Search

Thermal infrared imaging is an emerging modality that has gained increasing interest in recent years, mostly due to technical advances resulting in the availability of affordable microbolometer-based IR imaging sensors. However, while sensors are widely available, algorithms for thermal image processing still lack robustness and accuracy when compared to their RGB counterparts. Current methods developed for RGB data make use of machine learning algorithms that require large amounts of labeled images which are currently not available for the thermal domain. In this paper, we address the question whether providing a large number of labeled images would allow the application of current image processing methods on the example of solving challenging face analysis tasks. We introduce a high-resolution thermal facial image database with extensive manual annotations and explore how it can be used to adapt methods from the visual domain for infrared images. In addition, we extend existing approaches for infrared landmark detection with a head pose estimation for improved robustness and analyze the performance of a deep learning method on this task. An evaluation of algorithm performance shows that learning algorithms either outperform available solutions or allow completely new applications that could previously not be addressed. As a conclusion, we prove that investing the effort into acquiring appropriate training data and adapting competitive algorithms is not only a viable approach in analysing thermal infrared images but can also allow outperforming specific task-designed solutions. The database is freely available for academic use at https://github.com/marcinkopaczka/thermalfaceproject .

While morphologic magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of ligamentous wrist injuries, it is merely static and incapable of diagnosing dynamic wrist instability. Based on real-time MRI and algorithm-based image post-processing in terms of convolutional neural networks (CNNs), this study aims to develop and validate an automatic technique to quantify wrist movement. A total of 56 bilateral wrists (28 healthy volunteers) were imaged during continuous and alternating maximum ulnar and radial abduction. Following CNN-based automatic segmentations of carpal bone contours, scapholunate and lunotriquetral gap widths were quantified based on dedicated algorithms and as a function of wrist position. Automatic segmentations were in excellent agreement with manual reference segmentations performed by two radiologists as indicated by Dice similarity coefficients of 0.96 ± 0.02 and consistent and unskewed Bland–Altman plots. Clinical applicability of the framework was assessed in a patient with diagnosed scapholunate ligament injury. Considerable increases in scapholunate gap widths across the range-of-motion were found. In conclusion, the combination of real-time wrist MRI and the present framework provides a powerful diagnostic tool for dynamic assessment of wrist function and, if confirmed in clinical trials, dynamic carpal instability that may elude static assessment using clinical-standard imaging modalities.

Recent advances in deep learning have shown the capability to accurately segment cardiac structures in magnetic resonance images. However, while these models provide a good segmentation performance for the specified datasets, their generalization with respect to unseen data across different MRI scanners, vendors or clinics is still under investigation. Previous work that aims to increase the generalization performance provides proof that emphasizing the model design on a uniform preprocessing step may be more beneficial than searching for a better neural architecture. In this paper we build upon this idea and show that a carefully designed preprocessing pipeline plays an important role in enabling the neural network to generalize to the large variety in MRI images. We evaluate our model in the context of the Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image (M&Ms) Segmentation Challenge.

Analysis of laboratory animal behavior allows assessment of animal wellbeing. We present a method for the classification of different activities of laboratory mice by analyzing video clips using three deep learning methods. Animals placed in observation cages are filmed and short video clips are labelled as belonging to one of five defined behaviors. Subsequently, three different methods based on convolutional neural networks (CNNS) are applied to classify the clips. The best performing method - a two-stream network that analyzes individual frames as well as the video’s optical flow - achieves an accuracy of 86.4%, including detection of important behavioral patterns such as self-grooming. These results show that the presented analysis protocol allows automated assessment of animal behavior by algorithmic analysis of videos of mice on observation boxes.

We introduce a domain switch for deep neural networks that enables to re-weight convolutional kernels for an input of a known domain. This technique is designed to address re-occurring tasks across multiple domains that are known at runtime and to incorporate them into a single, domain-spanning network. We evaluate this approach in three distinct tasks, namely combined cell nuclei analysis across different stains and fluorescence images, facial landmark detection in grayscale and thermal infrared images, and the BraTS challenge where we treat different recording institutions as domains. We found that conventional U-nets trained on multiple domains perform similar to domain-specific U-nets. Our method improves the results in facial landmark detection significantly, but no change is measured in the other two experiments compared to multi-domain U-nets.

A lightweight framework for fast prototyping and training of deep neural networks for medical image analysis.