A5006688931- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Domain Adaptation and Few-Shot Learning
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Osteoarthritis Treatment and Mechanisms
- Fetal and Pediatric Neurological Disorders
- Advanced X-ray and CT Imaging
- Advanced Radiotherapy Techniques
- COVID-19 diagnosis using AI
- Lower Extremity Biomechanics and Pathologies
- Adversarial Robustness in Machine Learning
- Generative Adversarial Networks and Image Synthesis
- Cell Image Analysis Techniques
- Artificial Intelligence in Healthcare and Education
- Explainable Artificial Intelligence (XAI)
- Advanced Neuroimaging Techniques and Applications
- Radiation Dose and Imaging
- Brain Tumor Detection and Classification
- Cardiac Valve Diseases and Treatments
- Cleft Lip and Palate Research
- Digital Mental Health Interventions
- Cardiac Imaging and Diagnostics
University of Tübingen
2022-2025
Bernstein Center for Computational Neuroscience Tübingen
2024-2025
University of Lucerne
2025
ETH Zurich
2017-2021
Graz University of Technology
2021
Addiction Switzerland
2017-2018
University of Zurich
2017-2018
University Hospital Heidelberg
2018
Heidelberg University
2018
Board of the Swiss Federal Institutes of Technology
2018
Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation corresponding tasks has thus been subject intense research over past decades. In this paper, we introduce "Automatic Cardiac Diagnosis Challenge" dataset (ACDC), largest publicly available fully annotated for purpose MRI (CMR) assessment. contains data 150 multi-equipments CMRI recordings...
Identifying and interpreting fetal standard scan planes during 2-D ultrasound mid-pregnancy examinations are highly complex tasks, which require years of training. Apart from guiding the probe to correct location, it can be equally difficult for a non-expert identify relevant structures within image. Automatic image processing provide tools help experienced as well inexperienced operators with these tasks. In this paper, we propose novel method based on convolutional neural networks,...
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate missing k-space data. Deep learning (DL) provides a powerful framework extracting such existing datasets, through learning, and then using it reconstruction. Leveraging this, recent methods employed DL learn mappings fully sampled images paired including corresponding images, integrating knowledge implicitly. In this article, we propose an alternative approach...
Attributing the pixels of an input image to a certain category is important and well-studied problem in computer vision, with applications ranging from weakly supervised localisation understanding hidden effects data. In recent years, approaches based on interpreting previously trained neural network classifier have become de facto state-of-the-art are commonly used medical as well natural datasets. this paper, we discuss limitation these which may lead only subset specific features being...
Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not favourable option because acquiring samples from experts time-consuming and expensive. Consequently, numerous have been proposed in the literature for learning with limited examples. Unfortunately, approaches yet yielded significant gains over random augmentation image segmentation, where...
Measurement of head biometrics from fetal ultrasonography images is key importance in monitoring the healthy development fetuses. However, accurate measurement relevant anatomical structures subject to large inter-observer variability clinic. To address this issue, an automated method utilizing Fully Convolutional Networks (FCN) proposed determine measurements circumference (HC) and biparietal diameter (BPD). An FCN was trained on approximately 2000 2D ultrasound with annotations provided by...
Abstract Objective Segmentation of thigh muscle and adipose tissue is important for the understanding musculoskeletal diseases such as osteoarthritis. Therefore, purpose this work (a) to evaluate whether a fully automated approach provides accurate segmentation muscles cross-sectional areas (CSA) compared with manual (b) validity method based on previous clinical study. Materials methods The U-Net architecture trained 250 manually segmented thighs from Osteoarthritis Initiative (OAI)....
Tissue characterisation with CMR parametric mapping has the potential to detect and quantify both focal diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 particular shown promise as a useful biomarker support diagnostic, therapeutic prognostic decision-making ischaemic non-ischaemic cardiomyopathies. Convolutional neural networks Bayesian inference are category of artificial which model uncertainty network output. This study presents an...
Magnetic Resonance Imaging (MRI) offers strong soft tissue contrast but suffers from long acquisition times and requires tedious annotation radiologists. Traditionally, these challenges have been addressed separately with reconstruction image analysis algorithms. To see if performance could be improved by treating both as end-to-end, we hosted the K2S challenge, in which challenge participants segmented knee bones cartilage 8× undersampled k-space. We curated 300-patient dataset of multicoil...
The acquisition of a Magnetic Resonance (MR) scan usually takes longer than subjects can remain still. Movement the subject such as bulk patient motion or respiratory degrades image quality and its diagnostic value by producing artefacts like ghosting, blurring, smearing. This work focuses on effect reconstructed slices detection in reconstruction using supervised learning approach based random decision forests. Both effects occurring at various time points head scans cardiac are studied....
Background and purposeOnline adaptive magnetic resonance imaging (MRI)-guided radiotherapy requires fast dose calculation algorithms to reduce intra-fraction motion uncertainties improve workflow efficiency. While Monte-Carlo simulations are precise but computationally intensive, neural networks promise accurate modelling in strong fields. This study aimed train evaluate a deep network for MRI-guided using comprehensive clinical dataset.Materials methodsA dataset of 6595 irradiation segments...
Abstract While the field of medical image analysis has undergone a transformative shift with integration machine learning techniques, main challenge these techniques is often scarcity large, diverse, and well-annotated datasets. Medical images vary in format, size, other parameters therefore require extensive preprocessing standardization, for usage learning. Addressing challenges, we introduce Imaging Meta-Dataset (MedIMeta), novel multi-domain, multi-task meta-dataset. MedIMeta contains 19...