Hybrid LSTM/GRU-based Domain Adaptation Model for Correlation Analysis to Detect Glaucoma

International Journal of Electrical and Electronics Engineering

© 2023 by SSRG - IJEEE Journal

Volume 10 Issue 1

Year of Publication : 2023

Authors : Deepali M. Kotambkar, Pallavi M. Wankhede

10.14445/23488379/IJEEE-V10I1P116

How to Cite?

Deepali M. Kotambkar, Pallavi M. Wankhede, "Hybrid LSTM/GRU-based Domain Adaptation Model for Correlation Analysis to Detect Glaucoma," SSRG International Journal of Electrical and Electronics Engineering, vol. 10,  no. 1, pp. 168-175, 2023. Crossref, https://doi.org/10.14445/23488379/IJEEE-V10I1P116

Abstract:

Glaucoma identification is a multidomain task which involves the analysis of multimodal report sets. These sets include retinal scans from different sensors, blood report parameters, and eyesight reports. Existing glaucoma identification models either use a single report for analysis or suffer from domain adaptation issues, which limits their classification performance. Moreover, the models that use multidomain scans are highly complex and thus have limited scalability levels. To overcome these issues, the study of this text proposes the design of a hybrid Long-Short-Term Memory (LSTM) with a Gated Recurrent Unit (GRU) to identify glaucoma via correlation analysis. Both LSTM & GRU are individually capable of representing any signal into feature sets, but a hybrid combination of these models assists in the optimal representation of retinal reports via high-density feature analysis. These features are selected via a Genetic Algorithm (GA), which uses inter-class feature variation for fitness optimizations. The selected features are processed via a classification model that uses dual Convolutional Neural Networks (dCNNs) and assists in incorporating transfer learning during classification operations. The dCNN comprises a Recurrent Neural Network (RNN), which performs the initial classification of individual scans into approximate glaucoma levels. These approximate levels are fine-tuned by a customized CNN, which assists in identifying final glaucoma severity under clinical use cases. Correlation analysis between retinal scan components (including Macula, Arteries, Veins, and Optical Disc features) and glaucoma-specific blood reports & eyesight reports assist in continuous optimizations. Due to these operations, the proposed model can achieve 8.5% higher accuracy, 9.3% higher precision, and 4.9% higher recall, with 12.5% lower computational delay when compared with existing methods. These observed enhancements assist in deploying the model for real-time clinical use cases.

Keywords:

GRU, LSTM, GA, RNN, CNN, Macula, Veins, Optical Disc, Arteries.

References:

[1] Anita Manassakorn et al., "Glaunet: Glaucoma Diagnosis for OCTA Imaging Using A New CNN Architecture," IEEE Access, vol. 10, pp. 95613-95622, 2022, Crossref, https://doi.org/10.1109/ACCESS.2022.3204029
[2] R. Tamilaruvi et al., "Brain Tumor Detection in MRI Images Using Convolutional Neural Network Technique," SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 12, pp. 198-208, 2022. Crossref, https://doi.org/10.14445/23488379/IJEEE-V9I12P118
[3] Jiyeon Kim et al., "Feature Analysis of IoT Botnet Attacks Based on RNN and LSTM," International Journal of Engineering Trends and Technology, vol. 68, no. 4, pp. 43-47, 2020. Crossref, https://doi.org/10.14445/22315381/IJETT-V68I4P208S
[4] Patthapol Kunumpol et al., "Glaucutu: Time Until Perceived Virtual Reality Perimetry with Humphrey Field Analyzer Prediction-Based Artificial Intelligence," IEEE Access, vol. 10, pp. 36949-36962, 2022, Crossref, https://doi.org/10.1109/ACCESS.2022.3163845
[5] Wheyming Tina Song, Ing-Chou Lai, and Yi-Zhu Su, "A Statistical Robust Glaucoma Detection Framework Combining Retinex, CNN, and DOE Using Fundus Images," IEEE Access, vol. 9, pp. 103772-103783, 2021. Crossref, https://doi.org/10.1109/ACCESS.2021.3098032
[6] Devangjani, and Anandmankodia, "A Novel Approach for Real Time Multi-Scene Violent Activities Recognition with Modified Resnet50 and LSTM," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 292-309, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I8P231
[7] Deepak Parashar, and Dheeraj Agrawal, "2-D Compact Variational Mode Decomposition- Based Automatic Classification of Glaucoma Stages from Fundus Images," IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-10, 2021, Crossref, https://doi.org/10.1109/TIM.2021.3071223
[8] Megha V. Gupta, and Shubhangi L. Vaikole, "A Parallel Fusion RNN-LSTM Approach to Classify Mental Stress Using EEG Data," International Journal of Engineering Trends and Technology, vol. 70, no. 10, pp. 285-297, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I10P228
[9] Murthy V. S. N. Tatavarthy, and V. Naga Lakshmi, "Pedagogical Content Knowledge Classification Using CNN with Bi-LSTM," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 264-271, 2022.Crossref, https://doi.org/10.14445/22315381/IJETT-V70I8P228
[10] Diping Song et al., "Deep Relation Transformer for Diagnosing Glaucoma with Optical Coherence Tomography and Visual Field Function," IEEE Transactions on Medical Imaging, vol. 40, no. 9, pp. 2392-2402, 2021. Crossref, https://doi.org/10.1109/tmi.2021.3077484
[11] D. Parashar, and D. K. Agrawal, "Automatic Classification of Glaucoma Stages Using Two-Dimensional Tensor Empirical Wavelet Transform," IEEE Signal Processing Letters, vol. 28, pp. 66-70, 2021, Crossref, https://doi.org/10.1109/LSP.2020.3045638
[12] Tianjipeng, Manasa S, and Dr. T.C.Manjunath, "Early Detection of Eye Disease in Humans Using Random forest & HOG Concepts," SSRG International Journal of Electronics and Communication Engineering, vol. 7, no. 4, pp. 5-7, 2020. Crossref, https://doi.org/10.14445/23488549/IJECE-V7I4P102 
[13] Alu E. S., Aniobi D. E., and Ijah S. T., "Mobile Expert System on Febrile Diseases,” International Journal of Computer & Organization Trends, vol. 7, no. 4, pp. 1-11, 2017.
[14] Dr. B. Sakthivel et al., "IoT Based Solar Power Monitoring and Prediction Using Cuckoo Optimized LSTM," International Journal of P2P Network Trends and Technology, vol. 11, no. 2, pp. 6-8, 2021. Crossref, https://doi.org/10.14445/22492615/IJPTT-V11I2P402
[15] Manal Alghamdi, and Mohamad Abdel-Mottaleb, "A Comparative Study of Deep Learning Models for Diagnosing Glaucoma From Fundus Images," IEEE Access, vol. 9, pp. 23894-23906, 2021. Crossref, https://doi.org/10.1109/ACCESS.2021.305664
[16] Mir Tanvir Islam et al., "Deep Learning-Based Glaucoma Detection with Cropped Optic Cup and Disc and Blood Vessel Segmentation," IEEE Access, vol. 10, pp. 2828-2841, 2022, Crossref, https://doi.org/10.1109/ACCESS.2021.3139160
[17] Ms.S.Deepa, and Mr.S.Vijayprasath, "Certain Investigation of the Retinal Hemorrhage Detection in Fundus Images," SSRG International Journal of Electronics and Communication Engineering, vol. 2, no. 2, pp. 24-34, 2015. Crossref, https://doi.org/10.14445/23488549/IJECE-V2I2P106
[18] Poonam S. Panaskar, and Varsha D.Jadhav, "Nutritional, Antioxidant and GCMS Screening of Antidesma MONTANUM bl. Leaves," SSRG International Journal of Medical Science, vol. 6, no. 8, pp. 1-9, 2019. Crossref, https://doi.org/10.14445/23939117/IJMS-V6I8P101
[19] Ozer Can Devecioglu et al., "Real-Time Glaucoma Detection from Digital Fundus Images Using Self-Onns," IEEE Access, vol. 9, pp. 140031-140041, 2021. Crossref, https://doi.org/10.1109/ACCESS.2021.3118102
[20] Dr. R. Surendiran et al., "Effective Autism Spectrum Disorder Prediction to Improve the Clinical Traits Using Machine Learning Techniques," International Journal of Engineering Trends and Technology, vol. 70, no. 4, pp. 343-359, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I4P230
[21] S. Krishnan, J. Amudha, and Sushma Tejwani, "Gaze Exploration Index (GE I)-Explainable Detection Model for Glaucoma," IEEE Access, vol. 10, pp. 74334-74350, 2022. Crossref, https://doi.org/10.1109/ACCESS.2022.3188987
[22] Quoc Cuong Ngo et al., "Pupillary Complexity for the Screening of Glaucoma," IEEE Access, vol. 9, pp. 144871-144879, 2021, Crossref, https://doi.org/10.1109/ACCESS.2021.3122079
[23] Oluwatobi Joshua Afolabi et al., "The Use of U-Net Lite and Extreme Gradient Boost (XGB) for Glaucoma Detection," IEEE Access, vol. 9, pp. 47411-47424, 2021, Doi: 10.1109/ACCESS.2021.3068204.
[24] Kaveri A Thakoor et al., "Robust and Interpretable Convolutional Neural Networks to Detect Glaucoma in Optical Coherence Tomography Images," IEEE Transactions on Biomedical Engineering, vol. 68, no. 8, pp. 2456-2466, 2021.Crossref, https://doi.org/10.1109/tbme.2020.3043215
[25] Tianjipeng, Suma P, and Dr. T.C.Manjunath, "AI, ML and the Eye Disease Detection," SSRG International Journal of Computer Science and Engineering, vol. 7, no. 4, pp. 1-3, 2020. Crossref, https://doi.org/10.14445/23488387/IJCSE-V7I4P101
[26] Mohammed Yesufgetu, and Husain Shahnawaz, "A Proposed Model for Health Management and Expert Diagnosis System for the Prediction of Common Diseases for Ethiopia (East Africa)," SSRG International Journal of Medical Science, vol. 5, no. 2, pp. 1-9, 2018. Crossref, https://doi.org/10.14445/23939117/IJMS-V5I2P101
[27] Ronald H Silverman et al., "High-Frequency Ultrasound Activation of Perfluorocarbon Nanodroplets for Treatment of Glaucoma," IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 69, no. 6, pp. 1910-1916, 2022, Crossref, https://doi.org/10.1109/tuffc.2022.3142679.
[28] Dr. R. Surendiran et al., "Exploring the Cervical Cancer Prediction by Machine Learning and Deep Learning with Artificial Intelligence Approaches," International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 94-107, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P211
[29] Md. Sarwar Kamal et al., "Explainable AI for Glaucoma Prediction Analysis to Understand Risk Factors in Treatment Planning," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-9, 2022, Crossref, https://doi.org/10.1109/TIM.2022.3171613
[30] Dr. R. Surendiran et al., "A Systematic Review Using Machine Learning Algorithms for Predicting Preterm Birth," International Journal of Engineering Trends and Technology, vol. 70, no. 5, pp. 46-59, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I5P207
[31] Sakshi Goyal, and Deepali. M. Kotambkar, “Exploring Unet Architecture for Semantic Segmentation of the Brain MRI Scans,” Advanced Machine Intelligence and Signal Processing, Springer, vol. 858, 2022. Crossref, https://doi.org/10.1007/978-981-19- 0840-8_43