| 1. |
- Ekström, Magnus, 1966-, et al.
(författare)
-
Estimating density from presence/absence data in clustered populations
- 2021
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- 1. Inventories of plant populations are fundamental in ecological research and monitoring, butsuch surveys are often prone to field assessment errors. Presence/ absence (P/A) samplingmay have advantages over plant cover assessments for reducing such errors. However, thelinking between P/A data and plant density depends on model assumptions for plant spatialdistributions. Previous studies have shown, for example, how that plant density can beestimated under Poisson model assumptions on the plant locations. In this study, newmethods are developed and evaluated for linking P/A data with plant density assuming thatplants occur in clustered spatial patterns.2. New theory was derived for estimating plant density under Neyman–Scott-type cluster models such as the Matérn and Thomas cluster processes. Suggested estimators, correspondingconfidence intervals and a proposed goodness-of-fit test were evaluated in a Monte Carlosimulation study assuming a Matérn cluster process. Furthermore, the estimators were applied to plant data from environmental monitoring in Sweden to demonstrate their empiricalapplication.3. The simulation study showed that our methods work well for large enough sample sizes.The judgment of what is ’large enough’ is often difficult, but simulations indicate that asample size is large enough when the sampling distributions of the parameter estimators aresymmetric or mildly skewed. Bootstrap may be used to check whether this is true. Theempirical results suggest that the derived methodology may be useful for estimating densityof plants such as Leucanthemum vulgare and Scorzonera humilis.4. By developing estimators of plant density from P/A data under realistic model assumptions about plants’ spatial distributions, P/A sampling will become a more useful tool forinventories of plant populations. Our new theory is an important step in this direction.
|
|
| 2. |
- Jonsson, Bertil, et al.
(författare)
-
Development of Whiplash associated Disorders for adult and child occupants in cars launched since the 1980s in different impact directions
- 2011
-
Ingår i: 2011 IRCOBI Conference Proceedings - International Research Council on the Biomechanics of Injury (;Krakow;14 -16 September 2011). - : International Research Council on the Biomechanics of Injury. ; , s. 62-72, s. 62-72
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Studies have shown that crashworthiness of cars addressing fatal and serious injuries has generally improved over time. However, the development regarding injuries leading to medical impairment has not been shown to the same extent. The objective was to investigate the development of Whiplash associated Disorders (WAD) leading to long-term consequences for adult front seat occupants and for children 0-12 years of age in cars introduced at different year intervals and in different impact directions separated for gender. Long-term consequences were defined as occupants with WAD symptoms at least one month and those resulting in medical impairment. The developments were studied for cars divided into intervals according to year of introduction and for frontal, side and rear-end impacts. All adult occupants (35 611) and 76% of all children (973) reporting WAD between 1998 and 2008 were selected. Approximately 2% of the children reporting initial symptoms sustained medical impairment. The corresponding figure for adult occupants was approximately 10%. Between the introduction years 1980-84 and 2000-04 the proportions of adult occupants with medical impairment dropped by approximately 70% (both males and females) in frontal and rear-end crashes, while the reduction in lateral impacts appears to be somewhat lower. For children there is a tendency that the proportion of WAD increases in newer models in frontal collisions. The result indicates that protecting children facing forward deserves more attention from the automotive industry and governmental bodies.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Simkó, Attila, et al.
(författare)
-
Changing the Contrast of Magnetic Resonance Imaging Signals using Deep Learning
- 2021
-
Ingår i: Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR. - : Lübeck University; Hamburg University of Technology. ; , s. 713-727
-
Konferensbidrag (refereegranskat)abstract
- The contrast settings to select before acquiring magnetic resonance imaging (MRI) signal depend heavily on the subsequent tasks. As each contrast highlights different tissues, automated segmentation tools for example might be optimized for a certain contrast. While for radiotherapy, multiple scans of the same region with different contrasts can achieve a better accuracy for delineating tumours and organs at risk. Unfortunately, the optimal contrast for the subsequent automated methods might not be known during the time of signal acquisition, and performing multiple scans with different contrasts increases the total examination time and registering the sequences introduces extra work and potential errors. Building on the recent achievements of deep learning in medical applications, the presented work describes a novel approach for transferring any contrast to any other. The novel model architecture incorporates the signal equation for spin echo sequences, and hence the model inherently learns the unknown quantitative maps for proton density, ?1 and ?2 relaxation times (??, ?1 and ?2, respectively). This grants the model the ability to retrospectively reconstruct spin echo sequences by changing the contrast settings Echo and Repetition Time (?? and ??, respectively). The model learns to identify the contrast of pelvic MR images, therefore no paired data of the same anatomy from different contrasts is required for training. This means that the experiments are easily reproducible with other contrasts or other patient anatomies. Despite the contrast of the input image, the model achieves accurate results for reconstructing signal with contrasts available for evaluation. For the same anatomy, the quantitative maps are consistent for a range of contrasts of input images. Realized in practice, the proposed method would greatly simplify the modern radiotherapy pipeline. The trained model is made public together with a tool for testing the model on example images.
|
|
| 7. |
- Simkó, Attila, et al.
(författare)
-
MRI bias field correction with an implicitly trained CNN
- 2022
-
Ingår i: Proceedings of the 5th international conference on medical imaging with deep learning. - : ML Research Press. ; , s. 1125-1138
-
Konferensbidrag (refereegranskat)abstract
- In magnetic resonance imaging (MRI), bias fields are difficult to correct since they are inherently unknown. They cause intra-volume intensity inhomogeneities which limit the performance of subsequent automatic medical imaging tasks, \eg, tissue-based segmentation. Since the ground truth is unavailable, training a supervised machine learning solution requires approximating the bias fields, which limits the resulting method. We introduce implicit training which sidesteps the inherent lack of data and allows the training of machine learning solutions without ground truth. We describe how training a model implicitly for bias field correction allows using non-medical data for training, achieving a highly generalized model. The implicit approach was compared to a more traditional training based on medical data. Both models were compared to an optimized N4ITK method, with evaluations on six datasets. The implicitly trained model improved the homogeneity of all encountered medical data, and it generalized better for a range of anatomies, than the model trained traditionally. The model achieves a significant speed-up over an optimized N4ITK method—by a factor of 100, and after training, it also requires no parameters to tune. For tasks such as bias field correction - where ground truth is generally not available, but the characteristics of the corruption are known - implicit training promises to be a fruitful alternative for highly generalized solutions.
|
|
| 8. |
- Simkó, Attila, et al.
(författare)
-
Reproducibility of the methods in medical imaging with deep learning
- 2023
-
Ingår i: Medical imaging with deep learning 2023. - : ML Research Press. ; , s. 95-106
-
Konferensbidrag (refereegranskat)abstract
- Concerns about the reproducibility of deep learning research are more prominent than ever, with no clear solution in sight. The Medical Imaging with Deep Learning (MIDL) conference has made advancements in employing empirical rigor with regards to reproducibility by advocating open access, and recently also recommending authors to make their code public—both aspects being adopted by the majority of the conference submissions. We have evaluated all accepted full paper submissions to MIDL between 2018 and 2022 using established, but adjusted guidelines addressing the reproducibility and quality of the public repositories. The evaluations show that publishing repositories and using public datasets are becoming more popular, which helps traceability, but the quality of the repositories shows room for improvement in every aspect. Merely 22% of all submissions contain a repository that was deemed repeatable using our evaluations. From the commonly encountered issues during the evaluations, we propose a set of guidelines for machine learning-related research for medical imaging applications, adjusted specifically for future submissions to MIDL. We presented our results to future MIDL authors who were eager to continue an open discussion on the topic of code reproducibility.
|
|
