A New Approach for Detecting Fundus Lesions Using Image Processing and Deep Neural Network Architecture Based on YOLO Model.

Diabetic Retinopathy is one of the main causes of vision loss, and in its initial stages, it presents with fundus lesions, such as microaneurysms, hard exudates, hemorrhages, and soft exudates. Computational models capable of detecting these lesions can help in the early diagnosis of the disease and prevent the manifestation of more severe forms of lesions, helping in screening and defining the best form of treatment. However, the detection of these lesions through computerized systems is a challenge due to numerous factors, such as the characteristics of size and shape of the lesions, noise and the contrast of images available in the public datasets of Diabetic Retinopathy, the number of labeled examples of these lesions available in the datasets and the difficulty of deep learning algorithms in detecting very small objects in digital images. Thus, to overcome these problems, this work proposes a new approach based on image processing techniques, data augmentation, transfer learning, and deep neural networks to assist in the medical diagnosis of fundus lesions. The proposed approach was trained, adjusted, and tested using the public DDR and IDRiD Diabetic Retinopathy datasets and implemented in the PyTorch framework based on the YOLOv5 model. The proposed approach reached in the DDR dataset an mAP of 0.2630 for the IoU limit of 0.5 and F1-score of 0.3485 in the validation stage, and an mAP of 0.1540 for the IoU limit of 0.5 and F1-score of 0.2521, in the test stage. The results obtained in the experiments demonstrate that the proposed approach presented superior results to works with the same purpose found in the literature.

Dominance of Scorpaena maderensis among scorpaenids of littoral rocky reefs in Corsica (NW Mediterranean): Further evidence of Mediterranean Sea warming.

The population of Scorpaenidae was investigated in the Nature Reserve of Scàndula (Corsica, France, NW Mediterranean). While absent from Corsica a few decades ago, the Madeira rockfish Scorpaena maderensis is now the most abundant scorpaenid species in shallow rocky reef areas, far outnumbering Scorpaena notata and Scorpaena porcus. Considered as a subtropical species of Atlantic origin, the northward progression of the thermophilic S. maderensis and its dominance in Corsican waters is further evidence of the ongoing warming of the Mediterranean Sea.

Detection of Fundus Lesions through a Convolutional Neural Network in Patients with Diabetic Retinopathy.

Diabetic Retinopathy is a major cause of vision loss caused by retina lesions, including hard and soft exudates, microaneurysms, and hemorrhages. The development of a computational tool capable of detecting these lesions can assist in the early diagnosis of the most severe forms of the lesions and assist in the screening process and definition of the best treatment form. This paper proposes a computational model based on pre-trained convolutional neural networks capable of detecting fundus lesions to promote medical diagnosis support. The model was trained, adjusted, and evaluated using the DDR Diabetic Retinopathy dataset and implemented based on a YOLOv4 architecture and Darknet framework, reaching an mAP of 11.13% and a mIoU of 13.98%. The experimental results show that the proposed model presented results superior to those obtained in related works found in the literature.

In situ observations and modelling revealed environmental factors favouring occurrence of Vibrio in microbiome of the pelagic Sargassum responsible for strandings.

Historically, pelagic Sargassum were only found in the Sargasso Sea. Since 2011, blooms were regularly observed in warmer water, further south. Their developments in Central Atlantic are associated with mass strandings on the coasts, causing important damages and potentially dispersion of new bacteria. Microbiomes associated with pelagic Sargassum were analysed at large scale in Central Atlantic and near Caribbean Islands with a focus on pathogenic bacteria. Vibrio appeared widely distributed among pelagic Sargassum microbiome of our samples with higher occurrence than previously found in Mexico Gulf. Six out the 16 Vibrio-OTUs (Operational Taxonomic Unit), representing 81.2 ± 13.1% of the sequences, felt in cluster containing pathogens. Among the four different microbial profiles of pelagic Sargassum microbiome, Vibrio attained about 2% in two profiles whereas it peaked, in the two others, at 6.5 and 26.8% respectively, largely above the concentrations found in seawater surrounding raft (0.5%). In addition to sampling and measurements, we performed backward Lagrangian modelling of trajectories of rafts, and rebuilt the sampled rafts environmental history allowing us to estimate Sargassum growth rates along raft displacements. We found that Vibrio was favoured by high Sargassum growth rate and in situ ammonium and nitrite, modelled phosphate and nitrate concentrations, whereas zooplankters, benthic copepods, and calm wind (proxy of raft buoyancy near the sea surface) were less favourable for them. Relations between Vibrio and other main bacterial groups identified a competition with Alteromonas. According to forward Lagrangian tracking, part of rafts containing Vibrio could strand on the Caribbean coasts, however the strong decreases of modelled Sargassum growth rates along this displacement suggest unfavourable environment for Vibrio. For the conditions and areas observed, the sanitary risk seemed in consequence minor, but in other areas or conditions where high Sargassum growth rate occurred near coasts, it could be more important.