Early Diagnosis of Multiple Sclerosis Using Swept-Source Optical Coherence Tomography and Convolutional Neural Networks Trained with Data Augmentation.

BACKGROUND: The aim of this paper is to implement a system to facilitate the diagnosis of multiple sclerosis (MS) in its initial stages. It does so using a convolutional neural network (CNN) to classify images captured with swept-source optical coherence tomography (SS-OCT). METHODS: SS-OCT images from 48 control subjects and 48 recently diagnosed MS patients have been used. These images show the thicknesses (45 × 60 points) of the following structures: complete retina, retinal nerve fiber layer, two ganglion cell layers (GCL+, GCL++) and choroid. The Cohen distance is used to identify the structures and the regions within them with greatest discriminant capacity. The original database of OCT images is augmented by a deep convolutional generative adversarial network to expand the CNN's training set. RESULTS: The retinal structures with greatest discriminant capacity are the GCL++ (44.99% of image points), complete retina (26.71%) and GCL+ (22.93%). Thresholding these images and using them as inputs to a CNN comprising two convolution modules and one classification module obtains sensitivity = specificity = 1.0. CONCLUSIONS: Feature pre-selection and the use of a convolutional neural network may be a promising, nonharmful, low-cost, easy-to-perform and effective means of assisting the early diagnosis of MS based on SS-OCT thickness data.

Multifocal ERG wavelet packet decomposition applied to glaucoma diagnosis.

BACKGROUND: Glaucoma is the second-leading cause of blindness worldwide and early diagnosis is essential to its treatment. Current clinical methods based on multifocal electroretinography (mfERG) essentially involve measurement of amplitudes and latencies and assume standard signal morphology. This paper presents a new method based on wavelet packet analysis of global-flash multifocal electroretinogram signals. METHODS: This study comprised twenty-five patients diagnosed with OAG and twenty-five control subjects. Their mfERG recordings data were used to develop the algorithm method based on wavelet packet analysis. By reconstructing the third wavelet packet contained in the fourth decomposition level (ADAA4) of the mfERG recording, it is possible to obtain a signal from which to extract a marker in the 60-80 ms time interval. RESULTS: The marker found comprises oscillatory potentials with a negative-slope basal line in the case of glaucomatous recordings and a positive-slope basal line in the case of normal signals. Application of the optimal threshold calculated in the validation cases showed that the technique proposed achieved a sensitivity of 0.81 and validation specificity of 0.73. CONCLUSIONS: This new method based on mfERG analysis may be reliable enough to detect functional deficits that are not apparent using current automated perimetry tests. As new stimulation and analysis protocols develop, mfERG has the potential to become a useful tool in early detection of glaucoma-related functional deficits.