Blar i Institutt for helsevitenskap Gjøvik på forfatter "Pedersen, Marius"
-
A Weighted Histogram-Based Tone Mapping Algorithm for CT images
Völgyes, David; Martinsen, Anne Catrine Trægde; Stray-Pedersen, Arne; Waaler, Dag; Pedersen, Marius (Journal article; Peer reviewed, 2018)Computed Tomography (CT) images have a high dynamic range, which makes visualization challenging. Histogram equalization methods either use spatially invariant weights or limited kernel size due to the complexity of pairwise ... -
Enhancement of clustering techniques by coupling clustering tree and neural network: Application to brain tumour segmentation
Osadebey, Michael; Pedersen, Marius; Kalra, Meeta; Waaler, Dag; bouguila, nizar (Journal article; Peer reviewed, 2022) -
Evaluation of color spaces for unsupervised and deep learning skin lesion segmentation
Osadebey, Michael; Pedersen, Marius; Waaler, Dag (Chapter, 2020)The reliability of skin cancer diagnosis is dependent on accurate lesion segmentation. The choice of a color space in most contributions on skin lesion segmentation for melanoma detection are based on qualitative rather ... -
How different iterative and filtered back projection kernels affect CT numbers and low contrast detectability
Volgyes, David; Pedersen, Marius; Stray-Pedersen, Arne; Waaler, Dag; Martinsen, Anne Catrine Trægde (Journal article; Peer reviewed, 2016)Objective: The aim of this study was to evaluate how different iterative and filtered back projection kernels affect the computed tomography (CT) numbers and low contrast detectability. Methods: Five different scans ... -
Image De-Quantization Using Plate Bending Model
Völgyes, David; Martinsen, Anne Catrine Trægde; Stray-Pedersen, Arne; Waaler, Dag; Pedersen, Marius (Journal article; Peer reviewed, 2018)Discretized image signals might have a lower dynamic range than the display. Because of this, false contours might appear when the image has the same pixel value for a larger region and the distance between pixel levels ... -
Image texture and radiation dose properties in CT
Możejko, Dawid; Andersen, Hilde Kjernlie; Pedersen, Marius; Waaler, Dag; Martinsen, Anne Catrine Trægde (Journal article; Peer reviewed, 2016)The aim of this study was to compare image noise properties of GE Discovery HD 750 and Toshiba Aquilion ONE. The uniformity section of a Catphan 600 image quality assurance phantom was scanned with both scanners, at different ... -
Learning-based segmentation of optic disc in retinal images using clustering trees and local mode filtering
Osadebey, Michael; Pedersen, Marius; Waaler, Dag (Chapter, 2020)Delineation of the optic disc boundary in retinal images is the first step towards the computation of cup-to-disc ratio, an important indicator of ophthalmic pathologies such as glaucoma. This paper proposes the combination ... -
Memory Effects in Subjective Quality Assessment of X-Ray Images
Landré, Victor; Pedersen, Marius; Waaler, Dag (Chapter, 2017)Experiments with human observers is considered as the most precise way for the assessment of image quality. Although widely used, such experiments have its pitfalls and hazards. In this work we investigate if the quality ... -
Plant Leaves Region Segmentation in Cluttered and Occluded Images Using Perceptual Color Space and K-means-Derived Threshold with Set Theory
Osadebey, Michael; Pedersen, Marius; Waaler, Dag (Journal article; Peer reviewed, 2019) -
Simultaneous Artefact-Lesion Extraction for Skin Cancer Diagnosis
Osadebey, Michael; Pedersen, Marius; Waaler, Dag (Chapter, 2021)Presence of clutters, occlusions and dark corner artifacts in dermatoscopy images causes unsupervised and intensity-based image analysis systems to erroneously segment lesion boundaries required for accurate and reliable ... -
Three-stage segmentation of lung region from CT images using deep neural networks
Osadebey, Michael; Andersen, Hilde Kjernlie; Waaler, Dag; Fosså, Kristian; Martinsen, Anne Catrine Trægde; Pedersen, Marius (Journal article; Peer reviewed, 2021)