Filters

2018 - 201922020 - 20212

More filters

2022 - 20234
Reset filters

Settings

Author: Popp, Juergen × Start date: 2022 × End date: 2024 × DDC: 610 × Type: Text × WGL Institute: IPHT ×

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Semantic 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, Ana
    Non-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.
  • Thumbnail Image
    Item
    A 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, Sergi
    Sepsis 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.
  • Thumbnail Image
    Item
    Computational tissue staining of non-linear multimodal imaging using supervised and unsupervised deep learning
    (Washington, DC : OSA, 2021) Pradhan, Pranita; Meyer, Tobias; Vieth, Michael; Stallmach, Andreas; Waldner, Maximilian; Schmitt, Michael; Popp, Juergen; Bocklitz, Thomas
    Hematoxylin and Eosin (H&E) staining is the 'gold-standard' method in histopathology. However, standard H&E staining of high-quality tissue sections requires long sample preparation times including sample embedding, which restricts its application for 'real-time' disease diagnosis. Due to this reason, a label-free alternative technique like non-linear multimodal (NLM) imaging, which is the combination of three non-linear optical modalities including coherent anti-Stokes Raman scattering, two-photon excitation fluorescence and second-harmonic generation, is proposed in this work. To correlate the information of the NLM images with H&E images, this work proposes computational staining of NLM images using deep learning models in a supervised and an unsupervised approach. In the supervised and the unsupervised approach, conditional generative adversarial networks (CGANs) and cycle conditional generative adversarial networks (cycle CGANs) are used, respectively. Both CGAN and cycle CGAN models generate pseudo H&E images, which are quantitatively analyzed based on mean squared error, structure similarity index and color shading similarity index. The mean of the three metrics calculated for the computationally generated H&E images indicate significant performance. Thus, utilizing CGAN and cycle CGAN models for computational staining is beneficial for diagnostic applications without performing a laboratory-based staining procedure. To the author's best knowledge, it is the first time that NLM images are computationally stained to H&E images using GANs in an unsupervised manner.
  • Thumbnail Image
    Item
    Three step flow focusing enables image-based discrimination and sorting of late stage 1 Haematococcus pluvialis cells
    (San Francisco, Ca. : PLOS, 2021) Kraus, Daniel; Kleiber, Andreas; Ehrhardt, Enrico; Leifheit, Matthias; Horbert, Peter; Urban, Matthias; Gleichmann, Nils; Mayer, Guenter; Popp, Juergen; Henkel, Thomas
    Label-free and gentle separation of cell stages with desired target properties from mixed stage populations are a major research task in modern biotechnological cultivation process and optimization of micro algae. The reported microfluidic sorter system (MSS) allows the subsequent investigation of separated subpopulations. The implementation of a viability preserving MSS is shown for separation of late stage 1 Haematococcus pluvialis (HP) cells form a mixed stage population. The MSS combines a three-step flow focusing unit for aligning the cells in single file transportation mode at the center of the microfluidic channel with a pure hydrodynamic sorter structure for cell sorting. Lateral displacement of the cells into one of the two outlet channels is generated by piezo-actuated pump chambers. In-line decision making for sorting is based on a user-definable set of image features and properties. The reported MSS significantly increased the purity of target cells in the sorted population (94%) in comparison to the initial mixed stage population (19%).