next up previous contents
Next: Research Up: Graduate education Previous: Graduate courses   Contents


  1. Date: 150306 
    Image Segmentation using Snakes and Stochastic Watershed
    with applications to microscopy images of biological tissue
    Student: Bettina Selig 
    Supervisor: Cris L. Luengo 
    Assistant Supervisors: Gunilla Borgefors
    Opponent: Jesús Angulo, Center of Mathematical Morphology, MINES ParisTech
    Committee: Josef Bigun, Halmstad University; Michael Felsberg, Linköping University; Olen Tanyevych, University Paris-Est Créteil, Paris, France  
    Publisher: Acta Universitatis agriculturae Sueciae, ISBN: 978-91-576-8230-7 
    Abstract: The purpose of computerized image analysis is to extract meaningful information from digital images. To be able to find interesting regions or objects in the image, first, the image needs to be segmented. This thesis concentrates on two concepts that are used for image segmentation: the snake and the stochastic watershed. First, we focus on snakes, which are described by contours moving around on the image to find boundaries of objects. Snakes usually fail when concentric contours with similar appearance are supposed to be found successively, because it is impossible for the snake to push off one boundary and settle at the next. This thesis proposes the two-stage snake to overcome this problem. The two-stage snake introduces an intermediate snake that moves away from the influence region of the first boundary, to be able to be attracted by the second boundary. The two-stage snake approach is illustrated on fluorescence microscopy images of compression wood cross-sections for which previously no automated method existed. Further, we discuss and evolve the idea of stochastic watershed, originally a Monte Carlo approach to determine the most salient contours in the image. This approach has room for improvement concerning runtime and suppression of falsely enhanced boundaries. In this thesis, we propose the exact evaluation of the stochastic watershed (ESW) and the robust stochastic watershed (RSW), which address these two issues separately. With the ESW, we can determine the result without any Monte Carlo simulations, but instead using graph theory. Our algorithm is two orders of magnitude faster than the original approach. The RSW uses noise to disrupt weak boundaries that are consistently found in larger areas. It therefore improves the results for problems where objects differ in size. To benefit from the advantages of both new methods, we merged them in the fast robust stochastic watershed (FRSW). This FRSW uses a few realizations of the ESW, adding noise as in the RSW. Finally, we illustrate the RSW and the FRSW to segment in vivo confocal microscopy images of corneal endothelium. Our methods outperform the automatic segmentation algorithm in the commercial software NAVIS.

  2. Date: 20150612 
    Computerized Cell and Tissue Analysis 
    Student: Azadeh Fakhrzadeh 
    Supervisor: Cris L. Luengo
    Assistant Supervisor: Gunilla Borgefors; Lena Holm, Swedish University of Agricultural Sciences 
    Opponent: Nasir Rajpoot, University of Warwick, United Kingdom
    Committee: Ingela Parmryd, Dept. of Medical Cell Biology, UU; Johan Lundin, Institute for Molecular Medicine Finland, Helsinki, Finland; Anders Heyden, Lund University; Petter Ranefall, CBA (Reserve Committee Member)
    Publisher: Acta Universitatis Upsaliensis, ISBN: 978-91-554-9269-4
    Abstract: The latest advances in digital cameras combined with powerful computer software enable us to store high-quality microscopy images of specimen. Studying hundreds of images manually is very time consuming and has the problem of human subjectivity and inconsistency. Quantitative image analysis is an emerging field and has found its way into analysis of microscopy images for clinical and research purposes. When developing a pipeline, it is important that its components are simple enough to be generalized and have predictive value. This thesis addresses the automation of quantitative analysis of tissue in two different fields: pathology and plant biology.

    Testicular tissue is a complex structure consisting of seminiferous tubules. The epithelial layer of a seminiferous tubule contains cells that differentiate from primitive germ cells to spermatozoa in a number of steps. These steps are combined in 12 stages in the cycle of the seminiferous epithelium in the mink. The society of toxicological pathology recommends classifying the testicular epithelial into different stages when assessing tissue damage to determine if the dynamics in the spermatogenic cycle have been disturbed. This thesis presents two automated methods for fast and robust segmentation of tubules, and an automated method of staging them. For better accuracy and statistical analysis, we proposed to pool stages into 5 groups. This pooling is suggested based on the morphology of tubules. In the 5 stage case, the overall number of correctly classified tubules is 79.6