Search

Dynamic positron emission tomography and kinetic modeling play a critical role in tracer development research using small animals. Kinetic modeling from dynamic PET imaging requires accurate knowledge of an input function, ideally determined through arterial blood sampling. Arterial cannulation in mice, however, requires complex, time-consuming and terminal surgery, meaning that longitudinal studies are impossible. The aim of the current work was to develop and evaluate a non-invasive, deep-learning-based prediction model (DLIF) that directly takes the PET data as input to predict a usable input function. We first trained and evaluated the DLIF model on 68 [18F]Fluorodeoxyglucose mouse scans with image-derived targets using cross validation. Subsequently, we evaluated the performance of a trained DLIF model on an external dataset consisting of 8 mouse scans where the input function was measured by continuous arterial blood sampling. The results showed that the predicted DLIF and image-derived targets were similar, and the net influx rate constants following from Patlak modeling using DLIF as input function were strongly correlated to the corresponding values obtained using the image-derived input function. There were somewhat larger discrepancies when evaluating the model on the external dataset, which could be attributed to systematic differences in the experimental setup between the two datasets. In conclusion, our non-invasive DLIF prediction method may be a viable alternative to arterial blood sampling in small animal [18F]FDG imaging. With further validation, DLIF could overcome the need for arterial cannulation and allow fully quantitative and longitudinal experiments in PET imaging studies of mice.

The analysis of maritime traffic patterns for safety and security purposes is increasing in importance and, hence, Vessel Traffic Service operators need efficient and contextualized tools for the detection of abnormal maritime behavior. Current models lack interpretability and contextualization of their predictions and are generally not quantitatively evaluated on a large annotated dataset comprising all expected traffic in a Region of Interest. We propose a model for the detection of abnormal maritime behaviors that provides the closest behaviors as context to the predictions. The normalcy model relies on two-step clustering, which is first computed based on the positions of the vessels and then refined based on their kinematics. We design for each step a similarity measure, which combined are able to distinguish boats cruising shipping lanes in different directions, but also vessels with more freedom, such as pilot boats. Our proposed abnormality detection model achieved, on a large annotated dataset extracted from AIS logs that we publish, an ROC-AUC of 0.79, which is on a par with State-of-the-Art deep neural networks, while being more computationally efficient and more interpretable, thanks to the contextualization offered by our two-step clustering.

Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently to gain insight into, among others, DNNs’ generalization ability. However, it is by no means obvious how to estimate the mutual information (MI) between each hidden layer and the input/desired output to construct the IP. For instance, hidden layers with many neurons require MI estimators with robustness toward the high dimensionality associated with such layers. MI estimators should also be able to handle convolutional layers while at the same time being computationally tractable to scale to large networks. Existing IP methods have not been able to study truly deep convolutional neural networks (CNNs). We propose an IP analysis using the new matrix-based Rényi’s entropy coupled with tensor kernels, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data. Our results shed new light on previous studies concerning small-scale DNNs using a completely new approach. We provide a comprehensive IP analysis of large-scale CNNs, investigating the different training phases and providing new insights into the training dynamics of large-scale neural networks.

Age-reading of fish otoliths (ear stones) is important for the sustainable management of fish resources. However, the procedure is challenging and requires experienced readers to carefully examine annual growth zones. In a recent study, convolutional neural networks (CNNs) have been demonstrated to perform reasonably well on automatically predicting fish age from otolith images. In the present study, we carefully investigate the prediction rule learned by such neural networks to provide insight into the features that identify certain fish age ranges. For this purpose, a recent technique for visualizing and analyzing the predictions of the neural networks was applied to different versions of the otolith images. The results indicate that supplementary knowledge about the internal structure improves the results for the youngest age groups, compared to using only the contour shape attribute of the otolith. However, the contour shape and size attributes are, in general, sufficient for older age groups. In addition, within specific age ranges we find that the network tends to focus on particular areas of the otoliths and that the most discriminating factors seem to be related to the central part and the outer edge of the otolith. Explaining age predictions from otolith images as done in this study will hopefully help build confidence in the potential of deep learning algorithms for automatic age prediction, as well as improve the quality of the age estimation.