Microtubules are long cylindrical polymers, assembled from tubulin proteins. Microtubule ends can be visualized using fluorescence and confocal microscopy. This allows for the study of microtubule dynamics. However, the manual annotation of microtubules is laborious, which is why automated tracking methods are used. In this project we have investigated the automation of both microtubule detection and segmentation using deep convolutional neural networks. To this end, we have adapted the ISOODL network introduced by Böhm et al. This network not only detects, but also segments microtubules. Microtubule locations are represented as reference points at their center of mass. Separation between microtubules is introduced by predicting both xz- and yz-sheared masks. At every predicted reference point, post-processing operations revert the shearing operation. This results in microtubule detections and their corresponding segmentations. We have concluded that the ISOODL network is able to detect and segment microtubules. In an attempt to further improve the segmentation of overlapping microtubules, we developed a new network to be used exclusively on overlapping microtubules. This network
predicts the segmentation mask of every microtubule in a different channel of the output. However, the developed ’overlap network’ was unable to produce satisfactory segmentation results. Consequently, this data structure does not facilitate separation between overlapping microtubules.

The thesis is composed of two parts. The first part is the scientific article
that describes the main findings for our objective to align cerebral DSA series.
The second part of the thesis includes more extensive information regarding
the clinical and technical background of the project. Additionally, it contains
information on deep-learning

Heart failure is a leading cause of death and forms a growing health concern. The development of novel drugs is however hampered by the absence of adequate screening methods and disease models. Cardiomyocytes derived from patients could assist in the development of a patient specific drug screen method to test the efficacy and safety of putative drugs. Simultaneously, deep learning has been applied to a variety of biomedical datasets, achieving state-of-the-art performance. Previous methods for the classification of cardiomyocytes as healthy or diseased only focused on machine learning methods. We present the first deep learning approach to perform this classification task together with a novel artificial intelligence interpretability method called Contraction Analysis Local Interpretable model-agnostic explanations (CA-LIME), able to explain the predictions made by the classifier. The proposed classifier is shown to outperform previously developed methods to classify cardiomyocytes, obtaining 97.5% accuracy. Our results indicate this classifier could aid in the development of a high throughput drug screening system for cardiac drug development. The explanations made by CA-LIME are in correspondence with previous observations of drugs with known effects, verifying the effectiveness of our approach. Together with CA-LIME, the processing pipeline could lead to the discovery of new differences between the motion of healthy and aberrant beating cardiomyocytes.