| 1. |
- Andersson, Axel
(author)
-
Computational Methods for Image-Based Spatial Transcriptomics
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- Why does cancer develop, spread, grow, and lead to mortality? To answer these questions, one must study the fundamental building blocks of all living organisms — cells. Like a well-calibrated manufacturing unit, cells follow precise instructions by gene expression to initiate the synthesis of proteins, the workforces that drive all living biochemical processes.Recently, researchers have developed techniques for imaging the expression of hundreds of unique genes within tissue samples. This information is extremely valuable for understanding the cellular activities behind cancer-related diseases. These methods, collectively known as image-based spatial transcriptomics (IST) techniques, use fluorescence microscopy to combinatorically label mRNA species (corresponding to expressed genes) in tissue samples. Here, automatic image analysis is required to locate fluorescence signals and decode the combinatorial code. This process results in large quantities of points, marking the location of expressed genes. These new data formats pose several challenges regarding visualization and automated analysis.This thesis presents several computational methods and applications related to data generated from IST methods. Key contributions include: (i) A decoding method that jointly optimizes the detection and decoding of signals, particularly beneficial in scenarios with low signal-to-noise ratios or densely packed signals; (ii) a computational method for automatically delineating regions with similar gene compositions — efficient, interactive, and scalable for exploring patterns across different scales; (iii) a software enabling interactive visualization of millions of gene markers atop Terapixel-sized images (TissUUmaps); (iv) a tool utilizing signed-graph partitioning for the automatic identification of cells, independent of the complementary nuclear stain; (v) A fast and analytical expression for a score that quantifies co-localization between spatial points (such as located genes); (vi) a demonstration that gene expression markers can train deep-learning models to classify tissue morphology.In the final contribution (vii), an IST technique features in a clinical study to spatially map the molecular diversity within tumors from patients with colorectal liver metastases, specifically those exhibiting a desmoplastic growth pattern. The study unveils novel molecular patterns characterizing cellular diversity in the transitional region between healthy liver tissue and the tumor. While a direct answer to the initial questions remains elusive, this study sheds illuminating insights into the growth dynamics of colorectal cancer liver metastases, bringing us closer to understanding the journey from development to mortality in cancer.
|
|
| 2. |
- Arvidsson, Ida, et al.
(author)
-
Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer’s disease in patients with mild cognitive symptoms
- 2024
-
In: Alzheimer's Research and Therapy. - 1758-9193. ; 16:1
-
Journal article (peer-reviewed)abstract
- Background: Predicting future Alzheimer’s disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods: A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. Results: In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R2 = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R2 = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R2 = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R2 = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated. Conclusions: The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
|
|
| 3. |
- Broms, Camilla, et al.
(author)
-
Combined analysis of satellite and ground data for winter wheat yield forecasting
- 2023
-
In: Smart Agricultural Technology. - : Elsevier BV. - 2772-3755. ; 3
-
Journal article (peer-reviewed)abstract
- We built machine learning and image analysis tools in order to forecast winter wheat yield based on a rich multi dimensional tensor of agricultural information spanning different scales. This information consists of satellite multi-band images, local soil samples obtained from national databases, local weather as well as field data from 23 farms cultivating winter wheat in southern Sweden. This is inherently a large multi-scale problem due to the large temporal and spatial variation of the input data. We aggregate the data on spatially averaged features over grids which temporally span a seasonal timeline from seeding to harvest. Data cleaning is performed through interpolation for satellite images due to cloud obstructions. Furthermore data is heavily imbalanced since the amount of satellite information far exceeds that of the ground data. Data variance therefore can be an issue which we counter by using a decision tree approach. We find that the Light Gradient Boosting decision tree trained on 262 input features is able to predict winter wheat yield with 82% accuracy. Subsequently we employ game theory in order to better understand the relational importance of specific input features towards forecasting yield. Specifically we find that some of the most important features towards the resulting predictions are the percent clay and magnesium in the soil. Similarly the most important features from the satellite data are: a) the NORM index (Euclidean distance of all bands) computed in the second week of April, b) the NORM index computed in the middle of May as well as c) the second spectral band from the last week of June.
|
|
| 4. |
- Ede, Jacob, et al.
(author)
-
Retrograde cerebral perfusion reduces embolic and watershed lesions after acute type a aortic dissection repair with deep hypothermic circulatory arrest
- 2024
-
In: Journal of Cardiothoracic Surgery. - : BioMed Central (BMC). - 1749-8090. ; 19:1
-
Journal article (peer-reviewed)abstract
- Background: To assess whether retrograde cerebral perfusion reduces neurological injury and mortality in patients undergoing surgery for acute type A aortic dissection.Methods: Single-center, retrospective, observational study including all patients undergoing acute type A aortic dissection repair with deep hypothermic circulatory arrest between January 1998 and December 2022 with or without the adjunct of retrograde cerebral perfusion. 515 patients were included: 257 patients with hypothermic circulatory arrest only and 258 patients with hypothermic circulatory arrest and retrograde cerebral perfusion. The primary endpoints were clinical neurological injury, embolic lesions, and watershed lesions. Multivariable logistic regression was performed to identify independent predictors of the primary outcomes. Survival analysis was performed using Kaplan-Meier estimates.Results: Clinical neurological injury and embolic lesions were less frequent in patients with retrograde cerebral perfusion (20.2% vs. 28.4%, p = 0.041 and 13.7% vs. 23.4%, p = 0.010, respectively), but there was no significant difference in the occurrence of watershed lesions (3.0% vs. 6.1%, p = 0.156). However, after multivariable logistic regression, retrograde cerebral perfusion was associated with a significant reduction of clinical neurological injury (OR: 0.60; 95% CI 0.36–0.995, p = 0.049), embolic lesions (OR: 0.55; 95% CI 0.31–0.97, p = 0.041), and watershed lesions (OR: 0.25; 95%CI 0.07–0.80, p = 0.027). There was no significant difference in 30-day mortality (12.8% vs. 11.7%, p = ns) or long-term survival between groups.Conclusion: In this study, we showed that the addition of retrograde cerebral perfusion during hypothermic circulatory arrest in the setting of acute type A aortic dissection repair reduced the risk of clinical neurological injury, embolic lesions, and watershed lesions.
|
|
| 5. |
- Hansson, Jonas, et al.
(author)
-
Next generation relay autotuners—analysis and implementation
- 2021
-
In: Proceedings of the 5th IEEE Conference on Control Technologies and Applications (CCTA) 2021. ; , s. 1075-1982
-
Conference paper (peer-reviewed)abstract
- In order to produce models for automatic controller tuning, this paper proposes a method that combines a short experiment with a novel scheme for approximating processes using low-order time-delayed models. The method produces models aimed to tune PI and PID controllers, but they could also be used for other model-dependent controllers like MPC. The proposed method has been evaluated in simulations on benchmark processes. It has also been implemented in an industrial controller and tested experimentally on a water-tank process. It is shown that our method is successful in estimating models for a variety of processes such as lag-dominated, delay-dominated, balanced, and integrating processes. We also demonstrate that the experiment time is both shorter and more predictable than currently used autotuners.
|
|
| 6. |
- Lundh, Magnus, et al.
(author)
-
Model optimization for autotuners in industrial control systems
- 2021
-
In: Proceedings of the 26th International Conference on Emerging Technologies and Factory Automation (ETFA). - 9781728129891 ; , s. 1-4
-
Conference paper (peer-reviewed)abstract
- Automatic tuning of PID controllers using relay feedback experiments has received attention on and off since it was first proposed and industrially implemented in a control system in the 1980s. While optimal experiment design and modern system identification easily outperform the original automatic tuner, they rely on computational resources that are not always available in industrial control systems. Here we present a combination of experiment and subsequent output-error identification of continuoustime first-order time-delayed (FOTD) system models, that requires very little in terms of computations and memory. The method has been extensively evaluated in simulation, and a prototype has been implemented for the ABB AC 800M controller family.
|
|
| 7. |
- Simoni, Luca, et al.
(author)
-
Inclusion of the dwell time effect in the LuGre friction model
- 2020
-
In: Mechatronics. - : Elsevier BV. - 0957-4158. ; 66
-
Journal article (peer-reviewed)abstract
- The Dahl friction model is a simple dynamic model for friction obtained by adding dynamics to the stress strain curve. The model captures many aspects of friction and has been used for simulation for a long time. A drawback with the model is that it does not display the stick-slip effect. The LuGre friction model extends the Dahl model to capture the stick-slip motion but is does not capture the fact that friction increases between two surfaces in contact. In this paper we extend the LuGre model to include the effects of dwell time. The model is verified with experiments.
|
|
| 8. |
- Svensson, Måns, et al.
(author)
-
Näthat och demokratiskt deltagande – en kunskapsöversikt
- 2021
-
Reports (other academic/artistic)abstract
- Rätten att uttrycka åsikter, att kritisera och att ifrågasätta är en del av enlevande demokrati. Ett demokratiskt samhälle måste vara öppet för olikaröster och ge alla möjlighet att komma till tals. Demokratin är beroendeav att människor deltar och engagerar sig i samhällsfrågor. Med rättentill yttrandefrihet kommer också ett ansvar. Var och en bör skydda, värnaoch bevara yttrandefriheten genom att respektera andra och bidra till ensamhällsdebatt fri från hot och hat. Tystas människor tystnar demokratin.Den digitala utvecklingen gör det möjligt för fler att göra sin röst hörd. Det ärpositivt men för också med sig utmaningar. Att föra fram och sprida hot ochhat har blivit enklare. Uttalanden kan få snabb spridning i sociala medier ochpå så sätt få större genomslagskraft i dag än tidigare. Det kan missbrukas avpersoner som inte vill bevara det demokratiska samhället.Personer som engagerar sig i samhällsfrågor är särskilt utsatta för hotoch hat. Det gäller till exempel förtroendevalda, journalister, konstnärer,opinionsbildare, forskare och representanter för det civila samhället. Utsatthetkan också vara kopplat till exempelvis en persons kön, könsidentitet, hudfärg,sexuella läggning eller ålder. När kvinnor och hbtqi-personer får hot och hatriktat mot sig har det ofta att göra med kön och sexualitet.På uppdrag av Brottsoffermyndigheten har forskare vid Lunds universitetoch Högskolan i Halmstad genomfört en enkätundersökning som visadeatt mer än hälften av de tillfrågade har känt sig kränkta av sådant som andraskriver om dem på nätet. Särskilt utsatta är unga och personer med utländskbakgrund, och följden blir omfattande nivåer av självcensur bland dessagrupper. Det innebär att de anpassar hur de uttrycker sig för att undvika hotoch hat, eller helt avstår från att publicera och delta i samhällsdebatten. Detdemokratiska samtalet begränsas och viktiga röster riskerar att tystna.Även denna kunskapsöversikt är ett resultat av samarbetet mellan Brottsoffer- myndigheten, Lunds universitet och Högskolan i Halmstad. Den belyser olika frågor om näthat och demokratiskt deltagande, såsom vilka områden som genererar hot och hat, vilka samhälls- och yrkesgrupper som är särskilt utsatta och vilka konsekvenser näthat leder till.
|
|
| 9. |
- Åström, Karl Johan
(author)
-
Pioneers in CAS : Harry Nyquist
- 2022
-
In: IEEE Circuits and Systems Magazine. - 1531-636X. ; 22:1, s. 77-78
-
Journal article (peer-reviewed)
|
|
