liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 30) Show all publications
Zhang, Y., Robinson, A., Magnusson, M. & Felsberg, M. (2023). Leveraging Optical Flow Features for Higher Generalization Power in Video Object Segmentation. In: 2023 IEEEInternational Conferenceon Image Processing: Proceedings. Paper presented at 2023 IEEE International Conference on Image Processing (ICIP), 8–11 October 2023 Kuala Lumpur, Malaysia (pp. 326-330). IEEE
Open this publication in new window or tab >>Leveraging Optical Flow Features for Higher Generalization Power in Video Object Segmentation
2023 (English)In: 2023 IEEEInternational Conferenceon Image Processing: Proceedings, IEEE , 2023, p. 326-330Conference paper, Published paper (Refereed)
Abstract [en]

We propose to leverage optical flow features for higher generalization power in semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in many computer vision tasks. However, its relevance in video object segmentation was mainly in unsupervised settings or using the optical flow to warp or refine the previously predicted masks. Different from the latter, we propose to directly leverage the optical flow features in the target representation. We show that this enriched representation improves the encoder-decoder approach to the segmentation task. A model to extract the combined information from the optical flow and the image is proposed, which is then used as input to the target model and the decoder network. Unlike previous methods, e.g. in tracking where concatenation is used to integrate information from image data and optical flow, a simple yet effective attention mechanism is exploited in our work. Experiments on DAVIS 2017 and YouTube-VOS 2019 show that integrating the information extracted from optical flow into the original image branch results in a strong performance gain, especially in unseen classes which demonstrates its higher generalization power.

Place, publisher, year, edition, pages
IEEE, 2023
Keywords
Optical flow features; Attention mechanism; Semi-supervised VOS; Generalization power
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:liu:diva-199057 (URN)10.1109/ICIP49359.2023.10222542 (DOI)001106821000063 ()9781728198354 (ISBN)9781728198361 (ISBN)
Conference
2023 IEEE International Conference on Image Processing (ICIP), 8–11 October 2023 Kuala Lumpur, Malaysia
Available from: 2023-11-08 Created: 2023-11-08 Last updated: 2024-03-12
Magnusson, M., Alm Carlsson, G., Sandborg, M., Carlsson Tedgren, Å. & Malusek, A. (2023). On the Choice of Base Materials for Alvarez–Macovski and DIRA Dual-energy Reconstruction Algorithms in CT. In: Scott Hsieh, Krzysztof (Kris) Iniewski (Ed.), Photon Counting Computed Tomography: Clinical Applications, Image Reconstruction and Material Discrimination (pp. 153-175). Cham: Springer
Open this publication in new window or tab >>On the Choice of Base Materials for Alvarez–Macovski and DIRA Dual-energy Reconstruction Algorithms in CT
Show others...
2023 (English)In: Photon Counting Computed Tomography: Clinical Applications, Image Reconstruction and Material Discrimination / [ed] Scott Hsieh, Krzysztof (Kris) Iniewski, Cham: Springer , 2023, p. 153-175Chapter in book (Refereed)
Abstract [en]

The choice of the material base to which the material decomposition is performed in dual-energy computed tomography may affect the quality of reconstructed images. Resulting inaccuracies may lower their diagnostic value, or if the data are used for radiation treatment planning, the accuracy of such plans. The aim of this work is to investigate how the commonly used (water, bone) (WB), (water, iodine) (WI), and (approximate photoelectric effect, Compton scattering) (PC) doublets affect the reconstructed linear attenuation coefficient in the case of the Alvarez–Macovski (AM) method. The performance of this method is also compared to the performance of the dual-energy iterative reconstruction algorithm DIRA. In both cases, the study is performed using simulations.

The results show that the PC and WB doublets accurately predicted the linear attenuation coefficient (LAC) values for human tissues and elements with Z = 1, …, 20, in the 20–150 keV range, though there was a small (<5% discrepancy in the 20–35 keV range. The WI doublet did not represent the tissues as well as PC and WB; the largest discrepancies (>50% in some cases) were in the 20–40 keV range.

LACs reconstructed with the AM and DIRA followed this trend. AM produced artifacts when iodine was present in the phantom together with human tissues since AM can only work with one doublet at a time. It was shown that these artifacts could be avoided with DIRA using different doublets at different spatial positions, i.e., WB for soft and bone tissue and WI for the iodine solution.

Place, publisher, year, edition, pages
Cham: Springer, 2023
National Category
Medical Engineering
Identifiers
urn:nbn:se:liu:diva-194309 (URN)10.1007/978-3-031-26062-9_8 (DOI)2-s2.0-85172101197 (Scopus ID)9783031260629 (ISBN)9783031260612 (ISBN)
Note

Funding text: This work was supported by Cancerfonden [CAN 2017/1029, CAN 2018/622]; ALF Grants Region Östergötland [LiO-602731]; Patientsäkerhetsforskning Region Östergötland [LiO-724181]; and Vetenskapsrådet [VR-NT 2016-05033].

Available from: 2023-06-01 Created: 2023-06-01 Last updated: 2025-02-21Bibliographically approved
Magnusson, M., Sandborg, M., Alm Carlsson, G., Henriksson, L., Carlsson Tedgren, Å. & Malusek, A. (2021). ACCURACY OF CT NUMBERS OBTAINED BY DIRA AND MONOENERGETIC PLUS ALGORITHMS IN DUAL-ENERGY COMPUTED TOMOGRAPHY. Radiation Protection Dosimetry, 195(3-4), 212-217
Open this publication in new window or tab >>ACCURACY OF CT NUMBERS OBTAINED BY DIRA AND MONOENERGETIC PLUS ALGORITHMS IN DUAL-ENERGY COMPUTED TOMOGRAPHY
Show others...
2021 (English)In: Radiation Protection Dosimetry, ISSN 0144-8420, E-ISSN 1742-3406, Vol. 195, no 3-4, p. 212-217Article in journal (Refereed) Published
Abstract [en]

Dual-energy computed tomography (CT) can be used in radiotherapy treatment planning for the calculation of absorbed dose distributions. The aim of this work is to evaluate whether there is room for improvement in the accuracy of the Monoenergetic Plus algorithm by Siemens Healthineers. A Siemens SOMATOM Force scanner was used to scan a cylindrical polymethyl methacrylate phantom with four rod-inserts made of different materials. Images were reconstructed using ADMIRE and processed with Monoenergetic Plus. The resulting CT numbers were compared with tabulated values and values simulated by the proof-of-a-concept algorithm DIRA developed by the authors. Both the Monoenergetic Plus and DIRA algorithms performed well; the accuracy of attenuation coefficients was better than about ±1% at the energy of 70 keV. Compared with DIRA, the worse performance of Monoenergetic Plus was caused by its (i) two-material decomposition to iodine and water and (ii) imperfect suppression of the beam hardening artifact in ADMIRE.

Place, publisher, year, edition, pages
Oxford University Press, 2021
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-180414 (URN)10.1093/rpd/ncab108 (DOI)000711245400013 ()34265847 (PubMedID)
Note

Funding: CancerfondenSwedish Cancer Society [CAN 2017/1029, CAN 2018/622]; Swedish state government [LiO-602731]; Swedish county councils, the ALF-agreement [LiO-602731]; Patientsakerhetsforskning Region Ostergotland [LiO-724181]; VetenskapsradetSwedish Research Council [VR-NT 2016-05033]

Available from: 2021-10-19 Created: 2021-10-19 Last updated: 2022-05-25Bibliographically approved
Magnusson, M., Alm Carlsson, G., Sandborg, M., Carlsson Tedgren, Å. & Malusek, A. (2021). Optimal Selection of Base Materials for Accurate Dual-Energy Computed Tomography: Comparison Between the Alvarez–Macovski Method and DIRA. Paper presented at Optimisation in X-ray and Molecular Imaging 2020, Gothenburg, Sweden, 22-24 June 2020.. Radiation Protection Dosimetry, 195(3-4), 218-224
Open this publication in new window or tab >>Optimal Selection of Base Materials for Accurate Dual-Energy Computed Tomography: Comparison Between the Alvarez–Macovski Method and DIRA
Show others...
2021 (English)In: Radiation Protection Dosimetry, ISSN 0144-8420, E-ISSN 1742-3406, Vol. 195, no 3-4, p. 218-224Article in journal (Refereed) Published
Abstract [en]

The choice of the material base to which the material decomposition is performed in dual-energy computed tomography may affect the quality of reconstructed images. The aim of this work is to investigate how the commonly used bases (water, bone), (water, iodine) and (photoelectric effect, Compton scattering) affect the reconstructed linear attenuation coefficient in the case of the Alvarez–Macovski method. The performance of this method is also compared with the performance of the Dual-energy Iterative Reconstruction Algorithm (DIRA). In both cases, the study is performed using simulations. The results show that the Alvarez–Macovski method produced artefacts when iodine was present in the phantom together with human tissues since this method can only work with one doublet. It was shown that these artefacts could be avoided with DIRA using the (water, bone) doublet for tissues and the (water, iodine) doublet for the iodine solution.

Place, publisher, year, edition, pages
Oxford University Press, 2021
Keywords
Public Health, Environmental and Occupational Health, Radiology Nuclear Medicine and imaging, General Medicine, Radiation, Radiological and Ultrasound Technology
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-180182 (URN)10.1093/rpd/ncab097 (DOI)000711245400014 ()34240219 (PubMedID)
Conference
Optimisation in X-ray and Molecular Imaging 2020, Gothenburg, Sweden, 22-24 June 2020.
Funder
Swedish Cancer Society, CAN 2017/1029Region Östergötland, LiO-602731Swedish Cancer Society, CAN 2018/622Region Östergötland, LiO-724181Swedish Research Council, VR-NT 2016-05033
Note

Funding: CancerfondenSwedish Cancer Society [CAN 2017/1029, CAN 2018/622]; ALF Grants Region Ostergotland [LiO-602731]; Patientsakerhetsforskning Region Ostergotland [LiO-724181]; VetenskapsradetSwedish Research Council [VR-NT 2016-05033]

Available from: 2021-10-11 Created: 2021-10-11 Last updated: 2021-11-15Bibliographically approved
Jeuthe, J., Sánchez, J. C., Magnusson, M., Sandborg, M., Carlsson Tedgren, Å. & Malusek, A. (2021). Semi-Automated 3D Segmentation of Pelvic Region Bones in CT Volumes for the Annotation of Machine Learning Datasets. Paper presented at Optimisation in X-ray and Molecular Imaging 2020, Gothenburg, Sweden, 22-24 June 2020.. Radiation Protection Dosimetry, 195(3-4), 172-176
Open this publication in new window or tab >>Semi-Automated 3D Segmentation of Pelvic Region Bones in CT Volumes for the Annotation of Machine Learning Datasets
Show others...
2021 (English)In: Radiation Protection Dosimetry, ISSN 0144-8420, E-ISSN 1742-3406, Vol. 195, no 3-4, p. 172-176Article in journal (Refereed) Published
Abstract [en]

Automatic segmentation of bones in computed tomography (CT) images is used for instance in beam hardening correction algorithms where it improves the accuracy of resulting CT numbers. Of special interest are pelvic bones, which—because of their strong attenuation—affect the accuracy of brachytherapy in this region. This work evaluated the performance of the JJ2016 algorithm with the performance of MK2014v2 and JS2018 algorithms; all these algorithms were developed by authors. Visual comparison, and, in the latter case, also Dice similarity coefficients derived from the ground truth were used. It was found that the 3D-based JJ2016 performed better than the 2D-based MK2014v2, mainly because of the more accurate hole filling that benefitted from information in adjacent slices. The neural network-based JS2018 outperformed both traditional algorithms. It was, however, limited to the resolution of 1283 owing to the limited amount of memory in the graphical processing unit (GPU).

Place, publisher, year, edition, pages
Oxford University Press, 2021
Keywords
Public Health, Environmental and Occupational Health, Radiology Nuclear Medicine and imaging, General Medicine, Radiation
National Category
Health Sciences
Identifiers
urn:nbn:se:liu:diva-180196 (URN)10.1093/rpd/ncab073 (DOI)000711245400008 ()34037238 (PubMedID)
Conference
Optimisation in X-ray and Molecular Imaging 2020, Gothenburg, Sweden, 22-24 June 2020.
Note

Funding: VetenskapsradetSwedish Research Council [VR-NT 2016-05033]

Available from: 2021-10-11 Created: 2021-10-11 Last updated: 2024-03-25Bibliographically approved
Kardell, M., Magnusson, M., Sandborg, M., Alm Carlsson, G., Jeuthe, J. & Malusek, A. (2016). AUTOMATIC SEGMENTATION OF PELVIS FOR BRACHYTHERAPYOF PROSTATE. Radiation Protection Dosimetry, 169(1-4), 398-404
Open this publication in new window or tab >>AUTOMATIC SEGMENTATION OF PELVIS FOR BRACHYTHERAPYOF PROSTATE
Show others...
2016 (English)In: Radiation Protection Dosimetry, ISSN 0144-8420, E-ISSN 1742-3406, Vol. 169, no 1-4, p. 398-404Article in journal (Refereed) Published
Abstract [en]

Advanced model-based iterative reconstruction algorithms in quantitative computed tomography (CT) perform automatic segmentation of tissues to estimate material properties of the imaged object. Compared with conventional methods, these algorithms may improve quality of reconstructed images and accuracy of radiation treatment planning. Automatic segmentation of tissues is, however, a difficult task. The aim of this work was to develop and evaluate an algorithm that automatically segments tissues in CT images of the male pelvis. The newly developed algorithm (MK2014) combines histogram matching, thresholding, region growing, deformable model and atlas-based registration techniques for the segmentation of bones, adipose tissue, prostate and muscles in CT images. Visual inspection of segmented images showed that the algorithm performed well for the five analysed images. The tissues were identified and outlined with accuracy sufficient for the dual-energy iterative reconstruction algorithm whose aim is to improve the accuracy of radiation treatment planning in brachytherapy of the prostate.

National Category
Medical Imaging
Identifiers
urn:nbn:se:liu:diva-122978 (URN)10.1093/rpd/ncv461 (DOI)000383492100063 ()26567322 (PubMedID)
Funder
Swedish Cancer Society, CAN 2012/764Swedish Cancer Society, CAN 2014/691
Note

Funding agencies: Swedish Cancer Foundation [CAN 2012/764, CAN 2014/691]; Medical Faculty, Linkoping University; ALF Grants, Region Ostergotland [LiO-438731]

Available from: 2015-12-01 Created: 2015-12-01 Last updated: 2025-02-09
Örtenberg, A., Magnusson, M., Sandborg, M., Alm Carlsson, G. & Malusek, A. (2016). PARALLELISATION OF THE MODEL-BASED ITERATIVE RECONSTRUCTION ALGORITHM DIRA. Radiation Protection Dosimetry, 169(1-4), 405-409
Open this publication in new window or tab >>PARALLELISATION OF THE MODEL-BASED ITERATIVE RECONSTRUCTION ALGORITHM DIRA
Show others...
2016 (English)In: Radiation Protection Dosimetry, ISSN 0144-8420, E-ISSN 1742-3406, Vol. 169, no 1-4, p. 405-409Article in journal (Refereed) Published
Abstract [en]

New paradigms for parallel programming have been devised to simplify software development on multi-core processors and many-core graphical processing units (GPU). Despite their obvious benefits, the parallelisation of existing computer programs is not an easy task. In this work, the use of the Open Multiprocessing (OpenMP) and Open Computing Language (OpenCL) frameworks is considered for the parallelisation of the model-based iterative reconstruction algorithm DIRA with the aim to significantly shorten the code’s execution time. Selected routines were parallelised using OpenMP and OpenCL libraries; some routines were converted from MATLAB to C and optimised. Parallelisation of the code with the OpenMP was easy and resulted in an overall speedup of 15 on a 16-core computer. Parallelisation with OpenCL was more difficult owing to differences between the central processing unit and GPU architectures. The resulting speedup was substantially lower than the theoretical peak performance of the GPU; the cause was explained.

Place, publisher, year, edition, pages
Oxford university press: , 2016
National Category
Computer graphics and computer vision
Identifiers
urn:nbn:se:liu:diva-123009 (URN)10.1093/rpd/ncv430 (DOI)000383492100064 ()26454270 (PubMedID)
Funder
Swedish Cancer Society, CAN 2012/764Swedish Cancer Society, CAN 2014/691
Note

Funding agencies: Swedish Cancer Foundation [CAN 2012/764, CAN 2014/691]

Available from: 2015-12-01 Created: 2015-12-01 Last updated: 2025-02-07
Malusek, A., Magnusson, M., Sandborg, M., Westin, R. & Alm Carlsson, G. (2014). Prostate tissue decomposition via DECT using the modelbased iterative image reconstruction algorithm DIRA. In: Bruce R. Whiting; Christoph Hoeschen; Despina Kontos (Ed.), Medical Imaging 2014: Physics of Medical Imaging. Paper presented at Medical Imaging 2014 - Physics of Medical Imaging, San Diego, California, United States, 17–20 February 2014 (pp. Art.nr. 90333H). SPIE - International Society for Optical Engineering, 9033(90333H)
Open this publication in new window or tab >>Prostate tissue decomposition via DECT using the modelbased iterative image reconstruction algorithm DIRA
Show others...
2014 (English)In: Medical Imaging 2014: Physics of Medical Imaging / [ed] Bruce R. Whiting; Christoph Hoeschen; Despina Kontos, SPIE - International Society for Optical Engineering, 2014, Vol. 9033, no 90333H, p. Art.nr. 90333H-Conference paper, Published paper (Refereed)
Abstract [en]

Better knowledge of elemental composition of patient tissues may improve the accuracy of absorbed dose delivery in brachytherapy. Deficiencies of water-based protocols have been recognized and work is ongoing to implement patient-specific radiation treatment protocols. A model based iterative image reconstruction algorithm DIRA has been developed by the authors to automatically decompose patient tissues to two or three base components via dual-energy computed tomography. Performance of an updated version of DIRA was evaluated for the determination of prostate calcification. A computer simulation using an anthropomorphic phantom showed that the mass fraction of calcium in the prostate tissue was determined with accuracy better than 9%. The calculated mass fraction was little affected by the choice of the material triplet for the surrounding soft tissue. Relative differences between true and approximated values of linear attenuation coefficient and mass energy absorption coefficient for the prostate tissue were less than 6% for photon energies from 1 keV to 2 MeV. The results indicate that DIRA has the potential to improve the accuracy of dose delivery in brachytherapy despite the fact that base material triplets only approximate surrounding soft tissues.

Place, publisher, year, edition, pages
SPIE - International Society for Optical Engineering, 2014
Series
Progress in Biomedical Optics and Imaging, ISSN 1605-7422 ; Vol. 9033
Keywords
Dual energy computed tomography, model based iterative reconstruction algorithm, brachytherapy, prostate calcification
National Category
Clinical Medicine
Identifiers
urn:nbn:se:liu:diva-107506 (URN)10.1117/12.2043445 (DOI)000338775800120 ()2-s2.0-84901613219 (Scopus ID)
Conference
Medical Imaging 2014 - Physics of Medical Imaging, San Diego, California, United States, 17–20 February 2014
Available from: 2014-06-13 Created: 2014-06-13 Last updated: 2015-08-20Bibliographically approved
Malusek, A., Karlsson, M., Magnusson, M. & Alm Carlsson, G. (2013). The potential of dual-energy computed tomography for quantitative decomposition of soft tissues to water, protein and lipid in brachytherapy. Physics in Medicine and Biology, 58(4), 771-785
Open this publication in new window or tab >>The potential of dual-energy computed tomography for quantitative decomposition of soft tissues to water, protein and lipid in brachytherapy
2013 (English)In: Physics in Medicine and Biology, ISSN 0031-9155, E-ISSN 1361-6560, Vol. 58, no 4, p. 771-785Article in journal (Refereed) Published
Abstract [en]

Dosimetric accuracy of radiation treatment planning in brachytherapy depends on knowledge of tissue composition. It has been speculated that soft tissues can be decomposed to water, lipid and protein. The aim of our work is to evaluate the accuracy of such tissue decomposition. Selected abdominal soft tissues, whose average elemental compositions were taken from literature, were decomposed using dual energy computed tomography to water, lipid and protein via the three-material decomposition method. The quality of the decomposition was assessed using relative differences between (i) mass energy absorption and (ii) mass energy attenuation coefficients of the analyzed and approximated tissues. It was found that the relative differences were less than 2% for photon energies larger than 10 keV. The differences were notably smaller than the ones for water as the transport and dose scoring medium. The choice of the water, protein and lipid triplet resulted in negative elemental mass fractions for some analyzed tissues. As negative elemental mass fractions cannot be used in general purpose particle transport computer codes using the Monte Carlo method, other triplets should be used for the decomposition. These triplets may further improve the accuracy of the approximation as the differences were mainly caused by the lack of high-Z materials in the water, protein and lipid triplet.

Place, publisher, year, edition, pages
Institute of Physics, 2013
National Category
Medical and Health Sciences
Identifiers
urn:nbn:se:liu:diva-89734 (URN)10.1088/0031-9155/58/4/771 (DOI)000314396800004 ()
Note

Funding Agencies|Swedish Cancer Society (Cancerfonden)|100 512|

Available from: 2013-03-05 Created: 2013-03-05 Last updated: 2017-12-06
Magnusson, M., Dahlqvist Leinhard, O., van Ettinger-Veenstra, H. & Lundberg, P. (2012). FMRI Using 3D PRESTO-CAN - A Novel Method Based on Golden Angle Hybrid Radial-Cartesian Sampling of K-Space. Paper presented at ISMRM, Melbourne, Australia, 5-11 May, 2012.
Open this publication in new window or tab >>FMRI Using 3D PRESTO-CAN - A Novel Method Based on Golden Angle Hybrid Radial-Cartesian Sampling of K-Space
2012 (English)Conference paper, Published paper (Other academic)
National Category
Medical and Health Sciences
Identifiers
urn:nbn:se:liu:diva-78783 (URN)
Conference
ISMRM, Melbourne, Australia, 5-11 May, 2012
Available from: 2012-06-20 Created: 2012-06-20 Last updated: 2019-06-14
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-9072-2204

Search in DiVA

Show all publications