Scholarlink

<p>The analysis of fundus images is critical for the early detection and diagnosis of retinal diseases such as diabetic retinopathy (DR), glaucoma, and age-related macular degeneration (AMD). Traditional diagnostic workflows, however, often depend on manual interpretation and are both time- and resource-intensive. To address these limitations, we propose an automated and interpretable clinical decision support framework based on a hybrid feature extraction model called <i>HOG-CNN</i>. Our key contribution lies in effectively integrating handcrafted Histogram of Oriented Gradients (HOG) features with representations learned by the pretrained deep convolutional neural network EfficientNetB3. This fusion enables our model to capture both local texture patterns and high-level semantic features from retinal fundus images. We evaluated our model on three public benchmark datasets: APTOS 2019 (for binary and multiclass DR classification), ORIGA (for Glaucoma detection), and IC-AMD (for AMD diagnosis); HOG-CNN demonstrates consistently high performance. It achieves <b>98.5% accuracy and 99.2 AUC</b> for binary DR classification, and <b>94.2 AUC</b> for five-class DR classification. On the IC-AMD dataset, it attains <b>92.8% accuracy, 94.8% precision and 94.5 AUC</b>, outperforming several state-of-the-art models. For Glaucoma detection on ORIGA, our model achieves <b>83.9% accuracy and 87.2 AUC</b>, showing competitive performance despite dataset limitations. We show, through comprehensive appendix studies, the complementary strength of combining HOG and CNN backbone (EfficientNetB3) features. The model’s lightweight and interpretable design makes it particularly suitable for deployment in resource-constrained clinical environments. These results position HOG-CNN as a robust and scalable tool for automated retinal disease screening.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

HOG-CNN: Integrating Histogram of Oriented Gradients with Convolutional Neural Networks for Retinal Image Classification

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Faisal Ahmed

摘要

The analysis of fundus images is critical for the early detection and diagnosis of retinal diseases such as diabetic retinopathy (DR), glaucoma, and age-related macular degeneration (AMD). Traditional diagnostic workflows, however, often depend on manual interpretation and are both time- and resource-intensive. To address these limitations, we propose an automated and interpretable clinical decision support framework based on a hybrid feature extraction model called HOG-CNN. Our key contribution lies in effectively integrating handcrafted Histogram of Oriented Gradients (HOG) features with representations learned by the pretrained deep convolutional neural network EfficientNetB3. This fusion enables our model to capture both local texture patterns and high-level semantic features from retinal fundus images. We evaluated our model on three public benchmark datasets: APTOS 2019 (for binary and multiclass DR classification), ORIGA (for Glaucoma detection), and IC-AMD (for AMD diagnosis); HOG-CNN demonstrates consistently high performance. It achieves 98.5% accuracy and 99.2 AUC for binary DR classification, and 94.2 AUC for five-class DR classification. On the IC-AMD dataset, it attains 92.8% accuracy, 94.8% precision and 94.5 AUC, outperforming several state-of-the-art models. For Glaucoma detection on ORIGA, our model achieves 83.9% accuracy and 87.2 AUC, showing competitive performance despite dataset limitations. We show, through comprehensive appendix studies, the complementary strength of combining HOG and CNN backbone (EfficientNetB3) features. The model’s lightweight and interpretable design makes it particularly suitable for deployment in resource-constrained clinical environments. These results position HOG-CNN as a robust and scalable tool for automated retinal disease screening.