Motivation. DNA molecules mutate thousands of times every day. Some mutations are harmful to human cells, and may lead to the loss of function in important genes involved in DNA damage repair (DDR) mechanisms. Diseases such as tumors can exploit mutations in important, driver DDR genes to rapidly proliferate. Specific patterns of mutations (or signatures) are insightful indicators for the presence of DDR malfunctioning, which can be exploited to provide targeted treatment (e.g., by leveraging synthetic lethalities). Different methods have been developed to successfully extract relevant mutational signatures from the genomes of tumor patients. Most approaches are unsupervised and thus do not optimize toward distinguishing DDR deficiencies (DDRd). Supervised approaches achieve this, but rely on labeled in vitro data from tumor cell line genomes during training, due to the lack of DDRd ground truth for tumor patient genomes. Semi-supervised learning could bridge the gap and jointly exploit labeled cell line and unlabeled patient mutation profiles to generalize to patient tumors and provide more clinically relevant DDRd mutational signatures.
Results. We propose Pseudo-labeling Semi-Supervised NMF (PSS-NMF), a novel integrated signature extraction and label prediction method, which extends supervised non-negative matrix factorization (NMF) with the ability to incorporate unlabeled samples into the training via pseudo-labeling. Models learned using PSS-NMF were benchmarked on two different tasks, cancer type and DDRd prediction. PSS-NMF consistently improved prediction for patient tumors over the supervised NMF baseline for both tasks, learning signatures that better transferred to the patient tumor domain: the models achieved Macro F1 scores of 0.3842 and 0.1331 respectively for cancer type prediction, and 0.4928 vs 0.4704 for DDRd prediction. We further validated that PSS-NMF identified DDRd signatures were biologically relevant, by comparing them to known DDRd-related mutational signatures curated in COSMIC and investigating their exposures in patient tumor genomes.

For several years, the dynamics of cerebrospinal fluid (CSF) in the subarachnoid and perivascular space (SAS and PVS) have been a topic of controversy. Both the SAS and PVS are part of the glymphatic system, a network of CSF-filled regions crucial to waste disposal in the brain. The CSF in this system transports the waste, which is why fluid dynamics are a point of interest when trying to promote brain clearance and keep neurodegeneration at bay. The reason why CSF-dynamics remain unclear, originates in the difficulty to image and visualize them with adequate blood suppression and resolution to ensure that the motion observed is not coming from slow blood flow. For this purpose, a high resolution, CSF-specific magnetic resonance imaging sequence (CSF-STREAM) has been developed, for which a DTI-like metric called CSF-mobility has been derived to quantify fluid dynamics. CSF-mobility is a metric describing the amount of movement that CSF undergoes within a voxel, as a function of intra-voxel dephasing due to bipolar gradients. The metric is derived from the eigenvalues from the tensor information in each voxel (volumetric / 3D pixel) that describes this dephasing along different axes. The orientation of CSF-mobility can also be retrieved from CSF-STREAM data, but has not been characterized yet in detail. This report analyzes the eigenvector orientations of the CSF-mobility tensor in various CSF f illed spaces that are wrapped aronund blood vessels: the subarachnoid space (SAS) around the middle cerebral artery (MCA) and PVS around arteries in the basal ganglia and centrum semiovale (CSO). In a first experiment, the assessment of local alignment of the SAS and PVS vector field is described. In a second experiment, the first eigenvector (e1) orientation of each voxel within the SAS and PVS is compared to the local vessel orientation. Three metrics, describing the orientation of the principal CSF mobility orientation compared to the vessel orientation, are derived: Daxial, Dradial and Dspiral. For each parameter, variations in orientation over the cardiac cycle are analyzed and compared to a random binned signal in order to assess the influence of cardiac pulsatility on each parameter. Results show a clear preference for axial orientations in the SAS, with significant differences when comparing to a negative control ROI(p < 0.001), suggesting a difference in orientation patterns or displacement speeds between ROIs. The PVS ROIs indicate only small variations in orientation values from the negative control, with the basal ganglia ROI showing a significant difference from the negative control (p < 0.05), but not the CSO ROI. For all ROIs, the influence of cardiac pulsatility on the three parameters is significant when comparing to the random binned signal (p < 0.05). Further research on combinations with scalar f ield approaches and secondary and tertiary eigenvectors and values are advised to further assess what could cause certain directional patterns and reveal more underlying information about the CSF-mobility tensor. Also, data acquisition with multiple b-values could better characterize any possible variations in displacement speeds in different CSF-filled regions.

In this work, we present VisuaLayered, the implementation of a combined analysis workflow for pigment identification. VisuaLayered is an integrated, interactive system that focuses on the combined visual analysis of Macro X-Ray Fluorescence (MA-XRF) and Reflectance Imaging Spectroscopy (RIS) data.

Analysing paintings for pigment identification is relevant for many applications in the cultural heritage domain, such as conservation and restoration.
Domain experts use non-invasive scanning techniques as an initial step in their analysis. Two such techniques are MA-XRF and RIS. They provide hyperspectral data on the elemental and molecular composition of pigments, respectively. Domain experts analyse these two complementary data modalities in order to determine the pigments present in the different paint layers of a painting. However, due to the size and high-dimensionality of these datasets, experts have problems with efficiently analysing the data. In general, they examine the two data modalities separately in the analysis workflow and use their knowledge to unify all the information without additional software support, as there is no integrated system that is designed specifically for the combined analysis of MA-XRF and RIS data.

We worked in collaboration with domain experts from the Rijksmuseum, Amsterdam in order to design and implement VisuaLayered based on current domain practices. We use t-SNE for projecting the high-dimensional data into a two dimensional space, which the user can interactively explore in combination with other linked views in order to find connections between the two data modalities. With our system, experts can explore the spatial distribution and the correlation between pixels that have similar molecular and/or elemental compositions. Additionally, for the RIS data, we support endmember identification and analysis based on the pigments' spectral profiles.
We tested the efficiency of our system with respect to the designed workflow in a case study evaluation with our collaborator. They successfully used VisuaLayered for the analysis of one painting and found the views combining the two data modalities very useful for better understanding the relation between them. Moreover, they were able to identify new pigments, that they missed when using existing software.

Survival analysis is a statistical method used to predict when an event will occur. Machine learning survival models have been used in many cancer studies. However, machine learning models may not always be interpretable. The current lack of research for explainable survival analysis for urothelial cancer prompted this study. This study offers an insight into the generalizability and explainability of machine learning models for urothelial cancer. We also determine how we can make the models interpretable in the presence of collinearity. In this study, we compared the performance of the models; Rank Linear Support Vector Machine (SVM), Rank Kernel SVM, Coxnet, Random Survival Forest (RSF), and Gradient Boosting (Gboost). We used the Memorial Sloan Kettering (MSK) and The Cancer Genome Atlas (TCGA) datasets. We used gene expression variables and clinical variables to train our models. We evaluated these models based on the C-index. We used Permutation Feature Importance (PFI), a model-agnostic method, to explain our models and used Principal Component Analysis (PCA) to deal with collinearity. We determined that the best linear model was Rank Linear SVM (C-index = 0.58) and the best non-linear model was RSF (C-index = 0.63). Using PFI showed that some of the top-most important genes were expressed in urothelial cancer, one of them even being a prognostic marker. With PCA, we were able to deal with collinearity, and the performance using PCA was comparable to models not using it. PFI with PCA showed that processes exhibited in the top genes were prevalent in cancer.

In this paper, the DSNet framework used for automatic video summarization gets reviewed when using action localization datasets. The problem facing video summarizations using deep learning techniques is that datasets can be subjective depending on preferences of human annotators, making for noise in the labeling. This paper will look at a anchor-based approach and anchor-free approach which were introduced by the DSNet framework. More specific it will evaluate in experiments using different hyper-parameters if these approaches gain an increased performances when using action localization datasets instead. These results will show the increase in accuracy when using action localization datasets. Moreover it will compare the different approaches, meaning anchor-based and anchor-free, and see if they still have comparable performance with the method.

Video summarization is a task which many researchers have tried to automate with deep learning methods. One of these methods is the SUM-GAN-AAE algorithm developed by Apostolidis et al. which is an unsupervised machine learning method evaluated in this study. The research aims at testing the algorithm's performance on the Breakfast dataset, which is an action localization dataset, and evaluate it with rank correlation coefficients. Parameter optimization was performed to tune the learning rate of the system according to the Breakfast dataset. Then, by using k-fold cross-validation, three metrics were used to evaluate the trained model - F-Score, Kendall's τ and Spearman's ρ. Analysis of the results indicates a high F-Score as reported by the SUM-GAN-AAE paper but low rank correlation coefficients. Moreover, plotting importance scores per frame demonstrates the algorithm's inability to select key frames. The findings suggest that F-Score is not a fitting metric to use in the context of video summarization and the SUM-GAN-AAE algorithm performs poorly not only on action localization datasets but also on video summarization ones such as SumMe.

In the problem of video summarization, the goal is to select a subset of the input frames conveying the most important information of the input video. The collection of data proves to be a challenging task. In part because there exists a disagreement among human annotators on what segments of a video should be considered important for a summary. In this study we analyse a new dataset created with the goal of increasing agreement between the human annotators. The dataset has been created with the use of a novel annotation method, which uses existing action localization labels for segmenting the videos. We train a supervised and an unsupervised deep learning framework on popularly used benchmark datasets and the new dataset. Experimental results show the effectiveness of this novel summary annotation method in improving
the agreement between annotators. Analysis reveals some issues with the evaluation of the deep learning framework.

There is growing research on automated video summarization following the rise of video content. However, the subjectivity of the task itself is still an issue to address. This subjectivity stems from the fact that there can be different summaries for the same video depending on which parts one considers important. Supervised models especially suffer from this problem as they need informative labels to learn from. As a result, upon evaluation, supervised models appear to perform worse than unsupervised models. This inspired our research on whether action localization can aid the video summarization process. To investigate this issue, this paper will answer the question of how well VASNet, a supervised video summarization model, can predict summaries for videos in an action localization dataset. This involves investigating whether action localization can produce well-correlated human-generated summaries and how it affects the quality of predicted summaries. Our findings reveal that there is a positive indication that action localization can aid in producing more well-correlated human summaries. In addition, we have observed that upon comparison with several video summarization models, VASNet has performed well and that in general, supervised models appear to outperform unsupervised ones when trained with an action localization dataset.