uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 51) Show all publications
Totu, T., Buga, R., Dumitru, A., Costache, M., Sladoje, N. & Stanciu, S. (2018). An Objective Scoring Framework for Histology Slide Image Mosaics Applicable for the Reliable Benchmarking of Image Quality Assessment Algorithms. IEEE Access, 6, 53080-53091
Open this publication in new window or tab >>An Objective Scoring Framework for Histology Slide Image Mosaics Applicable for the Reliable Benchmarking of Image Quality Assessment Algorithms
Show others...
2018 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 6, p. 53080-53091Article in journal (Refereed) Published
Abstract [en]

The conversion of histology slides into electronic format represents a key element in modern histopathology workflows. The most common way of converting physical histology slides into digital versions consists of tile-based scanning. In such approaches, the entire image of the slide is generated by consecutively scanning adjacent sample regions with a degree of overlap and then stitching these together to constitute an image mosaic. To achieve a high-quality result, the image acquisition protocol for collecting the mosaic tiles requires a recalibration of the microscope when moving from one sample region to another. This recalibration procedure typically involves focus and illumination adjustments, aimed at rendering a homogeneous image mosaic in terms of brightness, contrast, and other important image properties. The accurate evaluation of the digital slide's quality factor is, therefore, an important matter, as it can lead to designing efficient (and automated) mosaic generation protocols. We introduce here a new methodology for the evaluation of image mosaics collected with brightfield microscopy on histology slides, coined Objective Quantifiable Scoring System (OQSS). It relies on objective scoring criteria that take into consideration fundamental characteristics of image mosaics, and on histology specific aspects. We present the theoretical principles of this methodology and discuss the potential utility of this framework as a quality ground-truth tagging mechanism of histology slide image mosaics applicable for the reliable benchmarking of image quality assessment algorithms.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Microscopy, Benchmark testing, Image quality, Pathology, Reliability, Protocols, Lighting
National Category
Medical Image Processing Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367991 (URN)10.1109/ACCESS.2018.2868127 (DOI)000447722200001 ()
Funder
VINNOVA
Available from: 2018-12-02 Created: 2018-12-02 Last updated: 2018-12-10Bibliographically approved
Bajic, B., Suveer, A., Gupta, A., Pepic, I., Lindblad, J., Sladoje, N. & Sintorn, I.-M. (2018). Denoising of short exposure transmission electron microscopy images for ultrastructural enhancement. In: International Symposium on Biomedical Imaging (ISBI 2018): . Paper presented at IEEE 15th International Symposium on Biomedical Imaging (ISBI), Washington, D.C, USA, April 2018 (pp. 921-925). IEEE
Open this publication in new window or tab >>Denoising of short exposure transmission electron microscopy images for ultrastructural enhancement
Show others...
2018 (English)In: International Symposium on Biomedical Imaging (ISBI 2018), IEEE, 2018, p. 921-925Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
IEEE, 2018
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367040 (URN)10.1109/ISBI.2018.8363721 (DOI)
Conference
IEEE 15th International Symposium on Biomedical Imaging (ISBI), Washington, D.C, USA, April 2018
Funder
VINNOVA, 2016-02329
Available from: 2018-11-27 Created: 2018-11-27 Last updated: 2018-12-18
Gupta, A., Suveer, A., Bajic, B., Pepic, I., Lindblad, J., Sladoje, N. & Sintorn, I.-M. (2018). Denoising of Short Exposure Transmission Electron Microscopy Images using CNN. In: Swedish Symposium on Image Analysis: . Paper presented at SSBA2018, Stockholm, Sweden, March 2018.
Open this publication in new window or tab >>Denoising of Short Exposure Transmission Electron Microscopy Images using CNN
Show others...
2018 (English)In: Swedish Symposium on Image Analysis, 2018Conference paper, Published paper (Other academic)
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367996 (URN)
Conference
SSBA2018, Stockholm, Sweden, March 2018
Available from: 2018-12-02 Created: 2018-12-02 Last updated: 2018-12-02
Öfverstedt, J., Sladoje, N. & Lindblad, J. (2018). Distance Between Vector-valued Images based on Intersection Decomposition with Applications in Object Detection. In: Swedish Symposium on Image Analysis: . Paper presented at SSBA 2018, Stockholm, Sweden, March 2018.
Open this publication in new window or tab >>Distance Between Vector-valued Images based on Intersection Decomposition with Applications in Object Detection
2018 (English)In: Swedish Symposium on Image Analysis, 2018Conference paper, Published paper (Other academic)
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367997 (URN)
Conference
SSBA 2018, Stockholm, Sweden, March 2018
Available from: 2018-12-02 Created: 2018-12-02 Last updated: 2018-12-07
Öfverstedt, J., Lindblad, J. & Sladoje, N. (2018). Fast and Robust Symmetric Image Registration Based on Intensity and Spatial Information. arXiv
Open this publication in new window or tab >>Fast and Robust Symmetric Image Registration Based on Intensity and Spatial Information
2018 (English)In: arXiv, ISSN 2331-8422Article in journal (Other academic) Published
Abstract [en]

Intensity-based image registration approaches rely on similarity measures to guide the search for geometric correspondences with high affinity between images. The properties of the used measure are vital for the robustness and accuracy of the registration. In this study a symmetric, intensity interpolation-free, affine registration framework based on a combination of intensity and spatial information is proposed. The excellent performance of the framework is demonstrated on a combination of synthetic tests, recovering known transformations in the presence of noise, and real applications in biomedical and medical image registration, for both 2D and 3D images. The method exhibits greater robustness and higher accuracy than similarity measures in common use, when inserted into a standard gradient-based registration framework available as part of the open source Insight Segmentation and Registration Toolkit (ITK). The method is also empirically shown to have a low computational cost, making it practical for real applications. Source code is available.

National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367969 (URN)
Funder
VINNOVA, 2016-02329
Available from: 2018-12-01 Created: 2018-12-01 Last updated: 2018-12-07
Öfverstedt, J., Lindblad, J. & Sladoje, N. (2018). Stochastic Distance Transform. arXiv
Open this publication in new window or tab >>Stochastic Distance Transform
2018 (English)In: arXiv, ISSN 2331-8422Article in journal (Other academic) Published
Abstract [en]

The distance transform (DT) and its many variations are ubiquitous tools for image processing and analysis. In many imaging scenarios, the images of interest are corrupted by noise. This has a strong negative impact on the accuracy of the DT, which is highly sensitive to spurious noise points. In this study, we consider images represented as discrete random sets and observe statistics of DT computed on such representations. We, thus, define a stochastic distance transform (SDT), which has an adjustable robustness to noise. Both a stochastic Monte Carlo method and a deterministic method for computing the SDT are proposed and compared. Through a series of empirical tests, we demonstrate that the SDT is effective not only in improving the accuracy of the computed distances in the presence of noise, but also in improving the performance of template matching and watershed segmentation of partially overlapping objects, which are examples of typical applications where DTs are utilized.

National Category
Computer Vision and Robotics (Autonomous Systems) Discrete Mathematics
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-367970 (URN)
Available from: 2018-12-01 Created: 2018-12-01 Last updated: 2018-12-07
Wetzer, E., Lindblad, J., Sintorn, I.-M., Hultenby, K. & Sladoje, N. (2018). Towards automated multiscale imaging and analysis in TEM: Glomeruli detection by fusion of CNN and LBP maps. In: Swedish Symposium on Deep Learning: . Paper presented at Swedish Symposium on Deep Learning.
Open this publication in new window or tab >>Towards automated multiscale imaging and analysis in TEM: Glomeruli detection by fusion of CNN and LBP maps
Show others...
2018 (English)In: Swedish Symposium on Deep Learning, 2018Conference paper, Oral presentation with published abstract (Other academic)
Keywords
Machine learning
National Category
Medical Image Processing Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-368016 (URN)
Conference
Swedish Symposium on Deep Learning
Available from: 2018-12-03 Created: 2018-12-03 Last updated: 2018-12-04
Wetzer, E., Lindblad, J., Sintorn, I.-M., Hultenby, K. & Sladoje, N. (2018). Towards automated multiscale imaging and analysis in TEM: Glomerulus detection by fusion of CNN and LBP maps. In: Workshop on BioImage Computing @ ECCV 2018: . Paper presented at European Conference on Computer Vision - ECCV 2018. Springer
Open this publication in new window or tab >>Towards automated multiscale imaging and analysis in TEM: Glomerulus detection by fusion of CNN and LBP maps
Show others...
2018 (English)In: Workshop on BioImage Computing @ ECCV 2018, Springer, 2018Conference paper, Published paper (Refereed)
Abstract [en]

Glomerulal structures in kidney tissue have to be analysed at a nanometer scale for several medical diagnoses. They are therefore commonly imaged using Transmission Electron Microscopy. The high resolution produces large amounts of data and requires long acquisition time, which makes automated imaging and glomerulus detection a desired option. This paper presents a deep learning approach for Glomerulus detection, using two architectures, VGG16 (with batch normalization) and ResNet50. To enhance the performance over training based only on intensity images, multiple approaches to fuse the input with texture information encoded in local binary patterns of different scales have been evaluated. The results show a consistent improvement in Glomerulus detection when fusing texture-based trained networks with intensity-based ones at a late classification stage.

Place, publisher, year, edition, pages
Springer, 2018
Keywords
Texture Analysis, Convolutional Neural Networks, Machine learning
National Category
Computer Vision and Robotics (Autonomous Systems) Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-368015 (URN)
Conference
European Conference on Computer Vision - ECCV 2018
Note

Paper in print

Available from: 2018-12-03 Created: 2018-12-03 Last updated: 2018-12-04
Suveer, A., Sladoje, N., Lindblad, J., Dragomir, A. & Sintorn, I.-M. (2017). Cilia ultrastructural visibility enhancement by multiple instance registration and super-resolution reconstruction. In: Swedish Symposium on Image Analysis: . Swedish Society for Automated Image Analysis
Open this publication in new window or tab >>Cilia ultrastructural visibility enhancement by multiple instance registration and super-resolution reconstruction
Show others...
2017 (English)In: Swedish Symposium on Image Analysis, Swedish Society for Automated Image Analysis , 2017Conference paper, Published paper (Other academic)
Place, publisher, year, edition, pages
Swedish Society for Automated Image Analysis, 2017
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-335371 (URN)
Available from: 2017-12-04 Created: 2017-12-04 Last updated: 2018-08-24
Öfverstedt, J., Sladoje, N. & Lindblad, J. (2017). Distance between vector-valued fuzzy sets based on intersection decomposition with applications in object detection. In: Mathematical Morphology and its Applications to Signal and Image Processing: . Paper presented at ISMM 2017, May 15–17, Fontainebleau, France (pp. 395-407). Springer, 10225
Open this publication in new window or tab >>Distance between vector-valued fuzzy sets based on intersection decomposition with applications in object detection
2017 (English)In: Mathematical Morphology and its Applications to Signal and Image Processing, Springer, 2017, Vol. 10225, p. 395-407Conference paper, Published paper (Refereed)
Abstract [en]

We present a novel approach to measuring distance between multi-channel images, suitably represented by vector-valued fuzzy sets. We first apply the intersection decomposition transformation, based on fuzzy set operations, to vector-valued fuzzy representations to enable preservation of joint multi-channel properties represented in each pixel of the original image. Distance between two vector-valued fuzzy sets is then expressed as a (weighted) sum of distances between scalar-valued fuzzy components of the transformation. Applications to object detection and classification on multi-channel images and heterogeneous object representations are discussed and evaluated subject to several important performance metrics. It is confirmed that the proposed approach outperforms several alternative single-and multi-channel distance measures between information-rich image/ object representations.

Place, publisher, year, edition, pages
Springer, 2017
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 10225
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-334377 (URN)10.1007/978-3-319-57240-6_32 (DOI)978-3-319-57239-0 (ISBN)
Conference
ISMM 2017, May 15–17, Fontainebleau, France
Available from: 2017-04-12 Created: 2017-11-22 Last updated: 2018-12-04
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-6041-6310

Search in DiVA

Show all publications

Profile pages

Personal page