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

Direct link
BETA
Malmberg, Filip
Publications (10 of 51) Show all publications
Ayyalasomayajula, K. R., Malmberg, F. & Brun, A. (2019). PDNet: Semantic segmentation integrated with a primal-dual network for document binarization. Pattern Recognition Letters
Open this publication in new window or tab >>PDNet: Semantic segmentation integrated with a primal-dual network for document binarization
2019 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344Article in journal (Refereed) Epub ahead of print
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-366933 (URN)10.1016/j.patrec.2018.05.011 (DOI)
Funder
Swedish Research Council, 2012-5743Riksbankens Jubileumsfond, NHS14-2068:1
Available from: 2018-05-16 Created: 2018-11-27 Last updated: 2018-12-18Bibliographically approved
Sandberg Melin, C., Malmberg, F. & Söderberg, P. G. (2018). A strategy for OCT estimation of the optic nerve head pigment epithelium central limit-inner limit of the retina minimal distance, PIMD-2π. Acta Ophthalmologica Scandinavica, 96
Open this publication in new window or tab >>A strategy for OCT estimation of the optic nerve head pigment epithelium central limit-inner limit of the retina minimal distance, PIMD-2π
2018 (English)In: Acta Ophthalmologica Scandinavica, ISSN 1395-3907, E-ISSN 1600-0420, Vol. 96Article in journal (Refereed) Epub ahead of print
National Category
Ophthalmology Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-362723 (URN)10.1111/aos.13908 (DOI)
Available from: 2018-09-10 Created: 2018-10-09 Last updated: 2018-10-10Bibliographically approved
Blache, L., Nysjö, F., Malmberg, F., Thor, A., Rodriguez-Lorenzo, A. & Nyström, I. (2018). SoftCut: A Virtual Planning Tool for Soft Tissue Resection on CT Images. In: Mark Nixon, Sasan Mahmoodi, and Reyer Zwiggelaar (Ed.), Medical Image Understanding and Analysis: . Paper presented at 22nd Medical Image Understanding and Analysis (MIUA) 2018 (pp. 299-310). Cham: Springer, 894
Open this publication in new window or tab >>SoftCut: A Virtual Planning Tool for Soft Tissue Resection on CT Images
Show others...
2018 (English)In: Medical Image Understanding and Analysis / [ed] Mark Nixon, Sasan Mahmoodi, and Reyer Zwiggelaar, Cham: Springer, 2018, Vol. 894, p. 299-310Conference paper, Published paper (Refereed)
Abstract [en]

With the increasing use of three-dimensional (3D) models and Computer Aided Design (CAD) in the medical domain, virtual surgical planning is now frequently used. Most of the current solutions focus on bone surgical operations. However, for head and neck oncologic resection, soft tissue ablation and reconstruction are common operations. In this paper, we propose a method to provide a fast and efficient estimation of shape and dimensions of soft tissue resections. Our approach takes advantage of a simple sketch-based interface which allows the user to paint the contour of the resection on a patient specific 3D model reconstructed from a computed tomography (CT) scan. The volume is then virtually cut and carved following this pattern. From the outline of the resection defined on the skin surface as a closed curve, we can identify which areas of the skin are inside or outside this shape. We then use distance transforms to identify the soft tissue voxels which are closer from the inside of this shape. Thus, we can propagate the shape of the resection inside the soft tissue layers of the volume. We demonstrate the usefulness of the method on patient specific CT data.

Place, publisher, year, edition, pages
Cham: Springer, 2018
Series
Communications in Computer and Information Science
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-364351 (URN)10.1007/978-3-319-95921-4_28 (DOI)978-3-319-95920-7 (ISBN)
Conference
22nd Medical Image Understanding and Analysis (MIUA) 2018
Available from: 2018-10-25 Created: 2018-10-25 Last updated: 2018-10-25
Malmberg, F. & Strand, R. (2018). When Can lp-norm Objective Functions Be Minimized via Graph Cuts?. In: Barneva R., Brimkov V., Tavares J. (Ed.), Combinatorial Image Analysis: . Paper presented at International Workshop on Combinatorial Image Analysis (pp. 112-117). Springer
Open this publication in new window or tab >>When Can lp-norm Objective Functions Be Minimized via Graph Cuts?
2018 (English)In: Combinatorial Image Analysis / [ed] Barneva R., Brimkov V., Tavares J., Springer, 2018, p. 112-117Conference paper, Published paper (Refereed)
Abstract [en]

Techniques based on minimal graph cuts have become a standard tool for solving combinatorial optimization problems arising in image processing and computer vision applications. These techniques can be used to minimize objective functions written as the sum of a set of unary and pairwise terms, provided that the objective function is sub-modular. This can be interpreted as minimizing the l1-norm of the vector containing all pairwise and unary terms. By raising each term to a power p, the same technique can also be used to minimize the lp-norm of the vector. Unfortunately, the submodularity of an l1-norm objective function does not guarantee the submodularity of the corresponding lp-norm objective function. The contribution of this paper is to provide useful conditions under which an lp-norm objective function is submodular for all p>= 1, thereby identifying a large class of lp-norm objective functions that can be minimized via minimal graph cuts.

Techniques based on minimal graph cuts have become a standard tool for solving combinatorial optimization problems arising in image processing and computer vision applications. These techniques can be used to minimize objective functions written as the sum of a set of unary and pairwise terms, provided that the objective function is submodular. This can be interpreted as minimizing the l1l1-norm of the vector containing all pairwise and unary terms. By raising each term to a power p, the same technique can also be used to minimize the lplp-norm of the vector. Unfortunately, the submodularity of an l1l1-norm objective function does not guarantee the submodularity of the corresponding lplp-norm objective function. The contribution of this paper is to provide useful conditions under which an lplp-norm objective function is submodular for all p≥1p≥1, thereby identifying a large class of lplp-norm objective functions that can be minimized via minimal graph cuts.

Place, publisher, year, edition, pages
Springer, 2018
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349
Keywords
Minimal graph cuts, lp -norm, Submodularity
National Category
Discrete Mathematics Computer Sciences
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-366961 (URN)10.1007/978-3-030-05288-1_9 (DOI)978-3-030-05287-4 (ISBN)
Conference
International Workshop on Combinatorial Image Analysis
Available from: 2018-11-27 Created: 2018-11-27 Last updated: 2018-11-27
Strand, R., Malmberg, F., Johansson, L., Lind, L., Sundbom, M., Ahlström, H. & Kullberg, J. (2017). A concept for holistic whole body MRI data analysis, Imiomics. PLoS ONE, 12(2), Article ID e0169966.
Open this publication in new window or tab >>A concept for holistic whole body MRI data analysis, Imiomics
Show others...
2017 (English)In: PLoS ONE, ISSN 1932-6203, E-ISSN 1932-6203, Vol. 12, no 2, article id e0169966Article in journal (Refereed) Published
Abstract [en]

Purpose: To present and evaluate a whole-body image analysis concept, Imiomics (imaging omics) and an image registration method that enables Imiomics analyses by deforming all image data to a common coordinate system, so that the information in each voxel can be compared between persons or within a person over time and integrated with non-imaging data.

Methods: The presented image registration method utilizes relative elasticity constraints of different tissue obtained from whole-body water-fat MRI. The registration method is evaluated by inverse consistency and Dice coefficients and the Imiomics concept is evaluated by example analyses of importance for metabolic research using non-imaging parameters where we know what to expect. The example analyses include whole body imaging atlas creation, anomaly detection, and cross-sectional and longitudinal analysis.

Results: The image registration method evaluation on 128 subjects shows low inverse consistency errors and high Dice coefficients. Also, the statistical atlas with fat content intensity values shows low standard deviation values, indicating successful deformations to the common coordinate system. The example analyses show expected associations and correlations which agree with explicit measurements, and thereby illustrate the usefulness of the proposed Imiomics concept.

Conclusions: The registration method is well-suited for Imiomics analyses, which enable analyses of relationships to non-imaging data, e.g. clinical data, in new types of holistic targeted and untargeted big-data analysis.

National Category
Radiology, Nuclear Medicine and Medical Imaging
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-316830 (URN)10.1371/journal.pone.0169966 (DOI)000395934400002 ()28241015 (PubMedID)
Available from: 2017-02-27 Created: 2017-03-07 Last updated: 2017-11-29Bibliographically approved
Nyström, I., Nysjö, J., Thor, A. & Malmberg, F. (2017). BoneSplit – A 3D painting tool for interactive bone segmentation in CT images. In: Pattern Recognition and Information Processing: PRIP 2016. Paper presented at PRIP 2016, October 3–5, Minsk, Belarus (pp. 3-13). Springer
Open this publication in new window or tab >>BoneSplit – A 3D painting tool for interactive bone segmentation in CT images
2017 (English)In: Pattern Recognition and Information Processing: PRIP 2016, Springer, 2017, p. 3-13Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2017
Series
Communications in Computer and Information Science ; 673
National Category
Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-317762 (URN)10.1007/978-3-319-54220-1_1 (DOI)978-3-319-54219-5 (ISBN)
Conference
PRIP 2016, October 3–5, Minsk, Belarus
Available from: 2017-02-17 Created: 2017-03-17 Last updated: 2017-03-17Bibliographically approved
Malmberg, F., Luengo Hendriks, C. L. & Strand, R. (2017). Exact Evaluation of Targeted Stochastic Watershed Cuts. Discrete Applied Mathematics, 216(2), 449-460
Open this publication in new window or tab >>Exact Evaluation of Targeted Stochastic Watershed Cuts
2017 (English)In: Discrete Applied Mathematics, ISSN 0166-218X, E-ISSN 1872-6771, Vol. 216, no 2, p. 449-460Article in journal (Refereed) Published
Abstract [en]

Seeded segmentation with minimum spanning forests, also known as segmentation by watershed cuts, is a powerful method for supervised image segmentation. Given that correct segmentation labels are provided for a small set of image elements, called seeds, the watershed cut method completes the labeling for all image elements so that the boundaries between different labels are optimally aligned with salient edges in the image. Here, a randomized version of watershed segmentation, the targeted stochastic watershed, is proposed for performing multi-label targeted image segmentation with stochastic seed input. The input to the algorithm is a set of probability density functions (PDFs), one for each segmentation label, defined over the pixels of the image. For each pixel, we calculate the probability that the pixel is assigned a given segmentation label in seeded watershed segmentation with seeds drawn from the input PDFs. We propose an efficient algorithm (quasi-linear with respect to the number of image elements) for calculating the desired probabilities exactly.

Place, publisher, year, edition, pages
Elsevier, 2017
Keywords
Image segmentation, Stochastic watershed, Watershed cut, Minimum spanning forest
National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-333808 (URN)10.1016/j.dam.2016.01.006 (DOI)000390504100011 ()
Available from: 2017-11-17 Created: 2017-11-17 Last updated: 2018-09-04Bibliographically approved
Söderberg, P. G., Malmberg, F. & Sandberg Melin, C. (2017). Further analysis of clinical feasibility of OCT-based glaucoma diagnosis with Pigment epithelium central limit–Inner limit of the retina Minimal Distance (PIMD). In: Ophthalmic Technologies XXVII: . Bellingham, WA: SPIE - International Society for Optical Engineering, Article ID 100450R.
Open this publication in new window or tab >>Further analysis of clinical feasibility of OCT-based glaucoma diagnosis with Pigment epithelium central limit–Inner limit of the retina Minimal Distance (PIMD)
2017 (English)In: Ophthalmic Technologies XXVII, Bellingham, WA: SPIE - International Society for Optical Engineering, 2017, article id 100450RConference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Bellingham, WA: SPIE - International Society for Optical Engineering, 2017
Series
Proc. SPIE ; 10045
National Category
Ophthalmology Medical Image Processing
Research subject
Computerized Image Processing
Identifiers
urn:nbn:se:uu:diva-341869 (URN)10.1117/12.2260139 (DOI)000405820700021 ()978-1-5106-0531-2 (ISBN)
Available from: 2017-02-10 Created: 2018-02-16 Last updated: 2018-03-03Bibliographically approved
Ahlström, H., Ekström, S., Sjöholm, T., Strand, R., Kullberg, J., Johansson, E., . . . Malmberg, F. (2017). Registration-based automated lesion detection and therapy evaluation of tumors in whole body PET-MR images. Paper presented at 42nd European-Society-for-Medical-Oncology Congress (ESMO), SEP 08-12, 2017, Madrid, SPAIN. Annals of Oncology, 28(S5), Article ID 78P.
Open this publication in new window or tab >>Registration-based automated lesion detection and therapy evaluation of tumors in whole body PET-MR images
Show others...
2017 (English)In: Annals of Oncology, ISSN 0923-7534, E-ISSN 1569-8041, Vol. 28, no S5, article id 78PArticle in journal, Meeting abstract (Other academic) Published
National Category
Radiology, Nuclear Medicine and Medical Imaging Cancer and Oncology
Identifiers
urn:nbn:se:uu:diva-346976 (URN)000411324000073 ()
Conference
42nd European-Society-for-Medical-Oncology Congress (ESMO), SEP 08-12, 2017, Madrid, SPAIN
Available from: 2018-03-26 Created: 2018-03-26 Last updated: 2018-03-26Bibliographically approved
Malmberg, F., Nordenskjöld, R., Strand, R. & Kullberg, J. (2017). SmartPaint: a tool for interactive segmentation of medical volume images. Computer Methods In Biomechanics And Biomedical Engeineering-Imaging And Visualization, 5(1), 36-44
Open this publication in new window or tab >>SmartPaint: a tool for interactive segmentation of medical volume images
2017 (English)In: Computer Methods In Biomechanics And Biomedical Engeineering-Imaging And Visualization, ISSN 2168-1163, Vol. 5, no 1, p. 36-44Article in journal (Refereed) Published
Abstract [en]

We present SmartPaint, a general-purpose method and software for interactive segmentation of medical volume images. SmartPaint uses a novel paint-brush interaction paradigm, where the user segments objects in the image by 'sweeping' over them with the mouse cursor. The key feature of SmartPaint is that the painting tools adapt to the image content, selectively sticking to objects of interest while avoiding other structures. This behaviour is achieved by modulating the effect of the tools by both the Euclidean distance and the range distance (difference in image intensity values) from the mouse cursor. We evaluate SmartPaint on three publicly available medical image datasets, covering different image modalities and segmentation targets. The results show that, with a limited user effort, SmartPaint can produce segmentations whose accuracy is comparable to both the state-of-the-art automatic segmentation methods and manual delineations produced by expert users. The SmartPaint software is freely available, and can be downloaded from the authors' web page (http://www.cb.uu.se/similar to filip/SmartPaint/).

Place, publisher, year, edition, pages
TAYLOR & FRANCIS LTD, 2017
Keywords
image segmentation, medical imaging, interactive segmentation
National Category
Biomaterials Science
Identifiers
urn:nbn:se:uu:diva-319143 (URN)10.1080/21681163.2014.960535 (DOI)000396688800005 ()
Available from: 2017-03-31 Created: 2017-03-31 Last updated: 2018-05-14Bibliographically approved
Organisations

Search in DiVA

Show all publications