06 Fakultät Luft- und Raumfahrttechnik und Geodäsie

Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/7

Browse

Filters

2023 - 20243

Settings

Institute: search.filters.UBSInstitut.Institut für Photogrammetrie und GeoinformatikStart date: 2023

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Editorial for PFG issue 5/2023
    (2023) Gerke, Markus; Cramer, Michael
  • Thumbnail Image
    ItemOpen Access
    Identification of novel biomarkers, shared molecular signatures and immune cell infiltration in heart and kidney failure by transcriptomics
    (2024) Long, Qingqing; Zhang, Xinlong; Ren, Fangyuan; Wu, Xinyu; Wang, Ze-Mu
    Introduction: Heart failure (HF) and kidney failure (KF) are closely related conditions that often coexist, posing a complex clinical challenge. Understanding the shared mechanisms between these two conditions is crucial for developing effective therapies. Methods: This study employed transcriptomic analysis to unveil molecular signatures and novel biomarkers for both HF and KF. A total of 2869 shared differentially expressed genes (DEGs) were identified in patients with HF and KF compared to healthy controls. Functional enrichment analysis was performed to explore the common mechanisms underlying these conditions. A protein-protein interaction (PPI) network was constructed, and machine learning algorithms, including Random Forest (RF), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), and Least Absolute Shrinkage and Selection Operator (LASSO), were used to identify key signature genes. These genes were further analyzed using Gene Set Variation Analysis (GSVA) and Gene Set Enrichment Analysis (GSEA), with their diagnostic values validated in both training and validation sets. Molecular docking studies were conducted. Additionally, immune cell infiltration and correlation analyses were performed to assess the relationship between immune responses and the identified biomarkers. Results: The functional enrichment analysis indicated that the common mechanisms are associated with cellular homeostasis, cell communication, cellular replication, inflammation, and extracellular matrix (ECM) production, with the PI3K-Akt signaling pathway being notably enriched. The PPI network revealed two key protein clusters related to the cell cycle and inflammation. CDK2 and CCND1 were identified as signature genes for both HF and KF. Their diagnostic value was validated in both training and validation sets. Additionally, docking studies with CDK2 and CCND1 were performed to evaluate potential drug candidates. Immune cell infiltration and correlation analyses highlighted the immune microenvironment, and that CDK2 and CCND1 are associated with immune responses in HF and KF. Discussion: This study identifies CDK2 and CCND1 as novel biomarkers linking cell cycle regulation and inflammation in heart and kidney failure. These findings offer new insights into the molecular mechanisms of HF and KF and present potential targets for diagnosis and therapy.
  • Thumbnail Image
    ItemOpen Access
    Building a fully-automatized active learning framework for the semantic segmentation of geospatial 3D point clouds
    (2024) Kölle, Michael; Walter, Volker; Sörgel, Uwe
    In recent years, significant progress has been made in developing supervised Machine Learning (ML) systems like Convolutional Neural Networks. However, it’s crucial to recognize that the performance of these systems heavily relies on the quality of labeled training data. To address this, we propose a shift in focus towards developing sustainable methods of acquiring such data instead of solely building new classifiers in the ever-evolving ML field. Specifically, in the geospatial domain, the process of generating training data for ML systems has been largely neglected in research. Traditionally, experts have been burdened with the laborious task of labeling, which is not only time-consuming but also inefficient. In our system for the semantic interpretation of Airborne Laser Scanning point clouds, we break with this convention and completely remove labeling obligations from domain experts who have completed special training in geosciences and instead adopt a hybrid intelligence approach. This involves active and iterative collaboration between the ML model and humans through Active Learning, which identifies the most critical samples justifying manual inspection. Only these samples (typically ≪1%of Passive Learning training points) are subject to human annotation. To carry out this annotation, we choose to outsource the task to a large group of non-specialists, referred to as the crowd, which comes with the inherent challenge of guiding those inexperienced annotators (i.e., “short-term employees”) to still produce labels of sufficient quality. However, we acknowledge that attracting enough volunteers for crowdsourcing campaigns can be challenging due to the tedious nature of labeling tasks. To address this, we propose employing paid crowdsourcing and providing monetary incentives to crowdworkers. This approach ensures access to a vast pool of prospective workers through respective platforms, ensuring timely completion of jobs. Effectively, crowdworkers become human processing units in our hybrid intelligence system mirroring the functionality of electronic processing units .