umu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Löfstedt, Tommy
Alternative names
Publications (10 of 21) Show all publications
Hadj-Selem, F., Löfstedt, T., Dohmatob, E., Frouin, V., Dubois, M., Guillemot, V. & Duchesnay, E. (2018). Continuation of Nesterov's Smoothing for Regression With Structured Sparsity in High-Dimensional Neuroimaging. IEEE Transactions on Medical Imaging, 37(11), 2403-2413
Open this publication in new window or tab >>Continuation of Nesterov's Smoothing for Regression With Structured Sparsity in High-Dimensional Neuroimaging
Show others...
2018 (English)In: IEEE Transactions on Medical Imaging, ISSN 0278-0062, E-ISSN 1558-254X, Vol. 37, no 11, p. 2403-2413Article in journal (Refereed) Published
Abstract [en]

Predictive models can be used on high-dimensional brain images to decode cognitive states or diagnosis/prognosis of a clinical condition/evolution. Spatial regularization through structured sparsity offers new perspectives in this context and reduces the risk of overfitting the model while providing interpretable neuroimaging signatures by forcing the solution to adhere to domain-specific constraints. Total variation (TV) is a promising candidate for structured penalization: it enforces spatial smoothness of the solution while segmenting predictive regions from the background. We consider the problem of minimizing the sum of a smooth convex loss, a non-smooth convex penalty (whose proximal operator is known) and a wide range of possible complex, non-smooth convex structured penalties such as TV or overlapping group Lasso. Existing solvers are either limited in the functions they can minimize or in their practical capacity to scale to high-dimensional imaging data. Nesterov’s smoothing technique can be used to minimize a large number of non-smooth convex structured penalties. However, reasonable precision requires a small smoothing parameter, which slows down the convergence speed to unacceptable levels. To benefit from the versatility of Nesterov’s smoothing technique, we propose a first order continuation algorithm, CONESTA, which automatically generates a sequence of decreasing smoothing parameters. The generated sequence maintains the optimal convergence speed toward any globally desired precision. Our main contributions are: gap to probe the current distance to the global optimum in order to adapt the smoothing parameter and the To propose an expression of the duality convergence speed. This expression is applicable to many penalties and can be used with other solvers than CONESTA. We also propose an expression for the particular smoothing parameter that minimizes the number of iterations required to reach a given precision. Furthermore, we provide a convergence proof and its rate, which is an improvement over classical proximal gradient smoothing methods. We demonstrate on both simulated and high-dimensional structural neuroimaging data that CONESTA significantly outperforms many state-of-the-art solvers in regard to convergence speed and precision.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
neuroimaging, prediction, signature, machine learning, structured sparsity, convex optimization
National Category
Computer Vision and Robotics (Autonomous Systems) Other Mathematics
Research subject
Computerized Image Analysis; Mathematics
Identifiers
urn:nbn:se:umu:diva-152953 (URN)10.1109/TMI.2018.2829802 (DOI)000449113800003 ()29993684 (PubMedID)
Available from: 2018-10-31 Created: 2018-10-31 Last updated: 2018-12-07Bibliographically approved
Garpebring, A., Brynolfsson, P., Kuess, P., Georg, D., Helbich, T. H., Nyholm, T. & Löfstedt, T. (2018). Density Estimation of Grey-Level Co-Occurrence Matrices for Image Texture Analysis. Physics in Medicine and Biology, 63(19), 9-15, Article ID 195017.
Open this publication in new window or tab >>Density Estimation of Grey-Level Co-Occurrence Matrices for Image Texture Analysis
Show others...
2018 (English)In: Physics in Medicine and Biology, ISSN 0031-9155, E-ISSN 1361-6560, Vol. 63, no 19, p. 9-15, article id 195017Article in journal (Refereed) Published
Abstract [en]

The Haralick texture features are common in the image analysis literature, partly because of their simplicity and because their values can be interpreted. It was recently observed that the Haralick texture features are very sensitive to the size of the GLCM that was used to compute them, which led to a new formulation that is invariant to the GLCM size. However, these new features still depend on the sample size used to compute the GLCM, i.e. the size of the input image region-of-interest (ROI).

The purpose of this work was to investigate the performance of density estimation methods for approximating the GLCM and subsequently the corresponding invariant features.

Three density estimation methods were evaluated, namely a piece-wise constant distribution, the Parzen-windows method, and the Gaussian mixture model. The methods were evaluated on 29 different image textures and 20 invariant Haralick texture features as well as a wide range of different ROI sizes.

The results indicate that there are two types of features: those that have a clear minimum error for a particular GLCM size for each ROI size, and those whose error decreases monotonically with increased GLCM size. For the first type of features, the Gaussian mixture model gave the smallest errors, and in particular for small ROI sizes (less than about 20×20).

In conclusion, the Gaussian mixture model is the preferred method for the first type of features (in particular for small ROIs). For the second type of features, simply using a large GLCM size is preferred.

Place, publisher, year, edition, pages
Institute of Physics and Engineering in Medicine, 2018
Keywords
Haralick features, invariant features, GLCM, density estimation, texture analysis, image analysis
National Category
Computer Vision and Robotics (Autonomous Systems) Other Mathematics
Identifiers
urn:nbn:se:umu:diva-152488 (URN)10.1088/1361-6560/aad8ec (DOI)000446205200005 ()30088815 (PubMedID)
Funder
Västerbotten County CouncilVINNOVA
Available from: 2018-10-08 Created: 2018-10-08 Last updated: 2018-10-31Bibliographically approved
Brynolfsson, P., Löfstedt, T., Asklund, T., Nyholm, T. & Garpebring, A. (2018). Gray-level invariant Haralick texture features. Paper presented at 37th Meeting of the European-Society-for-Radiotherapy-and-Oncology (ESTRO), APR 20-24, 2018, Barcelona, SPAIN. Radiotherapy and Oncology, 127, S279-S280
Open this publication in new window or tab >>Gray-level invariant Haralick texture features
Show others...
2018 (English)In: Radiotherapy and Oncology, ISSN 0167-8140, E-ISSN 1879-0887, Vol. 127, p. S279-S280Article in journal, Meeting abstract (Other academic) Published
Place, publisher, year, edition, pages
Elsevier, 2018
National Category
Cancer and Oncology
Identifiers
urn:nbn:se:umu:diva-150493 (URN)10.1016/S0167-8140(18)30837-5 (DOI)000437723401139 ()
Conference
37th Meeting of the European-Society-for-Radiotherapy-and-Oncology (ESTRO), APR 20-24, 2018, Barcelona, SPAIN
Available from: 2018-11-01 Created: 2018-11-01 Last updated: 2018-11-01Bibliographically approved
de Pierrefeu, A., Löfstedt, T., Laidi, C., Hadj-Selem, F., Bourgin, J., Hajek, T., . . . Duchesnay, E. (2018). Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine-learning with structured sparsity. Acta Psychiatrica Scandinavica, 138, 571-580
Open this publication in new window or tab >>Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine-learning with structured sparsity
Show others...
2018 (English)In: Acta Psychiatrica Scandinavica, ISSN 0001-690X, E-ISSN 1600-0447, Vol. 138, p. 571-580Article in journal (Refereed) Published
Abstract [en]

ObjectiveStructural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross‐sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings’ reproducibility.

MethodWe propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross‐site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first‐episode patients.

ResultsMachine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first‐episode psychosis patients (73% accuracy).

ConclusionThese results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.

Place, publisher, year, edition, pages
John Wiley & Sons, 2018
Keywords
classification, schizophrenia, structural MRI, first-episode psychosis, psychoradiology
National Category
Psychiatry Computer Vision and Robotics (Autonomous Systems) Other Mathematics
Research subject
Computerized Image Analysis; Psychiatry
Identifiers
urn:nbn:se:umu:diva-152928 (URN)10.1111/acps.12964 (DOI)000449521200009 ()
Available from: 2018-10-30 Created: 2018-10-30 Last updated: 2018-11-27Bibliographically approved
Garpebring, A. & Tommy, L. (2018). Parameter estimation using weighted total least squares in the two-compartment exchange model. Magnetic Resonance in Medicine, 79(1), 561-567
Open this publication in new window or tab >>Parameter estimation using weighted total least squares in the two-compartment exchange model
2018 (English)In: Magnetic Resonance in Medicine, ISSN 0740-3194, E-ISSN 1522-2594, Vol. 79, no 1, p. 561-567Article in journal (Refereed) Published
Abstract [en]

Purpose

The linear least squares (LLS) estimator provides a fast approach to parameter estimation in the linearized two-compartment exchange model. However, the LLS method may introduce a bias through correlated noise in the system matrix of the model. The purpose of this work is to present a new estimator for the linearized two-compartment exchange model that takes this noise into account.

Method

To account for the noise in the system matrix, we developed an estimator based on the weighted total least squares (WTLS) method. Using simulations, the proposed WTLS estimator was compared, in terms of accuracy and precision, to an LLS estimator and a nonlinear least squares (NLLS) estimator.

Results

The WTLS method improved the accuracy compared to the LLS method to levels comparable to the NLLS method. This improvement was at the expense of increased computational time; however, the WTLS was still faster than the NLLS method. At high signal-to-noise ratio all methods provided similar precisions while inconclusive results were observed at low signal-to-noise ratio.

Conclusion

The proposed method provides improvements in accuracy compared to the LLS method, however, at an increased computational cost. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

Place, publisher, year, edition, pages
John Wiley & Sons, 2018
Keywords
dynamic contrast-enhanced magnetic resonance imaging; parameter estimation, two-compartment exchange model, weighted total least squares
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:umu:diva-135670 (URN)10.1002/mrm.26677 (DOI)000417926300055 ()28349618 (PubMedID)
Available from: 2017-06-02 Created: 2017-06-02 Last updated: 2018-06-09Bibliographically approved
de Pierrefeu, A., Fovet, T., Hadj-Selem, F., Löfstedt, T., Ciuciu, P., Lefebvre, S., . . . Duchesnay, E. (2018). Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity. Human Brain Mapping, 39(4), 1777-1788
Open this publication in new window or tab >>Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity
Show others...
2018 (English)In: Human Brain Mapping, ISSN 1065-9471, E-ISSN 1097-0193, Vol. 39, no 4, p. 1777-1788Article in journal (Refereed) Published
Abstract [en]

Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algorithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification methods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The variation in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of principal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the dataset. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback.

Keywords
hallucinations, machine learning, real-time fMRI, resting-state networks, schizophrenia
National Category
Computer and Information Sciences Medical and Health Sciences
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:umu:diva-145654 (URN)10.1002/hbm.23953 (DOI)000427117300023 ()29341341 (PubMedID)
Available from: 2018-03-13 Created: 2018-03-13 Last updated: 2018-06-09Bibliographically approved
de Pierrefeu, A., Löfstedt, T., Hadj-Selem, F., Dubois, M., Jardri, R., Fovet, T., . . . Duchesnay, E. (2018). Structured Sparse Principal Components Analysis With the TV-Elastic Net Penalty. IEEE Transactions on Medical Imaging, 37(2), 396-407
Open this publication in new window or tab >>Structured Sparse Principal Components Analysis With the TV-Elastic Net Penalty
Show others...
2018 (English)In: IEEE Transactions on Medical Imaging, ISSN 0278-0062, E-ISSN 1558-254X, Vol. 37, no 2, p. 396-407Article in journal (Refereed) Published
Abstract [en]

Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover the dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, PCA’s interpretability remains limited. Indeed, the components produced by PCA are often noisy or exhibit no visually meaningful patterns. Furthermore, the fact that the components are usually non-sparse may also impede interpretation, unless arbitrary thresholding is applied. However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population. Recently, some alternatives to the standard PCA approach, such as sparse PCA (SPCA), have been proposed, their aim being to limit the density of the components. Nonetheless, sparsity alone does not entirely solve the interpretability problem in neuroimaging, since it may yield scattered andunstable components. We hypothesized that the incorporation of prior information regarding the structure of the data may lead to improved relevance and interpretability of brain patterns. We therefore present a simple extension of the popular PCA framework that adds structured sparsity penalties on the loading vectors in order to identify the few stable regions in the brain images that capture most of the variability. Such structured sparsity can be obtained by combining, e.g., l1 and total variation (TV) penalties, where the TV regularization encodes information on the underlying structure of the data. This paper presents the structured SPCA (denoted SPCA-TV) optimization framework and its resolution. We demonstrate SPCA-TV’s effectiveness and versatility on three different data sets. It can be applied to any kind of structured data, such as, e.g., N-dimensional array images or meshes of cortical surfaces. The gains of SPCA-TV over unstructured approaches (such as SPCA and ElasticNet PCA) or structured approach (such as GraphNet PCA) are significant, since SPCA-TV reveals the variability within a data set in the form of intelligible brain patterns that are easier to interpret and more stable across different samples.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
MRI, unsupervised machine learning, PCA, total variation
National Category
Computer and Information Sciences
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:umu:diva-145277 (URN)10.1109/TMI.2017.2749140 (DOI)000424467000006 ()28880163 (PubMedID)
Available from: 2018-02-26 Created: 2018-02-26 Last updated: 2018-06-09Bibliographically approved
Bylund, M., Jonsson, J., Lundman, J., Brynolfsson, P., Garpebring, A., Nyholm, T. & Löfstedt, T. (2018). Using deep learning to generate synthetic CTs for radiotherapy treatment planning. Paper presented at 37th Meeting of the European-Society-for-Radiotherapy-and-Oncology (ESTRO), APR 20-24, 2018, Barcelona, SPAIN. Radiotherapy and Oncology, 127, S283-S283
Open this publication in new window or tab >>Using deep learning to generate synthetic CTs for radiotherapy treatment planning
Show others...
2018 (English)In: Radiotherapy and Oncology, ISSN 0167-8140, E-ISSN 1879-0887, Vol. 127, p. S283-S283Article in journal, Meeting abstract (Other academic) Published
Place, publisher, year, edition, pages
Elsevier, 2018
National Category
Cancer and Oncology
Identifiers
urn:nbn:se:umu:diva-150491 (URN)10.1016/S0167-8140(18)30842-9 (DOI)000437723401144 ()
Conference
37th Meeting of the European-Society-for-Radiotherapy-and-Oncology (ESTRO), APR 20-24, 2018, Barcelona, SPAIN
Available from: 2018-11-01 Created: 2018-11-01 Last updated: 2018-11-01Bibliographically approved
Löfstedt, T., Hadj-Selem, F., Guillemot, V., Philippe, C., Duchesnay, E., Frouin, V. & Tenenhaus, A. (2016). Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis. In: Abdi, H Vinzi, VE Russolillo, G Saporta, G Trinchera, L (Ed.), MULTIPLE FACETS OF PARTIAL LEAST SQUARES AND RELATED METHODS: . Paper presented at 8th Meeting on Partial Least Squares (PLS), MAY 26-28, 2014, Conservatoire Natl Arts Metiers, Paris, FRANCE (pp. 129-139). SPRINGER INT PUBLISHING AG, 173
Open this publication in new window or tab >>Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis
Show others...
2016 (English)In: MULTIPLE FACETS OF PARTIAL LEAST SQUARES AND RELATED METHODS / [ed] Abdi, H Vinzi, VE Russolillo, G Saporta, G Trinchera, L, SPRINGER INT PUBLISHING AG , 2016, Vol. 173, p. 129-139Conference paper, Published paper (Refereed)
Abstract [en]

Regularized Generalized Canonical Correlation Analysis (RGCCA) extends regularized canonical correlation analysis to more than two sets of variables. Sparse GCCA(SGCCA) was recently proposed to address the issue of variable selection. However, the variable selection scheme offered by SGCCA is limited to the covariance (tau = 1) link between blocks. In this paper we go beyond the covariance link by proposing an extension of SGCCA for the full RGCCA model. (tau epsilon [0; 1]). In addition, we also propose an extension of SGCCA that exploits pre-given structural relationships between variables within blocks. Specifically, we propose an algorithm that allows structured and sparsity-inducing penalties to be included in the RGCCA optimization problem.

Place, publisher, year, edition, pages
SPRINGER INT PUBLISHING AG, 2016
Series
Springer Proceedings in Mathematics & Statistics, ISSN 2194-1009 ; 173
Keywords
RGCCA, Variable selection, Structured penalty, Sparse penalty
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:umu:diva-136099 (URN)10.1007/978-3-319-40643-5_10 (DOI)000400840200010 ()978-3-319-40643-5 (ISBN)978-3-319-40641-1 (ISBN)
Conference
8th Meeting on Partial Least Squares (PLS), MAY 26-28, 2014, Conservatoire Natl Arts Metiers, Paris, FRANCE
Available from: 2017-06-13 Created: 2017-06-13 Last updated: 2018-06-09Bibliographically approved
Peolsson, A., Peolsson, M., Jull, G., Löfstedt, T., Trygg, J. & O'Leary, S. (2015). Preliminary evaluation of dorsal muscle activity during resisted cervical extension in patients with longstanding pain and disability following anterior cervical decompression and fusion surgery. Physiotherapy, 101(1), 69-74
Open this publication in new window or tab >>Preliminary evaluation of dorsal muscle activity during resisted cervical extension in patients with longstanding pain and disability following anterior cervical decompression and fusion surgery
Show others...
2015 (English)In: Physiotherapy, ISSN 0031-9406, E-ISSN 1873-1465, Vol. 101, no 1, p. 69-74Article in journal (Refereed) Published
Abstract [en]

Objectives To compare mechanical activity (deformation and deformation rate) of the dorsal neck muscles between individuals with longstanding symptoms after anterior cervical decompression and fusion (ACDF) surgery and healthy controls.

Design Preliminary cross-sectional study.

Setting Neurosurgery clinic.

Participants Ten individuals {mean age 60 [standard deviation (SD) 7.111 who had undergone ACDF surgery 10 to 13 years previously and 10 healthy age- and sex-matched controls.

Main outcomes Mechanical activity of the different layers of dorsal neck muscles, measured at the C4 segment using ultrasonography (speckle tracking analysis) during a standardised, resisted cervical extension task.

Results A significant group x muscle interaction was found for muscle deformation (P<0.03) but not for deformation rate (P>0.79). The ACDF group showed significantly less deformation of the semispinalis capitis muscle during the extension task compared with the control group [mean 3.12 (SD 2.06) and 6.64 (SD 4.17), respectively; mean difference 3.34 (95% confidence interval 0.54 to 7.21)].

Conclusions As the semispinalis capitis muscle is a powerful neck extensor, the finding of altered activation following ACDF surgery lends support to the inclusion of exercise to train neck muscle performance in the management of these patients.

Keywords
Extensor muscles, Neck surgery, Disc disease, Ultrasonography, Exercise
National Category
Physiotherapy
Identifiers
urn:nbn:se:umu:diva-100750 (URN)10.1016/j.physio.2014.04.010 (DOI)000348292800009 ()25066646 (PubMedID)
Available from: 2015-04-26 Created: 2015-03-09 Last updated: 2018-06-07Bibliographically approved
Organisations

Search in DiVA

Show all publications