News and hype surround the field of radiology with headlines around the world purporting that it will be disrupted overnight. Few companies though really have the evidence to back up these claims. A combination of factors have led to this field being a target for innovators including the expansion of image archiving, the increase of diagnostic image-sharing and the computer-readable DICOM format. These innovative companies are seeking to apply AI, Machine and Deep Learning to this field in the hope of achieving time and cost savings, and to help doctors detect changes such as tumors, hardening of the arteries and provide highly accurate measurements of organs and blood flow. Even though in principal the challenges in this field are ripe for the application of modern technology, there are considerable market barriers new companies must face.

Experimental determination of protein function is resource-consuming. As an alternative, computational prediction of protein function has received attention. In this context, protein structural classification (PSC) can help, by allowing for determining structural classes of currently unclassified proteins based on their features, and then relying on the fact that proteins with similar structures have similar functions. Existing PSC approaches rely on sequence-based or direct ("raw") 3-dimensional (3D) structure-based protein features. Instead, we first model 3D structures as protein structure networks (PSNs). Then, we use ("processed") network-based features for PSC. We are the first ones to do so. We propose the use of graphlets, state-of-the-art features in many domains of network science, in the task of PSC. Moreover, because graphlets can deal only with unweighted PSNs, and because accounting for edge weights when constructing PSNs could improve PSC accuracy, we also propose a deep learning framework that automatically learns network features from the weighted PSNs. When evaluated on a large set of 9,509 CATH and 11,451 SCOP protein domains, our proposed approaches are superior to existing PSC approaches in terms of both accuracy and running time.

Unsupervised domain adaptation tries to adapt a classifier trained on a labeled source domain to a related but unlabeled target domain. Methods based on adversarial learning try to learn a representation that is at the same time discriminative for the labels yet incapable of discriminating the domains. We propose a very simple and efficient method based on this approach which only aligns predicted class probabilities across domains. Experiments show that this strikingly simple adversarial domain adaptation method is robust to overfitting and achieves state-of-the-art results on datasets for image classification.

Conventional wisdom holds that interleaved pooling layers in convolutional neural networks lead to stability to small translations and deformations. In this work, we investigate this claim empirically. We find that while pooling confers stability to deformation at initialization, the deformation stability at each layer changes significantly over the course of training and even decreases in some layers, suggesting that deformation stability is not unilaterally helpful. Surprisingly, after training, the pattern of deformation stability across layers is largely independent of whether or not pooling was present. We then show that a significant factor in determining deformation stability is filter smoothness. Moreover, filter smoothness and deformation stability are not simply a consequence of the distribution of input images, but depend crucially on the joint distribution of images and labels. This work demonstrates a way in which biases such as deformation stability can in fact be learned and provides an example of understanding how a simple property of learned network weights contributes to the overall network computation.

We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks. Our main hypothesis is that constraining the Lipschitz constant of a networks will have a regularising effect. To this end, we provide a simple technique for computing the Lipschitz constant of a feed forward neural network composed of commonly used layer types. This technique is then utilised to formulate training a Lipschitz continuous neural network as a constrained optimisation problem, which can be easily solved using projected stochastic gradient methods. Our evaluation study shows that, in isolation, our method performs comparatively to state-of-the-art regularisation techniques. Moreover, when combined with existing approaches to regularising neural networks the performance gains are cumulative.

Semantic segmentation is an established while rapidly evolving field in medical imaging. In this paper we focus on the segmentation of brain Magnetic Resonance Images (MRI) into cerebral structures using convolutional neural networks (CNN). CNNs achieve good performance by finding effective high dimensional image features describing the patch content only. In this work, we propose different ways to introduce spatial constraints into the network to further reduce prediction inconsistencies. A patch based CNN architecture was trained, making use of multiple scales to gather contextual information. Spatial constraints were introduced within the CNN through a distance to landmarks feature or through the integration of a probability atlas. We demonstrate experimentally that using spatial information helps to reduce segmentation inconsistencies.

Navigated 2D multi-slice dynamic Magnetic Resonance (MR) imaging enables high contrast 4D MR imaging during free breathing and provides in-vivo observations for treatment planning and guidance. Navigator slices are vital for retrospective stacking of 2D data slices in this method. However, they also prolong the acquisition sessions. Temporal interpolation of navigator slices an be used to reduce the number of navigator acquisitions without degrading specificity in stacking. In this work, we propose a convolutional neural network (CNN) based method for temporal interpolation via motion field prediction. The proposed formulation incorporates the prior knowledge that a motion field underlies changes in the image intensities over time. Previous approaches that interpolate directly in the intensity space are prone to produce blurry images or even remove structures in the images. Our method avoids such problems and faithfully preserves the information in the image. Further, an important advantage of our formulation is that it provides an unsupervised estimation of bi-directional motion fields. We show that these motion fields can be used to halve the number of registrations required during 4D reconstruction, thus substantially reducing the reconstruction time.

Convolutional Neural Networks (CNNs) require a large amount of annotated data to learn from, which is often difficult to obtain in the medical domain. In this paper we show that the sample complexity of CNNs can be significantly improved by using 3D roto-translation group convolutions (G-Convs) instead of the more conventional translational convolutions. These 3D G-CNNs were applied to the problem of false positive reduction for pulmonary nodule detection, and proved to be substantially more effective in terms of performance, sensitivity to malignant nodules, and speed of convergence compared to a strong and comparable baseline architecture with regular convolutions, data augmentation and a similar number of parameters. For every dataset size tested, the G-CNN achieved a FROC score close to the CNN trained on ten times more data.

This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with a convolution neural network (CNN) attention mechanism and training stacking-based ensembles for each of the sub-tasks. Our algorithm reached 3rd and 1st places in the valence ordinal classification sub-tasks in English and Spanish, respectively.

We propose a new generative model for domain adaptation, in which training data (source domain) and test data (target domain) come from different distributions. An essential problem in domain adaptation is to understand how the distribution shifts across domains. For this purpose, we propose a generative domain adaptation network to understand and identify the domain changes, which enables the generation of new domains. In addition, focusing on single domain adaptation, we demonstrate how our model recovers the joint distribution on the target domain from unlabeled target domain data by transferring valuable information between domains. Finally, to improve transfer efficiency, we build a causal generative domain adaptation network by decomposing the joint distribution of features and labels into a series of causal modules according to a causal model. Due to the modularity property of a causal model, we can improve the identification of distribution changes by modeling each causal modules separately. With the proposed adaptation networks, the predictive model on the target domain can be easily trained on data sampled from the learned networks. We demonstrate the efficacy of our method on both synthetic and real data experiments.