This review presents and discusses the contribution of machine learning techniques for diagnosis and disease monitoring in the context of clinical vision science. Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients' management are now available. Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process. This manuscript presents a review in multimodal ocular disease diagnosis and monitoring based on machine learning approaches. In the first section, the technical issues related to the different machine learning approaches will be present. Machine learning techniques are used to automatically recognize complex patterns in a given dataset. These techniques allows creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case. To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized. For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted. The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript. To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration, and diabetic retinopathy, these ocular pathologies being the major causes of irreversible visual impairment.

This study aims to analyze the protein aggregates spatial distribution for different cataract degrees, and correlate this information with the lens acoustical parameters and by this way, assess the cataract regional hardness. Different cataract degrees were induced ex vivo in porcine lenses. A 25 MHz ultrasonic transducer was used to obtain the acoustical parameters (velocity, attenuation, and backscattering signals). B-scan and Nakagami images were constructed. Also, lenses with different cataract degrees were sliced in two regions (nucleus and cortex), for fibers and collagen detection. A significant increase with cataract formation was found for the velocity, attenuation, and brightness intensity of the B-scan images and Nakagami m parameter ( ). The acoustical parameters showed a good to moderate correlation with the m parameter for the different stages of cataract formation. A strong correlation was found between the protein aggregates in the cortex and the m parameter. Lenses without cataract are characterized using a classification and regression tree, by a mean brightness intensity ≤0.351, a variance of the B-scan brightness intensity ≤0.070, a velocity ≤1625 m/s, and an attenuation ≤0.415 dB/mm·MHz (sensitivity: 100% and specificity: 72.6%). To characterize different cataract degrees, the m parameter should be considered. Initial stages of cataract are characterized by a mean brightness intensity >0.351 and a variance of the m parameter >0.110. Advanced stages of cataract are characterized by a mean brightness intensity >0.351, a variance of the m parameter ≤0.110, and a mean m parameter >0.374. For initial and advanced stages of cataract, a sensitivity of 78.4% and a specificity of 86.5% are obtained.

Based on this work, a medical prototype will be developed for early cataract detection, classification, and hardness estimation.

No abstract

No abstract