Search academic texts

Information × Registration Number 0124U004388, R & D request Title Implementing flexible, robust and automated Nextflow-based pipeline for unsupervised and semi-/supervised image segmentation using highly parallel fastLBP tool Head Frolova Alina O., Registration Date 14-10-2024 Organization Institute of Molecular Biology and Genetics of NAS of Ukraine popup.description1 This project is a continuation of the previous research - "Highly parallel implementation of Local Binary Pattern algorithm for high-throughput analysis imaging pipeline in spatial transcriptomics (fastLBP)". We plan to expand the possibilities of highly parallel implementation of LBP algorithm, a visual descriptor used for classification in computer vision. LBP will be applied to characterize tissue architecture of glioblastoma (GBM) brain tumors from large collections of tumor H&E images in combination with methods of spatial transcriptomics. We will implement the advanced tools and platforms, including automating the pathology work (manual annotation); create tissue and morphology independent tool with minimum parameters, which can influence image classification in unsupervised and supervised manner; perform integration of different services and tools into a single high-throughput analysis imaging pipeline. popup.nrat_date 2024-12-09 Close