Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning

Mahbub Hasan

doi:doi:10.11648/j.mcs.20251004.11

Research Article |

| Peer-Reviewed

Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning

Mahbub Hasan^*

Published in Mathematics and Computer Science (Volume 10, Issue 4)

Received: 1 August 2025 Accepted: 18 August 2025 Published: 25 September 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Diabetic Retinopathy (DR) is a leading cause of vision loss, and its early detection is essential for preventing unchanging damage. This study proposes an efficient classification framework using segmented retinal fundus images from the MESSIDOR dataset, focusing on vessel-level segmentation to enhance disease-specific feature extraction and minimize extraneous background information. The pipeline includes preprocessing steps such as image resizing, green channel extraction, binary masking, and Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation of both thick and thin vessels using traditional image processing techniques. Segmented features are classified within a Multiple Instance Learning (MIL) framework, evaluating MIL with Lagrangian Relaxation (MIL-RL), Semiproximal SVM (mi-SPSVM), Kernel-based Semiproximal SVM (mi-KSPSVM), and conventional SVM (linear and RBF kernels). Performance is evaluated using Testing Correctness (TC), Sensitivity, Specificity, F1-score, and computational time under 5-fold, 10-fold, and Leave-One-Out (LOO) cross validation (CV). Results show that preprocessing significantly improves accuracy across all models, with mi-SPSVM under LOO-CV achieving the best at 68.00% in TC and a 68.32% in F1-score. At the same time, mi-KSPSVM achieved the highest sensitivity of 84.00%. The findings reveal that a segmentation-first approach in the classification task can enhance both diagnostic accuracy and computational efficiency, making it suitable for real-time and resource-limited environments. This approach offers a worthwhile, scalable solution for automated DR screening, with future work aimed at integrating deep learning- based segmentation to further improve precision.

Published in	Mathematics and Computer Science (Volume 10, Issue 4)
DOI	10.11648/j.mcs.20251004.11
Page(s)	60-69
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Machine Learning, Optimization, Multiple Instance Learning, Support Vector Machine, Image Segmentation, Retinal Fundus Image

References

[1]	Ahmad Fadzil, M. H., Izhar, L. I., Venkatachalam, P. A., & Karunakar, T. V. N. (2007). Extraction and reconstruction of retinal vasculature. Journal of Medical Engineering & Technology, 31(6), 435-442. https://doi.org/10.1080/03091900601111201
[2]	Avolio, M., Fuduli, A., Vocaturo, E. and Zumpano, E., 2023, May. On detection of diabetic retinopathy via multiple instance learning. In Proceedings of the 27th International Database Engineered Applications Symposium (pp. 170-176). https://doi.org/10.1145/3589462.3589490
[3]	M. Mateen, J. Wen, M. Hassan, N. Nasrullah, S. Sun and S. Hayat, “Automatic Detection of Diabetic Retinopathy: A Review on Datasets, Methods and Evaluation Metrics,” in IEEE Access, vol. 8, pp. 48784-48811, 2020, https://doi.org/10.1109/ACCESS.2020.2980055
[4]	Li, T., Bo, W., Hu, C., Kang, H., Liu, H., Wang, K., & Fu, H. (2021). Applications of deep learning in fundus images: A review. Medical image analysis, 69, 101971. https://doi.org/10.1016/j.media.2021.101971
[5]	Andrews, S., Tsochantaridis, I. and Hofmann, T., 2002. Support vector machines for multiple-instance learning. Advances in neural information processing systems, 15. https://doi.org/10.5555/2968618.2968690
[6]	A. Astorino, A. Fuduli, P. Veltri, and E. Vocaturo, “On a recent algorithm for multiple instance learning. Preliminary applications in image classification,” 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, USA, 2017, pp. 1615-1619, https://doi.org/10.1109/BIBM.2017.8217901
[7]	Astorino, A., Fuduli, A., Gaudioso, M. and Vocaturo, E., 2018, June. A multiple instance learning algorithm for color images classification. In Proceedings of the 22nd International Database Engineering & Applications Symposium (pp. 262-266). https://doi.org/10.1145/3216122.3216144
[8]	Avolio, M. and Fuduli, A., 2024. The semiproximal SVM approach for multiple instance learning: a kernel-based computational study. Optimization Letters, 18(2), pp. 635-649. https://doi.org/10.1007/s11590-023-02022-8
[9]	Avolio, M. and Fuduli, A., 2020. A semiproximal support vector machine approach for binary multiple instance learning. IEEE transactions on neural networks and learning systems, 32(8), pp. 3566-3577. https://doi.org/10.1109/TNNLS.2020.3015442
[10]	Astorino, A., Fuduli, A. and Gaudioso, M., 2019. A Lagrangian relaxation approach for binary multiple instance classification. IEEE transactions on neural networks and learning systems, 30(9), pp. 2662-2671. https://doi.org/10.1109/TNNLS.2018.2885852
[11]	Y. Xiao, B. Liu and Z. Hao, “Multi-Instance Nonparallel Tube Learning,” in IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 2, pp. 2563-2577, Feb. 2025, https://doi.org/10.1109/TNNLS.2023.3347449
[12]	Zumpano, E., Fuduli, A., Vocaturo, E. and Avolio, M., 2021, July. Viral pneumonia images classification by Multiple Instance Learning: preliminary results. In Proceedings of the 25th International Database Engineering & Applications Symposium (pp. 292-296). https://doi.org/10.1145/3472163.3472170
[13]	Jeong Y, Hong Y-J, Han J-H. Review of Machine Learning Applications Using Retinal Fundus Images. Diagnostics. 2022; 12(1): 134. https://doi.org/10.3390/diagnostics12010134
[14]	Khan, K. B., Khaliq, A. A., Jalil, A. et al. A review of retinal blood vessels extraction techniques: challenges, taxonomy, and future trends. Pattern Anal Applic 22, 767-802 (2019). https://doi.org/10.1007/s10044-018-0754-8
[15]	Sarki, R., Ahmed, K., Wang, H. et al. Image Preprocessing in Classification and Identification of Diabetic Eye Diseases. Data Sci. Eng. 6, 455-471 (2021). https://doi.org/10.1007/s41019-021-00167-z
[16]	Edupuganti, V. G., Chawla, A., & Kale, A. (2018). Automatic Optic Disk and Cup Segmentation of Fundus Images Using Deep Learning. 2227-2231. https://doi.org/10.1109/icip.2018.8451753
[17]	A. Khawaja, T. M. Khan, K. Naveed, S. S. Naqvi, N. U. Rehman and S. Junaid Nawaz, “An Improved Retinal Vessel Segmentation Framework Using Frangi Filter Coupled With the Probabilistic Patch Based Denoiser,” in IEEE Access, vol. 7, pp. 164344-164361, 2019, https://doi.org/10.1109/ACCESS.2019.2953259
[18]	Frangi, A. F., Niessen, W. J., Vincken, K. L., Viergever, M. A. (1998). Multiscale vessel enhancement filtering. In: Wells, W. M., Colchester, A., Delp, S. (eds) Medical Image Computing and Computer-Assisted Intervention - MICCAI’98. MICCAI 1998. Lecture Notes in Computer Science, vol 1496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0056195
[19]	Mahapatra, S., Agrawal, S., Mishro, P. K., & Pachori, R. B. (2022). A novel framework for retinal vessel segmentation using optimal improved frangi filter and adaptive weighted spatial FCM. Computers in biology and medicine, 147, 105770. https://doi.org/10.1016/j.compbiomed.2022.105770
[20]	Lara Rodr´ıguez, Luis David, & Urcid Serrano, Gonzalo. (2016). Exudates and Blood Vessel Segmentation in Eye Fundus Images Using the Fourier and Cosine Discrete Transforms. Computación y Sistemas, 20(4), 697-708. https://doi.org/10.13053/cys-20-4-2305
[21]	Kumar, Ashish & Huang, Yo-Ping. (2021). Detection of Retinal Blood Vessels with their Geometrical Physical Characteristics for Retinopathy of Prematurity (ROP).
[22]	Decencière, Etienne and Zhang, Xiwei and Cazuguel, Guy and Lay, Bruno and Cochener, Béatrice and Trone, Caroline and Gain, Philippe and Ordó˜ nez-Varela, John-Richard and Massin, Pascale and Erginay, Ali, 2014. Feedback on a publicly distributed image database: the Messidor database. Image Analysis & Stereology, pp.231-234. https://doi.org/10.5566/ias.1155
[23]	Odeh, M. Alkasassbeh and M. Alauthman, “Diabetic Retinopathy Detection using Ensemble Machine Learning,” 2021 International Conference on Information Technology (ICIT), 2021, pp. 173-178, https://doi.org/10.1109/ICIT52682.2021.9491645
[24]	Carbonneau, M. A., Cheplygina, V., Granger, E. and Gagnon, G., 2018. Multiple instance learning: A survey of problem characteristics and applications. Pattern recognition, 77, pp. 329-353. https://doi.org/10.1016/j.patcog.2017.10.009

Cite This Article

Plain Text BibTeX RIS

APA Style

Hasan, M. (2025). Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Mathematics and Computer Science, 10(4), 60-69. https://doi.org/10.11648/j.mcs.20251004.11

Copy | Download

ACS Style

Hasan, M. Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Math. Comput. Sci. 2025, 10(4), 60-69. doi: 10.11648/j.mcs.20251004.11

Copy | Download

AMA Style

Hasan M. Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Math Comput Sci. 2025;10(4):60-69. doi: 10.11648/j.mcs.20251004.11

Copy | Download

@article{10.11648/j.mcs.20251004.11,
  author = {Mahbub Hasan},
  title = {Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning
},
  journal = {Mathematics and Computer Science},
  volume = {10},
  number = {4},
  pages = {60-69},
  doi = {10.11648/j.mcs.20251004.11},
  url = {https://doi.org/10.11648/j.mcs.20251004.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mcs.20251004.11},
  abstract = {Diabetic Retinopathy (DR) is a leading cause of vision loss, and its early detection is essential for preventing unchanging damage. This study proposes an efficient classification framework using segmented retinal fundus images from the MESSIDOR dataset, focusing on vessel-level segmentation to enhance disease-specific feature extraction and minimize extraneous background information. The pipeline includes preprocessing steps such as image resizing, green channel extraction, binary masking, and Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation of both thick and thin vessels using traditional image processing techniques. Segmented features are classified within a Multiple Instance Learning (MIL) framework, evaluating MIL with Lagrangian Relaxation (MIL-RL), Semiproximal SVM (mi-SPSVM), Kernel-based Semiproximal SVM (mi-KSPSVM), and conventional SVM (linear and RBF kernels). Performance is evaluated using Testing Correctness (TC), Sensitivity, Specificity, F1-score, and computational time under 5-fold, 10-fold, and Leave-One-Out (LOO) cross validation (CV). Results show that preprocessing significantly improves accuracy across all models, with mi-SPSVM under LOO-CV achieving the best at 68.00% in TC and a 68.32% in F1-score. At the same time, mi-KSPSVM achieved the highest sensitivity of 84.00%. The findings reveal that a segmentation-first approach in the classification task can enhance both diagnostic accuracy and computational efficiency, making it suitable for real-time and resource-limited environments. This approach offers a worthwhile, scalable solution for automated DR screening, with future work aimed at integrating deep learning- based segmentation to further improve precision.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning

AU  - Mahbub Hasan
Y1  - 2025/09/25
PY  - 2025
N1  - https://doi.org/10.11648/j.mcs.20251004.11
DO  - 10.11648/j.mcs.20251004.11
T2  - Mathematics and Computer Science
JF  - Mathematics and Computer Science
JO  - Mathematics and Computer Science
SP  - 60
EP  - 69
PB  - Science Publishing Group
SN  - 2575-6028
UR  - https://doi.org/10.11648/j.mcs.20251004.11
AB  - Diabetic Retinopathy (DR) is a leading cause of vision loss, and its early detection is essential for preventing unchanging damage. This study proposes an efficient classification framework using segmented retinal fundus images from the MESSIDOR dataset, focusing on vessel-level segmentation to enhance disease-specific feature extraction and minimize extraneous background information. The pipeline includes preprocessing steps such as image resizing, green channel extraction, binary masking, and Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation of both thick and thin vessels using traditional image processing techniques. Segmented features are classified within a Multiple Instance Learning (MIL) framework, evaluating MIL with Lagrangian Relaxation (MIL-RL), Semiproximal SVM (mi-SPSVM), Kernel-based Semiproximal SVM (mi-KSPSVM), and conventional SVM (linear and RBF kernels). Performance is evaluated using Testing Correctness (TC), Sensitivity, Specificity, F1-score, and computational time under 5-fold, 10-fold, and Leave-One-Out (LOO) cross validation (CV). Results show that preprocessing significantly improves accuracy across all models, with mi-SPSVM under LOO-CV achieving the best at 68.00% in TC and a 68.32% in F1-score. At the same time, mi-KSPSVM achieved the highest sensitivity of 84.00%. The findings reveal that a segmentation-first approach in the classification task can enhance both diagnostic accuracy and computational efficiency, making it suitable for real-time and resource-limited environments. This approach offers a worthwhile, scalable solution for automated DR screening, with future work aimed at integrating deep learning- based segmentation to further improve precision.

VL  - 10
IS  - 4
ER  -

Copy | Download

Author Information

Mahbub Hasan

Department of Computer Science and Engineering, Southeast University, Dhaka, Bangladesh

Contact Email

http://orcid.org/0009-0000-7906-1823

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Hasan, M. (2025). Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Mathematics and Computer Science, 10(4), 60-69. https://doi.org/10.11648/j.mcs.20251004.11

Copy | Download

ACS Style

Hasan, M. Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Math. Comput. Sci. 2025, 10(4), 60-69. doi: 10.11648/j.mcs.20251004.11

Copy | Download

AMA Style

Hasan M. Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning. Math Comput Sci. 2025;10(4):60-69. doi: 10.11648/j.mcs.20251004.11

Copy | Download

@article{10.11648/j.mcs.20251004.11,
  author = {Mahbub Hasan},
  title = {Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning
},
  journal = {Mathematics and Computer Science},
  volume = {10},
  number = {4},
  pages = {60-69},
  doi = {10.11648/j.mcs.20251004.11},
  url = {https://doi.org/10.11648/j.mcs.20251004.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mcs.20251004.11},
  abstract = {Diabetic Retinopathy (DR) is a leading cause of vision loss, and its early detection is essential for preventing unchanging damage. This study proposes an efficient classification framework using segmented retinal fundus images from the MESSIDOR dataset, focusing on vessel-level segmentation to enhance disease-specific feature extraction and minimize extraneous background information. The pipeline includes preprocessing steps such as image resizing, green channel extraction, binary masking, and Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation of both thick and thin vessels using traditional image processing techniques. Segmented features are classified within a Multiple Instance Learning (MIL) framework, evaluating MIL with Lagrangian Relaxation (MIL-RL), Semiproximal SVM (mi-SPSVM), Kernel-based Semiproximal SVM (mi-KSPSVM), and conventional SVM (linear and RBF kernels). Performance is evaluated using Testing Correctness (TC), Sensitivity, Specificity, F1-score, and computational time under 5-fold, 10-fold, and Leave-One-Out (LOO) cross validation (CV). Results show that preprocessing significantly improves accuracy across all models, with mi-SPSVM under LOO-CV achieving the best at 68.00% in TC and a 68.32% in F1-score. At the same time, mi-KSPSVM achieved the highest sensitivity of 84.00%. The findings reveal that a segmentation-first approach in the classification task can enhance both diagnostic accuracy and computational efficiency, making it suitable for real-time and resource-limited environments. This approach offers a worthwhile, scalable solution for automated DR screening, with future work aimed at integrating deep learning- based segmentation to further improve precision.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning

AU  - Mahbub Hasan
Y1  - 2025/09/25
PY  - 2025
N1  - https://doi.org/10.11648/j.mcs.20251004.11
DO  - 10.11648/j.mcs.20251004.11
T2  - Mathematics and Computer Science
JF  - Mathematics and Computer Science
JO  - Mathematics and Computer Science
SP  - 60
EP  - 69
PB  - Science Publishing Group
SN  - 2575-6028
UR  - https://doi.org/10.11648/j.mcs.20251004.11
AB  - Diabetic Retinopathy (DR) is a leading cause of vision loss, and its early detection is essential for preventing unchanging damage. This study proposes an efficient classification framework using segmented retinal fundus images from the MESSIDOR dataset, focusing on vessel-level segmentation to enhance disease-specific feature extraction and minimize extraneous background information. The pipeline includes preprocessing steps such as image resizing, green channel extraction, binary masking, and Contrast Limited Adaptive Histogram Equalization (CLAHE), followed by segmentation of both thick and thin vessels using traditional image processing techniques. Segmented features are classified within a Multiple Instance Learning (MIL) framework, evaluating MIL with Lagrangian Relaxation (MIL-RL), Semiproximal SVM (mi-SPSVM), Kernel-based Semiproximal SVM (mi-KSPSVM), and conventional SVM (linear and RBF kernels). Performance is evaluated using Testing Correctness (TC), Sensitivity, Specificity, F1-score, and computational time under 5-fold, 10-fold, and Leave-One-Out (LOO) cross validation (CV). Results show that preprocessing significantly improves accuracy across all models, with mi-SPSVM under LOO-CV achieving the best at 68.00% in TC and a 68.32% in F1-score. At the same time, mi-KSPSVM achieved the highest sensitivity of 84.00%. The findings reveal that a segmentation-first approach in the classification task can enhance both diagnostic accuracy and computational efficiency, making it suitable for real-time and resource-limited environments. This approach offers a worthwhile, scalable solution for automated DR screening, with future work aimed at integrating deep learning- based segmentation to further improve precision.

VL  - 10
IS  - 4
ER  -

Copy | Download