Deep learning models need a lot of labeled data to work well.In this study, we use a Self-Supervised Learning Tracks (SSL) method for semantic segmentation of archaeological monuments in Digital Terrain Models (DTMs).This method first uses unlabeled data to pretrain a model (pretext task), and then fine-tunes it with a small labeled dataset (downst
<p><strong>Background and aims.</strong> Recent literature shows that accelerated Portland cement (APC) is a non-toxic material that may have potential to promote bone healing.The objective of this study was to histologically evaluate periodontal healing focusing on new bone regeneration following implantation of APC into intra-bo
A new method for automatic optic disc localization and segmentation is presented.The localization procedure combines vascular and brightness information Pulse Spacer to provide the best estimate of the optic disc center which is the starting point for the segmentation algorithm.A detection rate of 99.58% and 100% was achieved for the Messidor and O
Haematological analyses can reveal the physiological condition of birds, which are known to efficiently disguise symptoms of stress and disease.However, the interpretation of such analyses requires species-specific baseline data, which are lacking for most free-living seabird species.We provide baseline reference data for several haematological par