.05.002
M. Irfan et al., "Effectiveness of Deep Learning Models for Brain Tumor Classification and Segmentation," Computers, Materials & Continua, vol. 76, no. 1, pp. 711–729, 2023. DOI: https://doi.org/10.32604/cmc.2023.038176
A. Kotte and V. K. Prasad, "Hybrid 3D U-Net and Attention Mechanisms for Whole Heart Segmentation from CT Images," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21822–21828, Apr. 2025. DOI: https://doi.org/10.48084/etasr.10115
K. Hamed and U. Ozgunalp, "A Comparative Analysis of Pretrained Models for Brain Tumaor Classification and Their Optimization Using Optuna," in 2024 Innovations in Intelligent Systems and Applications Conference (ASYU), Ankara, Turkiye, Oct. 2024, pp. 1–7. DOI: https://doi.org/10.1109/ASYU62119.2024.10757117
S. Ghosh, A. Chaki, and K. Santosh, "Improved U-Net architecture with VGG-16 for brain tumor segmentation," Physical and Engineering Sciences in Medicine, vol. 44, no. 3, pp. 703–712, Sep. 2021. DOI: https://doi.org/10.1007/s13246-021-01019-w
A. C. Yadav, M. H. Kolekar, Y. Sonawane, G. Kadam, S. Tiwarekar, and D. R. Kalbande, "EffUNet++: A Novel Architecture for Brain Tumor Segmentation Using FLAIR MRI Images," IEEE Access, vol. 12, pp. 152430–152443, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3480271
Downloads
How to Cite
License
Copyright (c) 2025 Thavavel Vaiyapuri
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.
