5 results
Search Results
Now showing 1 - 5 of 5
- ItemSemantic segmentation of non-linear multimodal images for disease grading of inflammatory bowel disease: A segnet-based application([Sétubal] : SCITEPRESS - Science and Technology Publications Lda., 2019) Pradhan, Pranita; Meyer, Tobias; Vieth, Michael; Stallmach, Andreas; Waldner, Maximilian; Schmitt, Michael; Popp, Juergen; Bocklitz, Thomas; De Marsico, Maria; Sanniti di Baja, Gabriella; Fred, AnaNon-linear multimodal imaging, the combination of coherent anti-stokes Raman scattering (CARS), two-photon excited fluorescence (TPEF) and second harmonic generation (SHG), has shown its potential to assist the diagnosis of different inflammatory bowel diseases (IBDs). This label-free imaging technique can support the ‘gold-standard’ techniques such as colonoscopy and histopathology to ensure an IBD diagnosis in clinical environment. Moreover, non-linear multimodal imaging can measure biomolecular changes in different tissue regions such as crypt and mucosa region, which serve as a predictive marker for IBD severity. To achieve a real-time assessment of IBD severity, an automatic segmentation of the crypt and mucosa regions is needed. In this paper, we semantically segment the crypt and mucosa region using a deep neural network. We utilized the SegNet architecture (Badrinarayanan et al., 2015) and compared its results with a classical machine learning approach. Our trained SegNet mod el achieved an overall F1 score of 0.75. This model outperformed the classical machine learning approach for the segmentation of the crypt and mucosa region in our study.
- ItemIn-vivo Raman spectroscopy: from basics to applications(Bellingham, Wash. : SPIE, 2018) Cordero, Eliana; Latka, Ines; Matthäus, Christian; Schie, Iwan W.; Popp, JürgenFor more than two decades, Raman spectroscopy has found widespread use in biological and medical applications. The instrumentation and the statistical evaluation procedures have matured, enabling the lengthy transition from ex-vivo demonstration to in-vivo examinations. This transition goes hand-in-hand with many technological developments and tightly bound requirements for a successful implementation in a clinical environment, which are often difficult to assess for novice scientists in the field. This review outlines the required instrumentation and instrumentation parameters, designs, and developments of fiber optic probes for the in-vivo applications in a clinical setting. It aims at providing an overview of contemporary technology and clinical trials and attempts to identify future developments necessary to bring the emerging technology to the clinical end users. A comprehensive overview of in-vivo applications of fiber optic Raman probes to characterize different tissue and disease types is also given.
- ItemZooming in on virus surface protein mobility(London : Future Medicine Ltd, 2018) Chojnacki, Jakub; Eggeling, Christian[no abstract available]
- ItemA Computational Pipeline for Sepsis Patients’ Stratification and Diagnosis([Setúbal, Portugal] : SCITEPRESS - Science and Technology Publications, Lda., 2018) Campos, David; Pinho, Renato; Neugebauer, Ute; Popp, Juergen; Oliveira, José Luis; Zwiggelaar, Reyer; Gamboa, Hugo; Fred, Ana; Bermúdez i Badia, SergiSepsis is still a little acknowledged public health issue, despite its increasing incidence and the growing mortality rate. In addition, a clear diagnosis can be lengthy and complicated, due to highly variable symptoms and non-specific criteria, causing the disease to be diagnosed and treated too late. This paper presents the HemoSpec platform, a decision support system which, by collecting and automatically processing data from several acquisition devices, can help in the early diagnosis of sepsis.
- ItemRelated carbapenemase-producing Klebsiella isolates detected in both a hospital and associated aquatic environment in Sweden(Berlin ; Heidelberg ; New York : Springer, 2018-8-31) Khan, Faisal Ahmad; Hellmark, Bengt; Ehricht, Ralf; Söderquist, Bo; Jass, JanaCarbapenem antibiotics are one of the last-resort agents against multidrug-resistant (MDR) bacteria. The occurrence of carbapenemase-producing Enterobacteriaceae (CPE) in wastewater and aquatic environments is an indication of MDR bacteria in the community. This study evaluated CPE in aquatic environments and compared them to the local hospital isolates in Sweden. Phenotypic and genotypic analyses of antibiotic resistance of environmental and clinical CPE were performed. The relatedness of the isolates and possible clonal dissemination was evaluated using phylogenetic and phyloproteomic analysis. Klebsiella oxytoca carrying carbapenemase genes (blaVIM-1, blaIMP-29) were isolated from wastewater and the recipient river, while K. oxytoca (blaVIM-1) and Klebsiella pneumoniae (blaVIM-1, blaOXA-48, blaNDM-1, blaKPC-3) were isolated from patients at the local clinics or hospital. The K. oxytoca classified as sequence type 172 (ST172) isolated from the river was genotypically related to two clinical isolates recovered from patients. The similarity between environmental and clinical isolates suggests the dispersion of blaVIM-1 producing K. oxytoca ST172 from hospital to aquatic environment and the likelihood of its presence in the community. This is the first report of CPE in aquatic environments in Sweden; therefore, surveillance of aquatic and hospital environments for CPE in other urban areas is important to determine the major transfer routes in order to formulate strategies to prevent the spread of MDR bacteria.