FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-130207

Research Article |

Performance Driven Outlier Detection in Health-Care Data: A Hybrid Approach Using Dual-Feature Optimization and Segmentation Techniques

Author(s): Ankita Roy1*, Atul Garg2

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 13, Issue 2

Publisher : FOREX Publication

Published : 30 May 2025

e-ISSN : 2347-470X

Page(s) : 237-249

DOI: https://doi.org/10.37391/IJEER.130207

Abstract

The healthcare sector is a domain where the implementation of human-centered design approaches and concepts can significantly impact well-being and patient care. Delivering superior medical care necessitates a profound comprehension of an individual's desires, encounters, and interests. This study examined the quantitative evaluation and utilization of MRI scans for preoperative conditions of the brain, lungs, and heart. However, identifying these intricate compositions is a formidable challenge. Traditional diagnostic methods are laborious and rely heavily on the clinical expertise of radiologists. This research proposes a non-invasive automatic diagnosis system for diseases utilizing hybrid deep learning approaches, specifically LSTM & PSO (Long Short-Term Memory & Particle Swarm Optimization), to improve the efficiency of outlier detection. Initially, images are initialized to generate standardized images. Next, an improved histogram equalization technique is used to improve the low-contrast MRI images. Finally, segmentation is performed using heat map and contouring techniques based on outlier detection. The findings indicate that the approach developed in this study is capable of classifying distinct groups of brain, lungs, and heart diseases through MRI images. The process involves extracting several physiognomies of the tumor and subsequently selecting the most suitable features through a combination of optimal feature selection techniques, namely PCA (Principal Component Analysis) and t-SNE (t-Distributed Stochastic Neighbor). The results demonstrate that the proposed approach exhibits superior productivity and effectiveness, and achieved an accuracy of 98.58%, 98.47%, and 98.58% on brain, lungs, and heart MRI images respectively, offering enhanced reliability and healthcare solution inclusively.

Keywords: Brain tumors , Diseases, Deep learning, Health, Optimization, Outliers.




Ankita Roy, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India; Email: ankita1001cs.phd20@chitkara.edu.in

Atul Garg, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India; Email: atul.garg@chitkara.edu.in

    [1] M. Manthe, S. Duffner, and C. Lartizien, ‘Whole brain radiomics for clustered federated personalization in brain tumor segmentation’, in Medical Imaging with Deep Learning, 2024, pp. 957–977.Çinar, A., & Yildirim, M. (2020). Detection of tumors on brain MRI images using the hybrid convolutional neural network architecture. Medical hypotheses, 139, 109684.
    [2] A. Çinar and M. Yildirim, ‘Detection of tumors on brain MRI images using the hybrid convolutional neural network architecture’, Medical hypotheses, vol. 139, p. 109684, 2020.
    [3] A. Garg and Others, ‘Outlier detection system for cardiovascular disease using time-series data: A comparative analysis’, in 2023 IEEE 2nd International Conference on Industrial Electronics: Developments & Applications (ICIDeA), 2023, pp. 378–382.
    [4] A. Humeau-Heurtier, ‘Texture feature extraction methods: A survey’, IEEE access, vol. 7, pp. 8975–9000, 2019.
    [5] M. M. Ahmed, A. Ali, B. N. Hashmi, W. K. Mashwani, and N. Gündüz, ‘Review on Medical Image Segmentation and Feature Extraction Approaches’, Journal of Independent Studies and Research Computing, vol. 21, no. 2, pp. 5–15, 2023.
    [6] J. He and X. Bi, ‘Automatic classification of spinal osteosarcoma and giant cell tumor of bone using optimized DenseNet’, Journal of Bone Oncology, vol. 46, p. 100606, 2024.
    [7] https://www.kaggle.com/datasets/danialsharifrazi/cad-cardiac-mri-dataset assessed on march 2024.
    [8] “Kaggle: Your Home for Data Science.” [Online]. Available: https://www.kaggle.com/datasets/shreyag1103/brain-mri-scans-for-brain-tumor-classification assessed on march 2024
    [9] https://www.kaggle.com/datasets/adityamahimkar/iqothnccd-lung-cancer-dataset assessed on march 2024.
    [10] H. Naveed, S. Anwar, M. Hayat, K. Javed, and A. Mian, ‘Survey: Image mixing and deleting for data augmentation’, Engineering applications of artificial intelligence, vol. 131, p. 107791, 2024.
    [11] C. Hu, H. Li, T. Ma, C. Zeng, and X. Ji, ‘An improved image enhancement algorithm: Radial contrast-limited adaptive histogram equalization’, Multimedia Tools and Applications, vol. 83, no. 36, pp. 83695–83707, 2024.
    [12] A. Naser, ‘A proposed CLCOA Technique Based on CLAHE using Cat Optimized Algorithm for Plants Images Enhancement’, Wasit Journal of Computer and Mathematics Science, vol. 3, no. 1, pp. 18–27, 2024.
    [13] B. Qian et al., ‘Deep contour attention learning for scleral deformation from OCT images’, The Visual Computer, vol. 41, no. 2, pp. 1155–1170, 2025.
    [14] J. Haferkamp, M. W. Ulmer, and J. F. Ehmke, ‘Heatmap-based decision support for repositioning in ride-sharing systems’, Transportation Science, vol. 58, no. 1, pp. 110–130, 2024.
    [15] I. Pavlŭ, J. Machalová, R. Tolosana-Delgado, K. Hron, K. Bachmann, and K. G. van den Boogaart, ‘Principal component analysis for distributions observed by samples in Bayes spaces’, Mathematical Geosciences, vol. 56, no. 8, pp. 1641–1669, 2024.
    [16] A. Ala, V. Simic, D. Pamucar, and N. Bacanin, ‘Enhancing patient information performance in internet of things-based smart healthcare system: Hybrid artificial intelligence and optimization approaches’, Engineering Applications of Artificial Intelligence, vol. 131, p. 107889, 2024.
    [17] L. Xia, C. Lee, and J. J. Li, ‘Statistical method scDEED for detecting dubious 2D single-cell embeddings and optimizing t-SNE and UMAP hyperparameters’, Nature Communications, vol. 15, no. 1, p. 1753, 2024.
    [18] J. Huang, F. Wang, L. Qiao, and X. Yang, ‘T-distributed stochastic neighbor embedding echo state network with state matrix dimensionality reduction for time series prediction’, Engineering Applications of Artificial Intelligence, vol. 122, p. 106055, 2023.
    [19] I. Sembiring, S. N. Wahyuni, and E. Sediyono, ‘LSTM algorithm optimization for COVID-19 prediction model’, Heliyon, vol. 10, no. 4, 2024.
    [20] P. Dhiman, V. Kukreja, and A. Kaur, ‘Citrus fruits classification and evaluation using deep convolution neural networks: an input layer resizing approach’, in 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), 2021, pp. 1–4.
    [21] P. Dhiman et al., ‘PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment’, EURASIP Journal on Advances in Signal Processing, vol. 2023, no. 1, p. 72, 2023.P. Dhiman, “Citrus Fruits Classification and Evaluation using Deep Convolution Neural Networks: An Input Layer Resizing Approach,” pp. 21–24, 2021.
    [22] A. Sharma, R. Kumar, and V. Jaiswal, ‘Classification of heart disease from MRI images using convolutional neural network’, in 2021 6th international conference on signal processing, computing and control (ISPCC), 2021, pp. 358–363.
    [23] F. Yan, H. Huang, W. Pedrycz, and K. Hirota, ‘A disease diagnosis system for smart healthcare based on fuzzy clustering and battle royale optimization’, Applied Soft Computing, vol. 151, p. 111123, 2024.
    [24] Y. Wang et al., ‘A brain MRI dataset and baseline evaluations for tumor recurrence prediction after Gamma Knife radiotherapy’, Scientific Data, vol. 10, no. 1, p. 785, 2023.
    [25] S. Ashwini, J. R. Arunkumar, R. T. Prabu, N. H. Singh, and N. P. Singh, ‘Diagnosis and multi-classification of lung diseases in CXR images using optimized deep convolutional neural network’, Soft Computing, vol. 28, no. 7, pp. 6219–6233, 2024.
    [26] S. Pal, R. P. Singh, and A. Kumar, ‘Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data’, Journal of Medical Physics, vol. 49, no. 1, pp. 22–32, 2024.

Ankita Roy, and Atul Garg (2025), Performance Driven Outlier Detection in Health-Care Data: A Hybrid Approach Using Dual-Feature Optimization and Segmentation Techniques. IJEER 13(2), 237-249. DOI: 10.37391/IJEER.130207.