| 1. |
- Björkman, Kristoffer, et al.
(author)
-
Clinical course of patients with single large-scale mtDNA deletions and childhood onset anemia
- 2022
-
In: 14th European Paediatric Neurology Society Congress, Glasgow, UK (ISBN 978-3-00-072065-9).
-
Conference paper (other academic/artistic)abstract
- Objective: To add to our knowledge of the clinical spectrum of patients with single large-scale mitochondrial DNA (mtDNA) deletion and childhood onset anemia. Methods: Retrospective collection of clinical data from medical records for patients, both living and deceased, with a single large-scale mtDNA deletion from seven mitochondrial disease centers in five countries. Statistical analysis with descriptive methods and Kaplan-Meier survival analysis. Results: Seventeen patients matching the genetic criterium and with anemia onset before six years of age. Exocrine pancreatic insufficiency was only seen in five patients in this group. Multiple organs were involved in all patients, with the most common non-hematologic ones being skeletal muscle, central nervous system, endocrine, eyes, gastrointestinal system, kidneys, hearing, liver and heart. Psychomotor retardation was seen in ten patients, hearing impairment in nine patients, failure to thrive in eight patients. Eight later developed Kearns-Sayre syndrome. Eleven patients were deceased, with a median age at death of 7.5 years. Conclusions: The classically described phenotype of patients with large-scale mtDNA deletions and early onset anemia is Pearson marrow-pancreas syndrome, characterized by sideroblastic anemia and exocrine pancreas dysfunction. Only a minority of our patients fulfill the original criteria of Pearson syndrome though. Involvement of other organs than the pancreas is more common. The clinical course vary, but multi-system impact is the rule and life-expectancy is low. Early onset anemia in patients with large-scale mtDNA deletions is most frequently not associated with exocrine pancreas dysfunction. Better knowledge of the phenotype is helpful for diagnosis and more accurate prognosis.
|
|
| 2. |
- Björkman, Kristoffer, et al.
(author)
-
Genotype-phenotype correlations in patients with complex I deficiency due to mutations in NDUFS1 and NDUFV1
- 2014
-
In: Euromit 2014, 15-19 juni, Tampere, Finland.
-
Conference paper (other academic/artistic)abstract
- Objectives: To study genotype-phenotype correlations in genes encoding complex I electron input module subunits. Materials and methods: We studied five patients with isolated complex I deficiency, three with NDUFS1 mutations and two with NDUFV1 mutations. A literature review of all reported cases of mutations in the affected genes was performed. Results: The literature review revealed pathological mutations in NDUFS1 for 18 patients in 17 families and correspondingly in NDUFV1 for 26 patients in 19 families. Unpublished clinical data for our five patients were added. Our study showed quite variable clinical courses; death before two years of age was seen in 41% of patients while 18% were alive at seven years. There was a significant difference between the NDUFS1 and NDUFV1 groups for clinical onset and life-span. Mutations in NDUFS1 were linked to a worse clinical course with earlier onset and earlier death. Conclusions: Genotype-phenotype correlations in patients with mutations affecting the genes that encode the electron input module of complex I vary, but patients with NDUFS1 mutation tend to have a worse clinical course than patients with NDUFV1 mutation. Identifying the mutations is of importance for accurate prognostic information and genetic counseling.
|
|
| 3. |
|
|
| 4. |
- Ge, Chenjie, 1991, et al.
(author)
-
Cross-Modality Augmentation of Brain Mr Images Using a Novel Pairwise Generative Adversarial Network for Enhanced Glioma Classification
- 2019
-
In: Proceedings - International Conference on Image Processing, ICIP. - 1522-4880.
-
Conference paper (peer-reviewed)abstract
- © 2019 IEEE. Brain Magnetic Resonance Images (MRIs) are commonly used for tumor diagnosis. Machine learning for brain tumor characterization often uses MRIs from many modalities (e.g., T1-MRI, Enhanced-T1-MRI, T2-MRI and FLAIR). This paper tackles two issues that may impact brain tumor characterization performance from deep learning: insufficiently large training dataset, and incomplete collection of MRIs from different modalities. We propose a novel pairwise generative adversarial network (GAN) architecture for generating synthetic brain MRIs in missing modalities by using existing MRIs in other modalities. By improving the training dataset, we aim to mitigate the overfitting and improve the deep learning performance. Main contributions of the paper include: (a) propose a pairwise generative adversarial network (GAN) for brain image augmentation via cross-modality image generation; (b) propose a training strategy to enhance the glioma classification performance, where GAN-augmented images are used for pre-training, followed by refined-training using real brain MRIs; (c) demonstrate the proposed method through tests and comparisons of glioma classifiers that are trained from mixing real and GAN synthetic data, as well as from real data only. Experiments were conducted on an open TCGA dataset, containing 167 subjects for classifying IDH genotypes (mutation or wild-type). Test results from two experimental settings have both provided supports to the proposed method, where glioma classification performance has consistently improved by using mixed real and augmented data (test accuracy 81.03%, with 2.57% improvement).
|
|
| 5. |
|
|
| 6. |
- Staron, Miroslaw, 1977, et al.
(author)
-
Robust machine learning in critical care - Software engineering and medical perspectives
- 2021
-
In: Proceedings - 2021 IEEE/ACM 1st Workshop on AI Engineering - Software Engineering for AI, WAIN 2021. - : Institute of Electrical and Electronics Engineers Inc.. ; , s. 62-69
-
Conference paper (peer-reviewed)abstract
- Using machine learning in clinical practice poses hard requirements on explainability, reliability, replicability and robustness of these systems. Therefore, developing reliable software for monitoring critically ill patients requires close collaboration between physicians and software engineers. However, these two different disciplines need to find own research perspectives in order to contribute to both the medical and the software engineering domain. In this paper, we address the problem of how to establish a collaboration where software engineering and medicine meets to design robust machine learning systems to be used in patient care. We describe how we designed software systems for monitoring patients under carotid endarterectomy, in particular focusing on the process of knowledge building in the research team. Our results show what to consider when setting up such a collaboration, how it develops over time and what kind of systems can be constructed based on it. We conclude that the main challenge is to find a good research team, where different competences are committed to a common goal.
|
|
| 7. |
- Augustian, Midhumol, et al.
(author)
-
EEG Analysis from Motor Imagery to Control a Forestry Crane
- 2018
-
In: Intelligent Human Systems Integration (IHSI 2018). - Cham : Springer. - 9783319738871 - 9783319738888 ; , s. 281-286
-
Conference paper (peer-reviewed)abstract
- Brain-computer interface (BCI) systems can provide people with ability to communicate and control real world systems using neural activities. Therefore, it makes sense to develop an assistive framework for command and control of a future robotic system which can assist the human robot collaboration. In this paper, we have employed electroencephalographic (EEG) signals recorded by electrodes placed over the scalp. The human-hand movement based motor imagery mentalization is used to collect brain signals over the motor cortex area. The collected µ-wave (8–13 Hz) EEG signals were analyzed with event-related desynchronization/synchronization (ERD/ERS) quantification to extract a threshold between hand grip and release movement and this information can be used to control forestry crane grasping and release functionality. The experiment was performed with four healthy persons to demonstrate the proof-of concept BCI system. From this study, it is demonstrated that the proposed method has potential to assist the manual operation of crane operators performing advanced task with heavy cognitive work load.
|
|
| 8. |
- Salford, Leif, et al.
(author)
-
The mammalian brain in the electromagnetic fields designed by man with special reference to blood-brain barrier function, neuronal damage and possible physical mechanisms
- 2008
-
In: PROGRESS OF THEORETICAL PHYSICS SUPPLEMENT. - 0375-9687. ; :173, s. 283-309
-
Conference paper (peer-reviewed)abstract
- Life oil earth was formed during billions of years, exposed to, and shaped by the original physical forces such as gravitation, cosmic irradiation, atmospheric electric fields and the terrestrial magnetism. The Schumann resonances at 7.4 Hz are all example of oscillations possibly important for life.(1)) The existing organisms are created to function in harmony with these forces. However, in the late 19th century mankind introduced the use of electricity, in the early 20th century long-wave radio and in the 1940-ies short-wave radio. High frequency RF was introduced in the 50-ies as FM and television and during the very last decades, microwaves of the modern communication society spread around the world. Today, however, one third of the world's population is owner of the microwave-producing mobile phones and an even larger number is exposed to the cordless RF emitting systems. To what; extent are all living organisms affected by these, almost everywhere present radio frequency fields? And what will be the effects of many years of continuing exposure? Since 1989 Our group has studied the effects upon the mammalian blood-brain barrier (BBB) in rats by non-thermal radio frequency electromagnetic fields (RF-EMF). These have been shown to cause significantly increased leak-age of the rats' own blood albumin through the BBB of exposed rats, at energy levels of 1W/kg and below, as compared to non-exposed animals in a total series of about two thousand animals.(2)-6)) One remarkable observation is the fact that the lowest energy levels, with whole-body average power densities below 10mW/kg, give rise to the most pronounced albumin leakage. If mobile communication, even at extremely low energy levels, causes the users' own albumin to leak out through the BBB, also other unwanted and toxic molecules in the blood, may leak into the brain tissue and concentrate in and damage the neurons and glial cells of the brain. In later studies we have shown that a 2-h exposure to GSM 915 MHz, at non-thermal SAB-values of 0.2, 2 and 200 mW/kg, gives rise to significant neuronal damage, seen not only 50 days after the exposure 7) but also after 28 days but not after 14 days. Albumin extravasations and uptake into neurons was enhanced after 14 clays, but not after 28.(8)) in our continued research, also the non-thermal effects oil tissue structure and memory function of long-term exposure for 13 months are studied.(9)) We have also performed microarray analysis of brains from rats exposed to short term GSM both at 1,800 MHz and at 900MHz and have found significant effects upon gene expression of membrane associated genes as compared to control animals.(10),11)) Most of our findings support that living organisms are affected by the non-thermal radio frequency fields. Some other Studies agree while others find no effects. The mechanisms by which the EMFs may alter BBB permeability are not Well Understood. At low field strengths, the effects on body temperature are negligible and thus heating effects are not involved. A change in the physicochemical characteristics of membranes has been suggested as a cause.(12)) We have performed experiments to verify a quantum mechanical model for interaction with protein-bound ions. Our results show that controlled frequency and amplitude of ELF EM fields upon spinach plasma vesicles can steer transport over the membrane.(13)) This may be a first proof of a resonance phenomenon where appropriate levels of frequency and amplitude in the right combination have the potency to communicate with the biology of membranes and transport systems. Our study has prompted Lis to elaborate on magnetic resonance models; the Ion Cyclotron Resonance (ICR) model and the Ion Parametric Resonance (IPR) Model in an attempt to explain the occurrence of resonance frequencies. This is extensively described here under the heading: Mechanisms behind the effects of electromagnetical fields upon biology. We also bring forward the concept of solitons being active in membranes and DNA/RNA-transcription as a, possible mean to understand and prove the biological effects of EMF. The Nishinomiya-Yukawa International and Interdisciplinary Symposium 2007 raised the question: What is Life? An obvious and simple answer could be: It is DNA! The DNA strand can be looked upon as an antenna resonating in the microwave band 6GHz with its harmonics and subharmonics.(14)-18)) If this holds true, the dramatic situation might exist, that all living organisms have a receptor for the newly constructed and world-wide man-made microvaves, leading to a direct effect upon the function of DNA - in concordance with our experimental findings! Our generation invented the microwave emitters. We now have in imperative obligation to further investigate the links between EMF and biology in order to prevent possible detrimental effects of the microwaves.
|
|
| 9. |
- Ge, Chenjie, 1991, et al.
(author)
-
3D Multi-Scale Convolutional Networks for Glioma Grading Using MR Images
- 2018
-
In: Proceedings - International Conference on Image Processing, ICIP. - 1522-4880. - 9781479970612 ; , s. 141-145
-
Conference paper (peer-reviewed)abstract
- This paper addresses issues of grading brain tumor, glioma, from Magnetic Resonance Images (MRIs). Although feature pyramid is shown to be useful to extract multi-scale features for object recognition, it is rarely explored in MRI images for glioma classification/grading. For glioma grading, existing deep learning methods often use convolutional neural networks (CNNs) to extract single-scale features without considering that the scales of brain tumor features vary depending on structure/shape, size, tissue smoothness, and locations. In this paper, we propose to incorporate the multi-scale feature learning into a deep convolutional network architecture, which extracts multi-scale semantic as well as fine features for glioma tumor grading. The main contributions of the paper are: (a) propose a novel 3D multi-scale convolutional network architecture for the dedicated task of glioma grading; (b) propose a novel feature fusion scheme that further refines multi-scale features generated from multi-scale convolutional layers; (c) propose a saliency-aware strategy to enhance tumor regions of MRIs. Experiments were conducted on an open dataset for classifying high/low grade gliomas. Performance on the test set using the proposed scheme has shown good results (with accuracy of 89.47%).
|
|
| 10. |
|
|
