Purpose: To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON). Patients and Methods: Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina’s tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity. Results: Determination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%). Conclusion: Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.
Haze is a source of unreliability for computer vision applications in outdoor scenarios, and it is usually caused by atmospheric conditions. The Dark Channel Prior (DCP) has shown remarkable results in image defogging with three main limitations: 1) high time-consumption, 2) artifact generation, and 3) sky-region over-saturation. Therefore, current work has focused on improving processing time without losing restoration quality and avoiding image artifacts during image defogging. Hence in this research, a novel methodology based on depth approximations through DCP, local Shannon entropy, and Fast Guided Filter is proposed for reducing artifacts and improving image recovery on sky regions with low computation time. The proposed-method performance is assessed using more than 500 images from three datasets: Hybrid Subjective Testing Set from Realistic Single Image Dehazing (HSTS-RESIDE), the Synthetic Objective Testing Set from RESIDE (SOTS-RESIDE) and the HazeRD. Experimental results demonstrate that the proposed approach has an outstanding performance over state-of-the-art methods in reviewed literature, which is validated qualitatively and quantitatively through Peak Signal-to-Noise Ratio (PSNR), Naturalness Image Quality Evaluator (NIQE) and Structural SIMilarity (SSIM) index on retrieved images, considering different visual ranges, under distinct illumination and contrast conditions. Analyzing images with various resolutions, the method proposed in this work shows the lowest processing time under similar software and hardware conditions.
Diabetic retinopathy (DR) is the primary cause of blindness in developing and developed countries. Early-stage DR detection reduces the risk of blindness in Diabetes Mellitus (DM) patients. There has been a sharp rise in the prevalence of DM in recent years, especially in low- and middle-income countries. In this context, automated artificial intelligence-based DM screening is a crucial tool to help classify the considerable amount of Retinal Fundus Images (RFI). However, retinal image quality assessment has shown to be fundamental in real-world DR screening processes to avoid out-of-distribution data, drift, and images lacking relevant anatomical information. This work analyzes the spatial domain features and image quality assessment metrics for carrying out Deep Learning (DL) classification and detecting notable features in RFI. In addition, a novel lightweight convolutional neural network is proposed specifically for binary classification at a low computational cost. The training results are comparable to state-of-the-art neural networks, which are widely used in DL applications. The implemented architecture achieves 98.6% area under the curve, and 97.66%, and 98.33% sensitivity and specificity, respectively. Moreover, the object detection model trained achieves 94.5% mean average precision. Furthermore, the proposed approach can be integrated into any automated RFI analysis system.
At present, Convolutional Neural Networks (ConvNets) achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of mammalian visual systems such as invariance to contrast and illumination changes. Some ideas for overcoming the illumination and contrast variations must usually be tuned manually and tend to fail when tested with other types of data degradation. In this context, a new bio-inspired entry layer is presented in this work, M6, which detects low-level geometric features (lines, edges, and orientations) similar to those patterns detected by the V1 visual cortex. This new trainable layer is capable of dealing with image classification tasks even with large contrast variations. The explanation for this behavior is due to the use of monogenic signal geometry, which represents each pixel value in a 3D space using quaternions, a fact that confers a degree of explainability to the networks. The M6 was compared to conventional convolutional layer (C) and a deterministic quaternion local phase layer (Q9). The experimental setup is designed to evaluate the robustness of this M6 enriched ConvNet model and includes three architectures, four datasets, and three types of contrast degradation (including non-uniform haze degradations). The numerical results reveal that the models with M6 are the most robust in front of any kind of contrast variations. This amounts to a significant enhancement of the C models, which usually have reasonably good performance only when the same training and test degradation are used, except for the case of maximum degradation. Moreover, the Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) are used to analyze and explain the robustness effect of the M6 feature maps under any kind of contrast degradations.
This article introduces a diabetic retinopathy screening program based on artificial intelligence that will be implemented in three hospitals in Mexico. It details the steps for the clinical integration of the system and tests preliminary convolutional neural network models based on Mexican guidelines.