Computer Department, Applied College, Najran University, Najran, Saudi Arabia.
Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, Alrazi University, Sana'a, Yemen.
PLoS One. 2023 Oct 20;18(10):e0289555. doi: 10.1371/journal.pone.0289555. eCollection 2023.
The number of diabetic retinopathy (DR) patients is increasing every year, and this causes a public health problem. Therefore, regular diagnosis of diabetes patients is necessary to avoid the progression of DR stages to advanced stages that lead to blindness. Manual diagnosis requires effort and expertise and is prone to errors and differing expert diagnoses. Therefore, artificial intelligence techniques help doctors make a proper diagnosis and resolve different opinions. This study developed three approaches, each with two systems, for early diagnosis of DR disease progression. All colour fundus images have been subjected to image enhancement and increasing contrast ROI through filters. All features extracted by the DenseNet-121 and AlexNet (Dense-121 and Alex) were fed to the Principal Component Analysis (PCA) method to select important features and reduce their dimensions. The first approach is to DR image analysis for early prediction of DR disease progression by Artificial Neural Network (ANN) with selected, low-dimensional features of Dense-121 and Alex models. The second approach is to DR image analysis for early prediction of DR disease progression is by integrating important and low-dimensional features of Dense-121 and Alex models before and after PCA. The third approach is to DR image analysis for early prediction of DR disease progression by ANN with the radiomic features. The radiomic features are a combination of the features of the CNN models (Dense-121 and Alex) separately with the handcrafted features extracted by Discrete Wavelet Transform (DWT), Local Binary Pattern (LBP), Fuzzy colour histogram (FCH), and Gray Level Co-occurrence Matrix (GLCM) methods. With the radiomic features of the Alex model and the handcrafted features, ANN reached a sensitivity of 97.92%, an AUC of 99.56%, an accuracy of 99.1%, a specificity of 99.4% and a precision of 99.06%.
糖尿病视网膜病变（DR）患者的数量每年都在增加，这构成了一个公共卫生问题。因此，定期对糖尿病患者进行诊断是必要的，以避免 DR 阶段进展到导致失明的晚期阶段。手动诊断需要付出努力和专业知识，并且容易出现错误和不同专家的诊断意见。因此，人工智能技术有助于医生做出正确的诊断并解决不同的意见。本研究开发了三种方法，每种方法都有两个系统，用于早期诊断 DR 疾病的进展。所有彩色眼底图像都经过图像增强和通过滤波器增加 ROI 对比度。通过 DenseNet-121 和 AlexNet（Dense-121 和 Alex）提取的所有特征都被输入到主成分分析（PCA）方法中，以选择重要特征并降低其维度。第一种方法是通过选择 Dense-121 和 Alex 模型的低维特征，使用人工神经网络（ANN）对 DR 图像进行分析，以早期预测 DR 疾病的进展。第二种方法是通过在 PCA 之前和之后整合 Dense-121 和 Alex 模型的重要和低维特征，对 DR 图像进行分析，以早期预测 DR 疾病的进展。第三种方法是通过使用放射组学特征的 ANN 对 DR 图像进行分析，以早期预测 DR 疾病的进展。放射组学特征是 CNN 模型（Dense-121 和 Alex）的特征与由离散小波变换（DWT）、局部二值模式（LBP）、模糊颜色直方图（FCH）和灰度共生矩阵（GLCM）方法提取的手工特征的组合。使用 Alex 模型的放射组学特征和手工特征，ANN 达到了 97.92%的灵敏度、99.56%的 AUC、99.1%的准确率、99.4%的特异性和 99.06%的精确率。
