Diabetic retinopathy prediction based on vision transformer and modified capsule network.

Diabetic retinopathy is considered one of the most common diseases that can lead to blindness in the working age, and the chance of developing it increases as long as a person suffers from diabetes. Protecting the sight of the patient or decelerating the evolution of this disease depends on its early detection as well as identifying the exact levels of this pathology, which is done manually by ophthalmologists. This manual process is very consuming in terms of the time and experience of an expert ophthalmologist, which makes developing an automated method to aid in the diagnosis of diabetic retinopathy an essential and urgent need. In this paper, we aim to propose a new hybrid deep learning method based on a fine-tuning vision transformer and a modified capsule network for automatic diabetic retinopathy severity level prediction. The proposed approach consists of a new range of computer vision operations, including the power law transformation technique and the contrast-limiting adaptive histogram equalization technique in the preprocessing step. While the classification step builds up on a fine-tuning vision transformer, a modified capsule network, and a classification model combined with a classification model, The effectiveness of our approach was evaluated using four datasets, including the APTOS, Messidor-2, DDR, and EyePACS datasets, for the task of severity levels of diabetic retinopathy. We have attained excellent test accuracy scores on the four datasets, respectively: 88.18%, 87.78%, 80.36%, and 78.64%. Comparing our results with the state-of-the-art, we reached a better performance.

Diabetic Retinopathy Prediction Based on Wavelet Decomposition and Modified Capsule Network.

Diabetic retinopathy (DR) is one of the most common consequences of diabetes. It affects the retina, causing blood vessel damage which can lead to loss of vision. Saving patients from losing their sight or at least slowing the progress of this disease depends mainly on the early detection of this pathology, on top of the detection of its specific stage. Furthermore, the early detection of diabetic retinopathy and the follow-up of the patient's condition remains an arduous task, whether for an experienced expert ophthalmologist or a computer-aided diagnosis technician. In this paper, we aim to propose a new automatic diabetic retinopathy severity level detection method. The proposed approach merges the pyramid hierarchy of the discrete wavelet transform of the retina fundus image with the modified capsule network and the modified inception block proposed, in addition to a new deep hybrid model that concatenates the inception block with capsule networks. The performance of our proposed approach has been validated on the APTOS dataset, as it achieved a high training accuracy of 97.71% and a high testing accuracy score of 86.54%, which is considered one of the best scores achieved in this field using the same dataset.

[Chronic corneal ulcer revealing Parry-Romberg's syndrome: a case report]. / Ulcère de cornée chronique révélant un syndrome de Parry-Romberg: à propos d´un cas.

Parry-Romberg´s syndrome is a rare clinical entity characterized by progressive hemifacial atrophy associated with several systemic manifestations including ophthalmologic, neurologic, maxillofacial symptoms whose treatment should be multidisciplinary. We here report a case of Parry-Romberg´s syndrome diagnosed in a patient referred for management of chronic corneal ulcer following hypoesthesia, characterized by rare and difficult-to-treat features.

[Trichotillomania involving the eyelashes: about a case]. / La trichotillomanie des cils: à propos d'un cas.

Trichotillomania is a neglected psychiatric disorder characterized by the urge to pull out the hair, the eyebrows or any other hair, but rarely the eyelashes. In the Diagnostic and Statistical Manual of Mental Disorders it is defined as habits and pulses disturbance. We here report the case of a girl with trichotillomania involving her left eyelashes due to low self-esteem. The disease may be episodic but it is usually chronic and difficult to treat. Given the possible clinical and psychiatric complications, early and accurate diagnosis is essential. Cognitive-behavioral therapy is the gold standard treatment.

[Ophthalmologic manifestations of Behçet's disease, about 33 cases]. / Les manifestations ophtalmologiques de la maladie de Behçet, à propos de 33 cas.

Les manifestations ophtalmologiques au cours de la maladie de Behçet sont dominées par les uvéites, les vascularites rétiniennes et les thromboses veineuses rétiniennes. Nous rapportons une étude rétrospective portant sur tous les malades atteints de la maladie de Behçet, hospitalisés au sein du service d'Ophtalmologie de Fès de Janvier 2007 à Décembre 2009. Au total ce sont 33 patients qui sont inclut dans l'étudeLa moyenne d'âge est de 28,4 ans. Le délai moyen de consultation varie entre 1 jour et 3 ans. L'atteinte oculaire est bilatérale chez 26 patients (78,8% des yeux). L'AV est très basse avant le traitement: 28,8% à moins de 1/10. Les manifestations oculaires sont dominées par l'uvéite avec 77,3%, suivie de la vascularite rétinienne 54, 5% et la maculopathie 51, 5%. Le pourcentage des yeux dont l'AV était inférieur à 1/10 est passé à 19,7% après traitement. La fréquence de l'atteinte oculaire au cours de la maladie de Behçet est diversement appréciée selon les auteurs et selon le mode de recrutement des patients: elle va de 29% à 100%. L'atteinte uvéale est la plus fréquente des manifestations ophtalmologiques. Les lésions vasculaires rétiniennes sont dominées par la vascularite rétinienne essentiellement la périphlébite aussi bien au pôle postérieur qu'à la périphérie rétinienne. En l'absence de traitement et de mauvaise observance, le pronostic oculaire de la maladie de Behçet est très mauvais. La cécité s'installe dans 13 à 32%. Les manifestations ophtalmologiques au cours de la maladie de Behçet ont une valeur considérable, tant sur le plan diagnostique que pronostique. Notre étude a permis de décrire les aspects cliniques de l'atteinte oculaire de la maladie de Behçet dans un service d'Ophtalmologie tertiaire au Maroc.