A5032908709- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Statistical Methods and Inference
- Skin Protection and Aging
- Medical Imaging and Analysis
- AI in cancer detection
- Human Pose and Action Recognition
- Advanced MRI Techniques and Applications
- Image and Object Detection Techniques
- Dental Radiography and Imaging
- Industrial Vision Systems and Defect Detection
- Optical measurement and interference techniques
- Advancements in Transdermal Drug Delivery
- Liver Disease Diagnosis and Treatment
- Digital Imaging for Blood Diseases
- 3D Shape Modeling and Analysis
- Dermatologic Treatments and Research
- Manufacturing Process and Optimization
Dermatologikum Hamburg
2020
Fraunhofer Institute for Applied Information Technology
2014
Fraunhofer Society
2012
University of Dundee
2005-2008
Statistical shape models are often learned from examples based on landmark correspondences between annotated examples. A method is proposed for learning such contours with inconsistent bifurcations and loops. Automatic segmentation of tibial femoral in knee X-ray images investigated as a step towards reliable, quantitative radiographic analysis osteoarthritis diagnosis assessment progression. Results presented using various features, the Mahalanobis distance, distance weighted K-nearest...
Abstract Background In vivo confocal Raman spectroscopy (CRS) revealed a clear correlation of age and dermal water content, indicating increasing content the dermis with age. This enhancement has been interpreted as an age‐dependent depletion, proteins, mainly collagen. Chronical sun exposure is known to destroy collagen network skin, which leads signs photoaging formation wrinkles. Noninvasive in measuring techniques for are limited. Therefore, sensitive quantify even mild degrees clinical...
Histological investigation of a lesion induced by radiofrequency ablation (RFA) treatment provides ground-truth about the true size, thus verifying success or failure RFA treatment. This work presents framework for registration two-dimensional large-scale histological sections and three-dimensional CT data typically used to guide intervention. The focus is on developed interactive methods reconstruction volume fusion high-resolution (MicroCT) into based natural feature points. evaluated...
Data below 1 mm voxel size is getting more and common in the clinical practice but it still hard to obtain a consistent collection of such datasets for medical image processing research. With this paper we provide large Contrast Enhanced (CE) Computed Tomography (CT) data from porcine animal experiments describe their acquisition procedure peculiarities. We have acquired three CE-CT phases at highest available scanner resolution 57 livers during induced respiratory arrest. These capture...
Statistical shape models are often learned from examples based on landmark correspondences between annotated examples. A method is proposed for learning such contours with inconsistent bifurcations and loops. It evaluated the task of segmenting tibial in knee radiographs. Results presented using various features, distance weighted K nearest neighbours differing eigenspace constraints.
A probabilistic method is proposed for segmentation of multiple objects that overlap or are in close proximity to one another. likelihood function formulated explicitly models overlapping object appearance. Priors on global appearance and geometry (including shape) learned from example images. Markov chain Monte Carlo methods used obtain samples a posterior distribution over model parameters which expectations can be estimated. The described detail the problem segmenting femur tibia x-ray...