Automatic segmentation of cristae membranes in 3d electron microscopy tomography images using artificial neural networks

Download

index.pdf

Date

2016

Author

Karadeniz, Merih Alphan

Metadata

Show full item record

Item Usage Stats

236
views

145
downloads

Electron Microscopy Tomography (EMT) technique produces 3D images of cells comprising hundreds of slices of high resolution frames. Segmentation of membranes in these images are necessary in order to reveal the relations between the structural components of the cell and its behaviour. The physical shape of the crista which is a membrane of the mitochondria has been hypostatized for being an early indicator for many diseases or mitochondrial dysfunctions. Automatic segmentation of cristae in EMT images are necessary since it needs a huge human effort to manually segment these membranes. In this study, a method for automatic and robust segmentation of the crista membrane in mitochondria is proposed. The method incorporates a pre-processing stage in which a bilateral image smoothing is applied for noise removal while preserving the crista membrane boundaries. The cristae membranes are first detected by an artificial neural network (ANN) trained on cropped mitochondria images from three different data sets. When a portion of the membrane boundary is almost or totally invisible, ANN may produce disconnected segmentation. In order to overcome this issue and increase the final performance by means of detecting the barely invisible membrane boundaries and decreasing false alarms, a boundary growing method called ‘directional growing’ is proposed. The method is tested with examples from four different data sets and numerical and visual analysis of the results are conducted

Subject Keywords

Tomography., Electron microscopy., Imaging systems in medicine., Image processing, Neural networks (Computer science).

URI

http://etd.lib.metu.edu.tr/upload/12620402/index.pdf
https://hdl.handle.net/11511/26098

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

Quantitative measurements obtained by micro-computed tomography and confocal laser scanning microscopy KAMBUROĞLU, KIVANÇ; Barenboim, S. F.; Arituerk, T.; Kaffe, I. (British Institute of Radiology, 2008-10-01) Objectives: To compare measurements obtained by micro-CT with those obtained by confocal laser scanning microscope in simulative internal resorption cavities.
High resolution computational spectral imaging with photon sieves Öktem, Sevinç Figen; Davila, Joseph (2014-10-27) Photon sieves, modifications of Fresnel zone plates, are a new class of diffractive image forming devices that open up new possibilities for high resolution imaging and spectroscopy, especially at UV and x-ray regime. In this paper, we develop a novel computational photon sieve imaging modality that enables high-resolution spectral imaging. For the spatially incoherent illumination, we study the problem of recovering the individual spectral images from the superimposed and blurred measurements of the propos...
Application of High Resolution Magnetic Resonance Imaging Methods for Spinal Cord Tissue Segmentation Durlu, Caglayan; Erdogan, Hasan Balkar; Kucukdeveci, Osman Fikret; Gençer, Nevzat Güneri (2016-01-01) This paper presents the primitive results of high resolution Magnetic Resonance (MR) Imaging experiments that are performed for spinal cord segmentation purposes. In the study, it is aimed to image the epidural space, the cerebrospinal fluid, the white matter and the gray matter tissues in the lower cervical and upper thoracic regions of the spine with a maximum voxel size of 1x1x1 mm(3). For this purpose, the MRI sequences providing T2 and T2* images and used for spinal cord segmentation in the literature ...
DeepDistance: A multi-task deep regression model for cell detection in inverted microscopy images Koyuncu, Can Fahrettin; Gunesli, Gozde Nur; Atalay, Rengül; GÜNDÜZ DEMİR, Çiğdem (Elsevier BV, 2020-07-01) This paper presents a new deep regression model, which we call DeepDistance, for cell detection in images acquired with inverted microscopy. This model considers cell detection as a task of finding most probable locations that suggest cell centers in an image. It represents this main task with a regression task of learning an inner distance metric. However, different than the previously reported regression based methods, the DeepDistance model proposes to approach its learning as a multi-task regression pro...
Image-based extraction of material reflectance properties of a 3D rigid object Erdem, ME; Erdem, IA; Yilmaz, UG; Atalay, Mehmet Volkan (2004-01-01) In this study, an appearance reconstruction method based on extraction of material reflectance properties of a three-dimensional (3D) object from its two-dimensional (2D) images is explained. One of the main advantages of this system is that the reconstructed object can be rendered in real-time with photorealistic quality in varying illumination conditions. The reflectance of the object is decomposed into diffuse and specular components. While the diffuse component is stored in a global texture, the specula...

Citation Formats

M. A. Karadeniz, “Automatic segmentation of cristae membranes in 3d electron microscopy tomography images using artificial neural networks,” M.S. - Master of Science, Middle East Technical University, 2016.