Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/978-3-642-81246-0_5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells.
Int J Med Inform
January 2025
Department of Computer Science and Artificial Intelligence, University of Udine, 33100, Italy.
Background: Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data.
Methods: In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images.
Automated mold defects classification in paintings: A comparison of machine learning and rule-based techniques.
PLoS One
January 2025
Faculty of Science and Engineering, School of Computer Science, University of Hull, Hull, United Kingdom.
Mold defects pose a significant risk to the preservation of valuable fine art paintings, typically arising from fungal growth in humid environments. This paper presents a novel approach for detecting and categorizing mold defects in fine art paintings. The technique leverages a feature extraction method called Derivative Level Thresholding to pinpoint suspicious regions within an image.
View Article and Find Full Text PDFNew Henneguya Species Cause Gill Disease of Commercial Amazonian Fish.
Acta Parasitol
January 2025
Laboratory of Morpho-Molecular Integration and Technologies (LIMT), Federal Rural University of the Amazon (UFRA), Belém, Pará, Brazil.
Background: Freshwater fish are affected with much parasitic diseases, among the most common are Henneguyosis caused by myxozoans of the genus Henneguya, which exhibit great diversity in fish from South America, particularly in the Brazilian Amazon.
Purpose: In this present study, we describe the morphological and phylogenetic aspects of the small ribosomal subunit (SSU rDNA) of two new species of Henneguya infecting the gills from Hypophthalmus marginatus, a freshwater catfish from the Amazon.
Methods: In 148 specimens, has been observed cyst formation in different regions of the gills, intrafilamentary and intralamellar.
Hennegoides Africanus sp. nov. from Kadey River in Cameroon.
Acta Parasitol
January 2025
Laboratory of Parasitology and Ecology, Department of Animal Biology and Physiology, Faculty of Sciences, University of Yaoundé I, P.O. Box 812, Yaoundé, Cameroon.
Purpose: Fish are susceptible to various parasitic infections, with Myxozoa emerging as a major group. A taxonomic study of Myxozoa is essential for the rapid diagnosis of species potentially responsible for epizootic diseases.
Methods: The studied fish was collected from the Kadey River, a tributary of the Sangha River in the Congo Basin in Cameroon, and parasitologically dissected.
Unveiling Paramyrothecium kamalii (Stachybotryaceae) as a novel foliar fungal pathogen on Matourea azurea in Kerala, India, based on morpho-cultural, pathological and molecular phylogenetic evidences.
Arch Microbiol
January 2025
Andaman and Nicobar Regional Centre, Botanical Survey of India, Haddo, Port Blair, 744102, India.
During recent survey for the investigation of foliar fungi in Kerala, India, a new species of foliicolous hyphomycete, Paramyrothecium kamalii was discovered on living leaves of Matourea azurea (Plantaginaceae) based on morpho-cultural characteristics and multigene (ITS, LSU, cmdA, tub2, and rpb2) phylogenetic analysis; is described, illustrated and discussed. In vitro Pathogenicity tests were performed and confirmed the pathogenic nature of the fungus, thereby fulfilling Koch's postulates. Phylogenetically, P.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!