Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models

Sheikh Afaan Farooq; Aleem Ali

doi:10.35377/saucis...1766963

EN

Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models

Abstract

The disorders that affect the lungs require a careful diagnosis, which relies on medical imaging such as chest X-rays for efficient detection. Convolutional neural networks show a lot of promise as a deep learning model in the automation of medical diagnosis, though in most cases, their success ends up being attached to how well the right features are chosen. In this work, three broad types of feature selection methods, which are the filter methods, the wrapper methods and the embedded methods, are analyzed on a chest X-ray dataset for their role in improving the performance of deep-learning methods in the classification of medical images. The evaluation metrics of the individual methods, which are classified into their specific broad types, are calculated. The results show that embedded techniques like Light Gradient Boosting Machine, along with filter methods such as Independent Component Analysis and Recursive Feature Elimination, which is a wrapper method, performed better, while the Mutual Information, which is a filter method, performed worst among the methods. The results eventually showed the highest difference in accuracy, being about 7.9%. In conclusion, these results establish the key role that the correct choice of a feature selection method plays in efficient medical image classification.

Keywords

References

N. A. Abujabal, A. B. Nassif, and J. S. Muhammad, “Optimizing lung cancer prediction through feature selection-based machine learning models,” 2024 Advances in Science and Engineering Technology International Conferences (ASET), pp. 1–6, Jun. 2024. doi: 10.1109/aset60340.2024.10708717
A. Alsahaf, N. Petkov, V. Shenoy, and G. Azzopardi, “A framework for feature selection through boosting,” Expert Systems with Applications, vol. 187, p. 115895, Jan. 2022. doi: 10.1016/j.eswa.2021.115895
Muhammad Umair Ali et al., “Correlation-filter-based channel and feature selection framework for hybrid EEG-fNIRS BCI applications,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 6, pp. 3361–3370, Jun. 2024. doi: 10.1109/jbhi.2023.3294586
N. Bellarmino, R. Cantoro, M. Huch, T. Kilian, U. Schlichtmann, and G. Squillero, “Embedded Feature Selection in MCU Performance Screening,” 2024 IEEE International Conference on Design, Test and Technology of Integrated Systems (DTTIS), pp. 1–6, Oct. 2024. doi: 10.1109/dttis62212.2024.10780418
J. Ehrhardt, and M. Wilms, “Autoencoders and variational autoencoders in medical image analysis,” Elsevier eBooks, pp. 129–162, Jan. 2022. doi: 10.1016/b978-0-12-824349-7.00015-3
T. D. Jui, and P. Rivas, “Fairness issues, current approaches, and challenges in machine learning models,” International Journal of Machine Learning and Cybernetics, vol. 15, pp. 3095–3125, Jan. 2024. doi: 10.1007/s13042-023-02083-2
A. Torang, P. Gupta, and D. J. Klinke, “An elastic-net logistic regression approach to generate classifiers and gene signatures for types of immune cells and T helper cell subsets,” BMC Bioinformatics, vol. 20, no. 1, Aug. 2019. doi: 10.1186/s12859-019-2994-z
B. Venkatesh, and J. Anuradha, “A Review of Feature Selection and Its Methods,” Cybernetics and Information Technologies, vol. 19, no. 1, pp. 3–26, Mar. 2019. doi: 10.2478/cait-2019-0001

Y. Xing, D. Li, and C. Li, “Time series prediction via elastic net regularization integrating partial autocorrelation,” Applied Soft Computing, vol. 129, pp. 109640–109640, Nov. 2022. doi: 10.1016/j.asoc.2022.109640
H. Wang, “A novel feature selection method based on quantum support vector machine,” Physica Scripta, vol. 99, no. 5, p. 056006, Apr. 2024. doi: 10.1088/1402-4896/ad36ef
W. Ying, D. Wang, H. Chen, and Y. Fu, “Feature Selection as Deep Sequential Generative Learning,” arXiv.org, 2024. doi: 10.48550/arXiv.2403.03838
N. S. Tzannes, and J. P. Noonan, “The mutual information principle and applications,” Information and Control, vol. 22, no. 1, pp. 1–12, Feb. 1973. doi: 10.1016/s0019-9958(73)90448-8
S. Gupta, and S. Gupta, “Feature Extraction and Feature Selection Procedures for Medical Image Analysis,” Advances in medical technologies and clinical practice book series, pp. 221–280, Oct. 2024. doi: 10.4018/979-8-3693-5226-7.ch010
J. Paolino, “Using summary tables to introduce principal component analysis in an elementary data science course,” Teaching Statistics, Jun. 2024. doi: 10.1111/test.12375
M. Jasmine Pemeena Priyadarsini et al., “Lung Diseases Detection Using Various Deep Learning Algorithms,” Journal of Healthcare Engineering, vol. 2023, p. e3563696, Feb. 2023. doi: 10.1155/2023/3563696
D. Patel, A. Saxena, and J. Wang, “A machine learning-based wrapper method for feature selection,” International Journal of Data Warehousing and Mining, vol. 20, no. 1, pp. 1–33, Sep. 2024. doi: 10.4018/ijdwm.352041
A. Tharwat, “Independent component analysis: An introduction,” Applied Computing and Informatics, vol. 17, no. 2, Aug. 2018. doi: 10.1016/j.aci.2018.08.006
R. J. Urbanowicz, M. Meeker, W. La Cava, R. S. Olson, and J. H. Moore, “Relief-based feature selection: Introduction and review,” Journal of Biomedical Informatics, vol. 85, pp. 189–203, Sep. 2018. doi: 10.1016/j.jbi.2018.07.014
W. Zhao, G. Li, H. Yang, Q. Gao, and Q. Wang, “Embedded feature selection on graph-based multi-view clustering,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 15, pp. 17016–17023, Mar. 2024. doi: 10.1609/aaai.v38i15.29645
X. Cheng, “A comprehensive study of feature selection techniques in machine learning models,” SSRN Electronic Journal, Jan. 2025. doi: 10.2139/ssrn.5154947
I. Madakkatel, and E. Hyppönen, “LLpowershap: logistic loss-based automated Shapley values feature selection method,” BMC Medical Research Methodology, vol. 24, no. 1, Oct. 2024. doi: 10.1186/s12874-024-02370-8
E. M. Maseno, and Z. Wang, “Hybrid wrapper feature selection method based on genetic algorithm and extreme learning machine for intrusion detection,” Journal of Big Data, vol. 11, no. 1, Feb. 2024. doi: 10.1186/s40537-024-00887-9
F. Zandi, P. Mansouri, and R. Sheibani, “Selecting the optimal classifier for wrapper-based feature selection methods,” Proceedings of the Pakistan Academy of Sciences: A. Physical and Computational Sciences, vol. 61, no. 3, Sep. 2024. doi: 10.53560/ppasa(61-3)848
Philemon Uten Emmoh, C. I. Eke, and T. Moses, “A feature selection and scoring scheme for dimensionality reduction in a machine learning task,” Journal of the Nigerian Society of Physical Sciences, vol. 7, no. 1, pp. 2273–2273, Dec. 2024. doi: 10.46481/jnsps.2025.2273
J. Bohrer, and M. Dorn, “Enhancing classification with hybrid feature selection: A multi-objective genetic algorithm for high-dimensional data,” Expert Syst. Appl., vol. 255, p. 124518, Jun. 2024. doi: 10.1016/j.eswa.2024.124518
X. Gong, J. Wang, Q. Ren, K. Zhang, E.-S. M. El-Alfy, and J. Mańdziuk, “Embedded feature selection approach based on TSK fuzzy system with sparse rule base for high-dimensional classification problems,” Knowledge-Based Systems, vol. 295, p. 111809, Jul. 2024. doi: 10.1016/j.knosys.2024.111809
B. Guelib, N. Khlifa, and R. Bounab, “Embedded gene expression data based on ridgeclassifier for alzheimer’s disease classification,” 2023 International Conference on Innovations in Intelligent Systems and Applications (INISTA), pp. 1–6, Sep. 2023. doi: 10.1109/inista59065.2023.10310317
J. H. Holland, “Genetic Algorithms,” Scientific American, vol. 267, no. 1, pp. 66–72, Jul. 1992. doi: 10.1038/scientificamerican0792-66
S. K. R. Mallidi, and R. R. Ramisetty, “Embedded-filter ACO using clustering based mutual information for feature selection,” Journal of Combinatorial Optimization, vol. 49, art. no. 27, Feb. 2025. doi: 10.1007/s10878-025-01259-6
A. K. Naik, and Venkatanareshbabu Kuppili, “An embedded feature selection method based on generalized classifier neural network for cancer classification,” Computers in Biology and Medicine, vol. 168, pp. 107677–107677, Jan. 2024. doi: 10.1016/j.compbiomed.2023.107677
K. Nemati, A. H. R. Sheikhani, S. Kordrostami, and K. K. Roudposhti, “The embedded feature selection method based on artificial neural network using gray wolf optimizer and structured sparsity norms,” Research Square, Sep. 2023. doi: 10.21203/rs.3.rs-3360806/v1
X. Shu, “Embedded Feature Selection Method Based on Neural Networks—Research on Simulation Application of European Football Data,” 2024 2nd International Conference on Mechatronics, IoT and Industrial Informatics (ICMIII), pp. 758–763, Jun. 2024. doi: 10.1109/icmiii62623.2024.00147
Y. Syahidin, N. U. Maulidevi, and K. Surendro, “Feature selection method based on genetic algorithm with wrapper-embedded technique for medical record classification,” Proceedings of the 2023 12th International Conference on Software and Computer Applications, pp. 184–191, Feb. 2023. doi: 10.1145/3587828.3587856
D. J. Zhou, R. Chahal, I. H. Gotlib, and S. Liu, “Comparison of lasso and stepwise regression in psychological data,” Methodology, vol. 20, no. 2, pp. 121–143, Jun. 2024. doi: 10.5964/meth.11523
M. Zeng, H. Mo, Z. Liang, and H. Wang, “A Lite Fireworks Algorithm with Fractal Dimension Constraint for Feature Selection,” arXiv.org, 2023. [Online]. Available: https://arxiv.org/abs/2303.05516 . [Accessed: Feb. 17, 2026].
S. Kumar, “Covid19-Pneumonia-Normal Chest X-Ray Images,” Mendeley Data, vol. 1, Jun. 2022. doi: 10.17632/dvntn9yhd2.1
L. Fischer, and P. Wollstadt, “Precision and Recall Reject Curves for Classification,” arXiv.org, 2023. [Online]. Available: https://arxiv.org/abs/2308.08381 . [Accessed: Sep. 08, 2024].
Vishnu Sharma, and Dr. Gaurav Khandelwal, “Ant colony optimization: A technique used for image processing,” International Journal of Information Technology and Management, vol. 18, no. 2, pp. 84–89, Sep. 2023. doi: 10.29070/ftfw8q07
T. M. Franke, T. Ho, and C. A. Christie, “The chi-square test: Often used and more often misinterpreted,” American Journal of Evaluation, vol. 33, no. 3, pp. 448–458, Nov. 2011. doi: 10.1177/1098214011426594
S. S. Md Noh, N. Ibrahim, M. M. Mansor, N. A. Md Ghani, and M. Yusoff, “Hybrid embedded and filter feature selection methods in big-dimension mammary cancer and prostatic cancer data,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 13, no. 3, p. 3101, Sep. 2024. doi: 10.11591/ijai.v13.i3.pp3101-3110
Y. Li, F. Lu, and Y. Yin, “Applying logistic LASSO regression for the diagnosis of atypical Crohn’s disease,” Scientific Reports, vol. 12, no. 1, Jul. 2022. doi: 10.1038/s41598-022-15609-5
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.

Details

Primary Language

English

Subjects

Artificial Intelligence (Other)

Journal Section

Research Article

Authors

Sheikh Afaan Farooq ^*
0009-0002-4478-2705
India

Aleem Ali
0000-0001-5298-4775
India

Early Pub Date

March 15, 2026

Publication Date

March 15, 2026

Submission Date

August 17, 2025

Acceptance Date

November 7, 2025

Published in Issue

Year 2026 Volume: 9 Number: 1

DOI

https://doi.org/10.35377/saucis...1766963

IZ

https://izlik.org/JA64ES66MZ

Cite

RIS / Bibtex

APA

Farooq, S. A., & Ali, A. (2026). Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models. Sakarya University Journal of Computer and Information Sciences, 9(1), 90-104. https://doi.org/10.35377/saucis...1766963

AMA

1.Farooq SA, Ali A. Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models. SAUCIS. 2026;9(1):90-104. doi:10.35377/saucis.1766963

Chicago

Farooq, Sheikh Afaan, and Aleem Ali. 2026. “Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models”. Sakarya University Journal of Computer and Information Sciences 9 (1): 90-104. https://doi.org/10.35377/saucis. 1766963.

EndNote

Farooq SA, Ali A (March 1, 2026) Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models. Sakarya University Journal of Computer and Information Sciences 9 1 90–104.

IEEE

[1]S. A. Farooq and A. Ali, “Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models”, SAUCIS, vol. 9, no. 1, pp. 90–104, Mar. 2026, doi: 10.35377/saucis...1766963.

ISNAD

Farooq, Sheikh Afaan - Ali, Aleem. “Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models”. Sakarya University Journal of Computer and Information Sciences 9/1 (March 1, 2026): 90-104. https://doi.org/10.35377/saucis. 1766963.

JAMA

1.Farooq SA, Ali A. Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models. SAUCIS. 2026;9:90–104.

MLA

Farooq, Sheikh Afaan, and Aleem Ali. “Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 1, Mar. 2026, pp. 90-104, doi:10.35377/saucis. 1766963.

Vancouver

1.Sheikh Afaan Farooq, Aleem Ali. Optimizing Medical Image Diagnosis: The Role of Feature Selection in Deep Learning Models. SAUCIS. 2026 Mar. 1;9(1):90-104. doi:10.35377/saucis. 1766963