Research Article
Segmented Retinal Fundus Image Classification Approach with Multiple Instance Learning
Mahbub Hasan*
Issue:
Volume 10, Issue 4, August 2025
Pages:
60-69
Received:
1 August 2025
Accepted:
18 August 2025
Published:
25 September 2025
DOI:
10.11648/j.mcs.20251004.11
Downloads:
Views:
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.
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 minimi...
Show More
Research Article
Maximum Likelihood Estimation for Uncertain Moving Average Model Under Imprecise Observations
Xiaosheng Wang,
Ben He*
Issue:
Volume 10, Issue 4, August 2025
Pages:
70-82
Received:
1 September 2025
Accepted:
15 September 2025
Published:
25 September 2025
DOI:
10.11648/j.mcs.20251004.12
Downloads:
Views:
Abstract: Time series analysis serves as a practical way to investigate data that changes over time, and has great potential for development in fields such as weather prediction and financial engineering. However, due to the imperfections in technology, it is not always possible to obtain precise observational data. Therefore, modeling with uncertain time series is more suitable. Choosing appropriate parameter estimation methods is a critical aspect of the modeling process for uncertain time series. This paper proposes using maximum likelihood estimation for the parameter estimation of the first-order uncertain moving average (UMA) model, and for predicting future values and calculating the confidence intervals. Subsequently, the effectiveness of this method is demonstrated through numerical examples. Firstly, we employ an iterative method to convert the first-order UMA model into an uncertain autoregressive (UAR) model. Secondly, the maximum likelihood method is used to estimate the unknown parameters of the UMA model. Additionally, for this model where the observations are linear uncertain variables, a specific maximum likelihood estimation approach is provided. Thirdly, following the estimation values obtained, future data predictions and confidence intervals are calculated. Furthermore, when the observations are linear uncertain variables, corresponding confidence intervals are also provided. Finally, two practical cases are presented to demonstrate the practicality of the method. Moreover, contrasted with the least squares method, the results indicate that this method can enhance the accuracy of predictions.
Abstract: Time series analysis serves as a practical way to investigate data that changes over time, and has great potential for development in fields such as weather prediction and financial engineering. However, due to the imperfections in technology, it is not always possible to obtain precise observational data. Therefore, modeling with uncertain time se...
Show More
