References of "Husch, Andreas 50030581"
     in
Bookmark and Share    
See detailAnalysis and comparison of gait impairments in patients with Parkinson’s disease and normal pressure hydrocephalus using wearable sensors and machine learning algorithms
Magni, Stefano UL; Bremm, René Peter UL; Lecossois, Sylvie et al

Scientific Conference (2022, September 05)

Objectives. Gait impairments in patients with Parkinson’s disease (PD) and normal pressure hydrocephalus (NPH) are visually assessed by movement disorders experts for diagnoses and to decide on ... [more ▼]

Objectives. Gait impairments in patients with Parkinson’s disease (PD) and normal pressure hydrocephalus (NPH) are visually assessed by movement disorders experts for diagnoses and to decide on pharmaceutical and surgical interventions. Despite standardised tests and clinicians’ expertise, such approaches entail a considerable level of subjectivity. The recent development of wearable sensors and machine learning offers complementary approaches providing more objective, quantitative assessments of gait impairments. We aim to employ the data gathered from an inertial measurement unit synchronized with a novel foot pressure sensor embedded in the patient’s shoes to characterize gait impairments. We focus on distinguishing PD from NPH and on assessing gait impairment before and after surgical intervention. Methods. A cohort of 10 PD and 10 NPH patients was assembled and patients performed standardised walking tests. Measurements were performed employing wearable sensors comprising a three-axes gyroscope, a three-axes accelerometer and eight pressure sensors embedded in each patient’s shoe. To analyse the generated data, existing algorithms were implemented and adapted. These allow to compute gait cycle parameters such as step time and metrics characterizing the swing and stance phases. Machine learning algorithms where employed to identify major changes in gait cycle parameters between the two groups of patients, and for individual patients before and after surgical intervention as DBS implantation in PD and Shunt implantation in NPH. Results. The gait impairments of both disease groups were measured and quantified. An algorithm to extract gait cycle parameters from sensors was implemented, tested and employed on such patients. Gait cycle parameters within and between the groups of PD and NPH patients were compared, assessing what gait cycle parameters allow to distinguish between these groups. Gait cycle impairments of patients before and after surgery were compared, assessing the effect of DBS or Shunt implantation and which gait cycle parameters allow to monitor symptoms improvement. Conclusions. Wearable sensors measuring pressure, combined with gait cycle parameters extraction and machine learning algorithms, have a great potential for objective evaluation of gait impairment. In particular, they allow to characterize what differentiate such impairments between PD and NPH patients, and what allow to assess motor symptoms improvement after surgery. [less ▲]

Detailed reference viewed: 18 (0 UL)
Full Text
Peer Reviewed
See detailGeneralising from conventional pipelines using deep learning in high‑throughput screening workfows
Garcia Santa Cruz, Beatriz UL; Sölter, Jan; Gomez Giro, Gemma UL et al

in Scientific Reports (2022)

The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality ... [more ▼]

The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality of the results relies on the accuracy of the image analysis. Although state-of-the-art solutions for image segmentation employ deep learning approaches, the high cost of manually generating ground truth labels for model training hampers the day-to-day application in experimental laboratories. Alternatively, traditional computer vision-based solutions do not need expensive labels for their implementation. Our work combines both approaches by training a deep learning network using weak training labels automatically generated with conventional computer vision methods. Our network surpasses the conventional segmentation quality by generalising beyond noisy labels, providing a 25% increase of mean intersection over union, and simultaneously reducing the development and inference times. Our solution was embedded into an easy-to-use graphical user interface that allows researchers to assess the predictions and correct potential inaccuracies with minimal human input. To demonstrate the feasibility of training a deep learning solution on a large dataset of noisy labels automatically generated by a conventional pipeline, we compared our solution against the common approach of training a model from a small manually curated dataset by several experts. Our work suggests that humans perform better in context interpretation, such as error assessment, while computers outperform in pixel-by-pixel fne segmentation. Such pipelines are illustrated with a case study on image segmentation for autophagy events. This work aims for better translation of new technologies to real-world settings in microscopy-image analysis. [less ▲]

Detailed reference viewed: 177 (15 UL)
Full Text
Peer Reviewed
See detailThe effect of dataset confounding on predictions of deep neural networks for medical imaging
Garcia Santa Cruz, Beatriz UL; Husch, Andreas UL; Hertel, Frank UL

in Vol. 3 (2022): Proceedings of the Northern Lights Deep Learning Workshop 2022 (2022, April 18)

The use of Convolutional Neural Networks (CNN) in medical imaging has often outperformed previous solutions and even specialists, becoming a promising technology for Computer-aided-Diagnosis (CAD) systems ... [more ▼]

The use of Convolutional Neural Networks (CNN) in medical imaging has often outperformed previous solutions and even specialists, becoming a promising technology for Computer-aided-Diagnosis (CAD) systems. However, recent works suggested that CNN may have poor generalisation on new data, for instance, generated in different hospitals. Uncontrolled confounders have been proposed as a common reason. In this paper, we experimentally demonstrate the impact of confounding data in unknown scenarios. We assessed the effect of four confounding configurations: total, strong, light and balanced. We found the confounding effect is especially prominent in total confounder scenarios, while the effect on light and strong confounding scenarios may depend on the dataset robustness. Our findings indicate that the confounding effect is independent of the architecture employed. These findings might explain why models can report good metrics during the development stage but fail to translate to real-world settings. We highlight the need for thorough consideration of these commonly unattended aspects, to develop safer CNN-based CAD systems. [less ▲]

Detailed reference viewed: 128 (18 UL)
Full Text
Peer Reviewed
See detailAbstract: The Importance of Dataset Choice Lessons Learned from COVID-19 X-ray Imaging Models
Garcia Santa Cruz, Beatriz UL; Bossa, Matias Nicolas UL; Soelter, Jan et al

in Bildverarbeitung für die Medizin 2022. Informatik aktuell. Springer Vieweg, Wiesbaden. (2022, April 05)

Detailed reference viewed: 29 (2 UL)
Full Text
Peer Reviewed
See detailRapid artificial intelligence solutions in a pandemic—The COVID-19-20 Lung CT Lesion Segmentation Challenge
Roth, Holger R.; Xu, Ziyue; Diez, Carlos Tor et al

in Medical Image Analysis (2022)

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of ... [more ▼]

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020. [less ▲]

Detailed reference viewed: 13 (0 UL)
Full Text
Peer Reviewed
See detailPublic Covid-19 X-ray datasets and their impact on model bias - a systematic review of a significant problem
Garcia Santa Cruz, Beatriz UL; Bossa, Matias Nicolas UL; Sölter, Jan UL et al

in Medical Image Analysis (2021), 74

Computer-aided diagnosis and stratification of COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and ... [more ▼]

Computer-aided diagnosis and stratification of COVID-19 based on chest X-ray suffers from weak bias assessment and limited quality-control. Undetected bias induced by inappropriate use of datasets, and improper consideration of confounders prevents the translation of prediction models into clinical practice. By adopting established tools for model evaluation to the task of evaluating datasets, this study provides a systematic appraisal of publicly available COVID-19 chest X-ray datasets, determining their potential use and evaluating potential sources of bias. Only 9 out of more than a hundred identified datasets met at least the criteria for proper assessment of the risk of bias and could be analysed in detail. Remarkably most of the datasets utilised in 201 papers published in peer-reviewed journals, are not among these 9 datasets, thus leading to models with a high risk of bias. This raises concerns about the suitability of such models for clinical use. This systematic review highlights the limited description of datasets employed for modelling and aids researchers to select the most suitable datasets for their task. [less ▲]

Detailed reference viewed: 179 (39 UL)
Peer Reviewed
See detailModel bias and its impact on computer-aided diagnosis: A data-centric approach
Garcia Santa Cruz, Beatriz UL; Bossa, Matias Nicolas UL; Sölter, Jan UL et al

Poster (2021, August)

Machine learning and data-driven solutions open exciting opportunities in many disciplines including healthcare. The recent transition to this technology into real clinical settings brings new challenges ... [more ▼]

Machine learning and data-driven solutions open exciting opportunities in many disciplines including healthcare. The recent transition to this technology into real clinical settings brings new challenges. Such problems derive from several factors, including their dataset origin, composition and description, hampering their fairness and secure application. Considering the potential impact of incorrect predictions in applied-ML healthcare research is urgent. Undetected bias induced by inappropriate use of datasets and improper consideration of confounders prevents the translation of prediction models into clinical practice. Therefore, in this work, the use of available systematic tools to assess the risk of bias in models is employed as the first step to explore robust solutions for better dataset choice, dataset merge and design of the training and validation step during the ML development pipeline. [less ▲]

Detailed reference viewed: 110 (17 UL)
Full Text
Peer Reviewed
See detailModelling COVID-19 dynamics and potential for herd immunity by vaccination in Austria, Luxembourg and Sweden
Kemp, Francoise UL; Proverbio, Daniele UL; Aalto, Atte UL et al

in Journal of Theoretical Biology (2021)

Against the COVID-19 pandemic, non-pharmaceutical interventions have been widely applied and vaccinations have taken off. The upcoming question is how the interplay between vaccinations and social ... [more ▼]

Against the COVID-19 pandemic, non-pharmaceutical interventions have been widely applied and vaccinations have taken off. The upcoming question is how the interplay between vaccinations and social measures will shape infections and hospitalizations. Hence, we extend the Susceptible-Exposed-Infectious-Removed (SEIR) model including these elements. We calibrate it to data of Luxembourg, Austria and Sweden until 15 December 2020. Sweden results having the highest fraction of undetected, Luxembourg of infected and all three being far from herd immunity in December. We quantify the level of social interaction, showing that a level around 1/3 of before the pandemic was still required in December to keep the effective reproduction number Refft below 1, for all three countries. Aiming to vaccinate the whole population within 1 year at constant rate would require on average 1,700 fully vaccinated people/day in Luxembourg, 24,000 in Austria and 28,000 in Sweden, and could lead to herd immunity only by mid summer. Herd immunity might not be reached in 2021 if too slow vaccines rollout speeds are employed. The model thus estimates which vaccination rates are too low to allow reaching herd immunity in 2021, depending on social interactions. Vaccination will considerably, but not immediately, help to curb the infection; thus limiting social interactions remains crucial for the months to come. [less ▲]

Detailed reference viewed: 233 (44 UL)
Full Text
See detailLeveraging state-of-the-art architectures by enriching training information - a case study
Sölter, Jan; Proverbio, Daniele; Baniasadi, Mehri et al

Speeches/Talks (2021)

Our working hypothesis is that key factors in COVID-19 imaging are the available imaging data and their label noise and confounders, rather than network architectures per se. Thus, we applied existing ... [more ▼]

Our working hypothesis is that key factors in COVID-19 imaging are the available imaging data and their label noise and confounders, rather than network architectures per se. Thus, we applied existing state-of-the-art convolution neural network frameworks based on the U-Net architecture, namely nnU-Net [3], and focused on leveraging the available training data. We did not apply any pre-training nor modi ed the network architecture. First, we enriched training information by generating two additional labels for lung and body area. Lung labels were created with a public available lung segmentation network and weak body labels were generated by thresholding. Subsequently, we trained three di erent multi-class networks: 2-label (original background and lesion labels), 3-label (additional lung label) and 4-label (additional lung and body label). The 3-label obtained the best single network performance in internal cross-validation (Dice-Score 0.756) and on the leaderboard (Dice- Score 0.755, Haussdor 95-Score 57.5). To improve robustness, we created a weighted ensemble of all three models, with calibrated weights to optimise the ranking in Dice-Score. This ensemble achieved a slight performance gain in internal cross-validation (Dice-Score 0.760). On the validation set leaderboard, it improved our Dice-Score to 0.768 and Haussdor 95- Score to 54.8. It ranked 3rd in phase I according to mean Dice-Score. Adding unlabelled data from the public TCIA dataset in a student-teacher manner signi cantly improved our internal validation score (Dice-Score of 0.770). However, we noticed partial overlap between our additional training data (although not human-labelled) and  nal test data and therefore submitted the ensemble without additional data, to yield realistic assessments. [less ▲]

Detailed reference viewed: 36 (6 UL)
Full Text
Peer Reviewed
See detailDynamical SPQEIR model assesses the effectiveness of non-pharmaceutical interventions against COVID-19 epidemic outbreaks.
Proverbio, Daniele UL; Kemp, Francoise UL; Magni, Stefano UL et al

in PloS one (2021), 16(5), 0252019

Against the current COVID-19 pandemic, governments worldwide have devised a variety of non-pharmaceutical interventions to mitigate it. However, it is generally difficult to estimate the joint impact of ... [more ▼]

Against the current COVID-19 pandemic, governments worldwide have devised a variety of non-pharmaceutical interventions to mitigate it. However, it is generally difficult to estimate the joint impact of different control strategies. In this paper, we tackle this question with an extended epidemic SEIR model, informed by a socio-political classification of different interventions. First, we inquire the conceptual effect of mitigation parameters on the infection curve. Then, we illustrate the potential of our model to reproduce and explain empirical data from a number of countries, to perform cross-country comparisons. This gives information on the best synergies of interventions to control epidemic outbreaks while minimising impact on socio-economic needs. For instance, our results suggest that, while rapid and strong lockdown is an effective pandemic mitigation measure, a combination of social distancing and early contact tracing can achieve similar mitigation synergistically, while keeping lower isolation rates. This quantitative understanding can support the establishment of mid- and long-term interventions, to prepare containment strategies against further outbreaks. This paper also provides an online tool that allows researchers and decision makers to interactively simulate diverse scenarios with our model. [less ▲]

Detailed reference viewed: 119 (9 UL)
Full Text
Peer Reviewed
See detailIntraoperative discrimination of native meningioma and dura mater by Raman spectroscopy
Jelke, Finn; Mirizzi, Giulia; Borgmann, Felix Kleine et al

in Scientific Reports (2021)

Detailed reference viewed: 52 (5 UL)
See detailDBS Imaging Methods II: Electrode Localization
Husch, Andreas UL; Hertel, Frank

in Horn, Andreas (Ed.) Connectomic Deep Brain Stimulation (2021)

Connectomic Deep Brain Stimulation (DBS) covers this highly efficacious treatment option for movement disorders such as Parkinson’s Disease, Essential Tremor and Dystonia. The book examines its impact on ... [more ▼]

Connectomic Deep Brain Stimulation (DBS) covers this highly efficacious treatment option for movement disorders such as Parkinson’s Disease, Essential Tremor and Dystonia. The book examines its impact on distributed brain networks that span across the human brain in parallel with modern-day neuroimaging concepts and the connectomics of the brain. It asks several questions, including which cortical areas should DBS electrodes be connected in order to generate the highest possible clinical improvement? Which connections should be avoided? Could these connectomic insights be used to better understand the mechanism of action of DBS? How can they be transferred to individual patients, and more. This book is suitable for neuroscientists, neurologists and functional surgeons studying DBS. It provides practical advice on processing strategies and theoretical background, highlighting and reviewing the current state-of-the-art in connectomic surgery. [less ▲]

Detailed reference viewed: 91 (4 UL)
Full Text
Peer Reviewed
See detailDifferentiation of primary CNS lymphoma and glioblastoma using Raman spectroscopy and machine learning algorithms
Klamminger, Gilbert Georg; Klein, Karoline; Mombaerts, Laurent UL et al

in Free Neuropathology (2021), 2

Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnostics and therapy, but most importantly also determines the intraoperative surgical ... [more ▼]

Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnostics and therapy, but most importantly also determines the intraoperative surgical course. Advanced radiological methods allow this to a certain extent but ultimately, biopsy is still necessary for final diagnosis. As an upcoming method that enables tissue analysis by tracking changes in the vibrational state of molecules via inelastic scattered photons, we used Raman Spectroscopy (RS) as a label free method to examine specimens of both tumor entities intraoperatively, as well as postoperatively in formalin fixed paraffin embedded (FFPE) samples. Results: We applied and compared statistical performance of linear and nonlinear machine learning algorithms (Logistic Regression, Random Forest and XGBoost), and found that Random Forest classification distinguished the two tumor entities with a balanced accuracy of 82,4% in intraoperative tissue condition and with 94% using measurements of distinct tumor areas on FFPE tissue. Taking a deeper insight into the spectral properties of the tumor entities, we describe different tumor-specific Raman shifts of interest for classification. Conclusions: Due to our findings, we propose RS as an additional tool for fast and non-destructive, perioperative tumor tissue discrimination, which may augment treatment options at an early stage. RS may further serve as a useful additional tool for neuropathological diagnostics with little requirements for tissue integrity. [less ▲]

Detailed reference viewed: 52 (2 UL)
Full Text
Peer Reviewed
See detailAutomated Deep Learning-based Segmentation of Brain, SEEG and DBS Electrodes on CT Images.
Vlasov, Vanja UL; Bofferding, Marie UL; Marx, Loic Marc UL et al

in Bildverarbeitung für die Medizin 2021 (2021)

Detailed reference viewed: 76 (6 UL)
Full Text
Peer Reviewed
See detailApplication of Raman Spectroscopy for Detection of Histologically Distinct Areas in Formalin-fixed Paraffin-embedded (FFPE) Glioblastoma
Klamminger, Gilbert Georg; Gerardy, Jean-Jacques UL; Jelke, Finn et al

in Neuro-Oncology Advances (2021)

Background Although microscopic assessment is still the diagnostic gold standard in pathology, non-light microscopic methods such as new imaging methods and molecular pathology have considerably ... [more ▼]

Background Although microscopic assessment is still the diagnostic gold standard in pathology, non-light microscopic methods such as new imaging methods and molecular pathology have considerably contributed to more precise diagnostics. As an upcoming method, Raman spectroscopy (RS) offers a "molecular fingerprint" which could be used to differentiate tissue heterogeneity or diagnostic entities. RS has been successfully applied on fresh and frozen tissue, however more aggressively, chemically treated tissue such as formalin-fixed, paraffin-embedded (FFPE) samples are challenging for RS. Methods To address this issue, we examined FFPE samples of morphologically highly heterogeneous glioblastoma (GBM) using RS in order to classify histologically defined GBM areas according to RS spectral properties. We have set up a SVM (support vector machine)-based classifier in a training cohort and corroborated our findings in a validation cohort. Results Our trained classifier identified distinct histological areas such as tumor core and necroses in GBM with an overall accuracy of 70.5% based on spectral properties of RS. With an absolute misclassification of 21 out of 471 Raman measurements, our classifier has the property of precisely distinguishing between normal appearing brain tissue and necrosis. When verifying the suitability of our classifier system in a second independent dataset, very little overlap between necrosis and normal appearing brain tissue can be detected. Conclusion These findings show that histologically highly variable samples such as GBM can be reliably recognized by their spectral properties using RS. As a conclusion, we propose that RS may serve useful as a future method in the pathological toolbox. [less ▲]

Detailed reference viewed: 74 (1 UL)
Full Text
See detailRapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge.
Roth, Holger; Xu, Ziyue; Diez, Carlos Tor et al

E-print/Working paper (2021)

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of ... [more ▼]

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020. [less ▲]

Detailed reference viewed: 44 (0 UL)
Full Text
Peer Reviewed
See detailAutomatic Detection of Nigrosome Degeneration in Susceptibility-Weighted MRI for Computer-Aided Diagnosis of Parkinson’s Disease Using Machine Learning
Garcia Santa Cruz, Beatriz UL; Husch, Andreas UL; Hertel, Frank UL

in Movement Disorders (2020, September 12)

Objective: Automatize the detection of ‘swallow-tail’ appearance in substantia nigra dopaminergic neurons using MRI for more robust tests on Parkinson’s disease (PD) diagnosis. Background: Differential ... [more ▼]

Objective: Automatize the detection of ‘swallow-tail’ appearance in substantia nigra dopaminergic neurons using MRI for more robust tests on Parkinson’s disease (PD) diagnosis. Background: Differential diagnosis of PD is challenging even in specialized centers. The use of imaging techniques can be bene cial for the diagnosis. Although DaTSCAN has been proven to be clinically useful, it is not widely available and has radiation risk and high-cost associated. Therefore, MRI scans for PD diagnosis offer several advantages over DaTSCAN [1]. Recent literature shows strong evidence of high diagnostic accuracy using the ‘swallow-tail’ shape of the dorsolateral substantia nigra in 3T – SWI [2]. Nevertheless, the majority of such studies rely on the subjective opinion of experts and manual methods for the analysis to assess the accuracy of these features. Alternatively, we propose a fully automated solution to evaluate the absence or presence of this feature for computer-aided diagnosis (CAD) of PD. Method: Restrospective study of 27 PD and 18 non-PD was conducted, including standard high-resolution 3D MRI – T1 & SWI sequences (additionally, T2 scans were used to increase the registration references). Firstly, spatial registration and normalization of the images were performed. Then, the ROI was extracted using atlas references. Finally, a supervised machine learning model was built using 5-fold-within-5-fold nested cross-validation. Results: Preliminary results show signi cant sensitivity (0.92) and ROC AUC (0.82), allowing for automated classi cation of patients based on swallow-tail biomarker from MRI. Conclusion: Detection of nigrosome degeneration (swallow-tail biomarker) in accessible brain imaging techniques can be automatized with signi cant accuracy, allowing for computer-aided PD diagnosis. References: [1] Schwarz, S. T., Xing, Y., Naidu, S., Birchall, J., Skelly, R., Perkins, A., ... & Gowland, P. (2017). Protocol of a single group prospective observational study on the diagnostic value of 3T susceptibility weighted MRI of nigrosome-1 in patients with parkinsonian symptoms: the N3iPD study (nigrosomal iron imaging in Parkinson’s disease). BMJ open, 7(12), e016904. [2] – Schwarz, S. T., Afzal, M., Morgan, P. S., Bajaj, N., Gowland, P. A., & Auer, D. P. (2014). The ‘swallow tail’ appearance of the healthy nigrosome –a new accurate test of Parkinson’s disease: a case-control and retrospective cross-sectional MRI study at 3T. PloS one, 9(4). [less ▲]

Detailed reference viewed: 182 (22 UL)
Full Text
Peer Reviewed
See detailFastField: An Open-Source Toolbox for Efficient Approximation of Deep Brain Stimulation Electric Fields
Baniasadi, Mehri UL; Proverbio, Daniele UL; Goncalves, Jorge UL et al

in NeuroImage (2020)

Deep brain stimulation (DBS) is a surgical therapy to alleviate symptoms of certain brain disorders by electrically modulating neural tissues. Computational models predicting electric fields and volumes ... [more ▼]

Deep brain stimulation (DBS) is a surgical therapy to alleviate symptoms of certain brain disorders by electrically modulating neural tissues. Computational models predicting electric fields and volumes of tissue activated are key for efficient parameter tuning and network analysis. Currently, we lack efficient and flexible software implementations supporting complex electrode geometries and stimulation settings. Available tools are either too slow (e.g. finite element method–FEM), or too simple, with limited applicability to basic use-cases. This paper introduces FastField, an efficient open-source toolbox for DBS electric field and VTA approximations. It computes scalable e-field approximations based on the principle of superposition, and VTA activation models from pulse width and axon diameter. In benchmarks and case studies, FastField is solved in about 0.2s, ~ 1000 times faster than using FEM. Moreover, it is almost as accurate as using FEM: average Dice overlap of 92%, which is around typical noise levels found in clinical data. Hence, FastField has the potential to foster efficient optimization studies and to support clinical applications [less ▲]

Detailed reference viewed: 193 (29 UL)
Full Text
See detailOn the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets
Garcia Santa Cruz, Beatriz UL; Sölter, Jan UL; Bossa, Matias Nicolas UL et al

E-print/Working paper (2020)

 Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, in particular by the use of deep learning ... [more ▼]

 Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, in particular by the use of deep learning models. In this context hundreds of models where proposed with the majority of them trained on public datasets. Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias, hindering the applicability of these models to real-world clinical practice. Considering that datasets are an essential part of model building and evaluation, a deeper understanding of the current landscape is needed. This paper presents an overview of the currently public available COVID-19 chest X-ray datasets. Each dataset is briefly described and potential strength, limitations and interactions between datasets are identified. In particular, some key properties of current datasets that could be potential sources of bias, impairing models trained on them are pointed out. These descriptions are useful for model building on those datasets, to choose the best dataset according the model goal, to take into account the specific limitations to avoid reporting overconfident benchmark results, and to discuss their impact on the generalisation capabilities in a specific clinical setting. [less ▲]

Detailed reference viewed: 348 (10 UL)
Full Text
Peer Reviewed
See detailImpressive weight gain after deep brain stimulation of nucleus accumbens in treatment- ­ resistant bulimic anorexia nervosa
Arroteia, Isabel Fernandes; Husch, Andreas UL; Baniasadi, Mehri UL et al

in BMJ Case Reports (2020)

Anorexia nervosa (AN) severely impacts individual’s mental and physical health as well as quality of life. In 21% of cases no durable response to conservative treatment can be obtained. The serious course ... [more ▼]

Anorexia nervosa (AN) severely impacts individual’s mental and physical health as well as quality of life. In 21% of cases no durable response to conservative treatment can be obtained. The serious course of the disease in the most severely affected patients justifies invasive treatment options. One of the treatment methods increasingly used in recent years is deep brain stimulation (DBS). A 42-year- old woman suffering from chronic AN of the bulimic subtype shows a 46.9% weight gain and a subjective increase in quality of life, 12 months after bilateral nucleus accumbens (NAcc) DBS implantation. No improvement in comorbid depression could be achieved. DBS of the NAcc is a treatment option to be considered in severe AN when conventional treatment modalities recommended by evidence-based guidelines have not been able to bring lasting relief to the patient’s suffering. [less ▲]

Detailed reference viewed: 98 (8 UL)