Hippocampal representations for deep learning on Alzheimer's disease.

Deep learning offers a powerful approach for analyzing hippocampal changes in Alzheimer's disease (AD) without relying on handcrafted features. Nevertheless, an input format needs to be selected to pass the image information to the neural network, which has wide ramifications for the analysis, but has not been evaluated yet. We compare five hippocampal representations (and their respective tailored network architectures) that span from raw images to geometric representations like meshes and point clouds. We performed a thorough evaluation for the prediction of AD diagnosis and time-to-dementia prediction with experiments on an independent test dataset. In addition, we evaluated the ease of interpretability for each representation-network pair. Our results show that choosing an appropriate representation of the hippocampus for predicting Alzheimer's disease with deep learning is crucial, since it impacts performance and ease of interpretation.

The Medical Segmentation Decathlon.

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Discriminative and generative models for anatomical shape analysis on point clouds with deep neural networks.

We introduce deep neural networks for the analysis of anatomical shapes that learn a low-dimensional shape representation from the given task, instead of relying on hand-engineered representations. Our framework is modular and consists of several computing blocks that perform fundamental shape processing tasks. The networks operate on unordered point clouds and provide invariance to similarity transformations, avoiding the need to identify point correspondences between shapes. Based on the framework, we assemble a discriminative model for disease classification and age regression, as well as a generative model for the accruate reconstruction of shapes. In particular, we propose a conditional generative model, where the condition vector provides a mechanism to control the generative process. For instance, it enables to assess shape variations specific to a particular diagnosis, when passing it as side information. Next to working on single shapes, we introduce an extension for the joint analysis of multiple anatomical structures, where the simultaneous modeling of multiple structures can lead to a more compact encoding and a better understanding of disorders. We demonstrate the advantages of our framework in comprehensive experiments on real and synthetic data. The key insights are that (i) learning a shape representation specific to the given task yields higher performance than alternative shape descriptors, (ii) multi-structure analysis is both more efficient and more accurate than single-structure analysis, and (iii) point clouds generated by our model capture morphological differences associated to Alzheimer's disease, to the point that they can be used to train a discriminative model for disease classification. Our framework naturally scales to the analysis of large datasets, giving it the potential to learn characteristic variations in large populations.

Recalibrating 3D ConvNets with Project & Excite.

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for segmentation tasks in computer vision and medical imaging. Recently, computational blocks termed squeeze and excitation (SE) have been introduced to recalibrate F-CNN feature maps both channel- and spatial-wise, boosting segmentation performance while only minimally increasing the model complexity. So far, the development of SE blocks has focused on 2D architectures. For volumetric medical images, however, 3D F-CNNs are a natural choice. In this article, we extend existing 2D recalibration methods to 3D and propose a generic compress-process-recalibrate pipeline for easy comparison of such blocks. We further introduce Project & Excite (PE) modules, customized for 3D networks. In contrast to existing modules, Project & Excite does not perform global average pooling but compresses feature maps along different spatial dimensions of the tensor separately to retain more spatial information that is subsequently used in the excitation step. We evaluate the modules on two challenging tasks, whole-brain segmentation of MRI scans and whole-body segmentation of CT scans. We demonstrate that PE modules can be easily integrated into 3D F-CNNs, boosting performance up to 0.3 in Dice Score and outperforming 3D extensions of other recalibration blocks, while only marginally increasing the model complexity. Our code is publicly available on https://github.com/ai-med/squeezeandexcitation.

Chloride and sulphate toxicity to Hydropsyche exocellata (Trichoptera, Hydropsychidae): Exploring intraspecific variation and sub-lethal endpoints.

The rivers and streams of the world are becoming saltier due to human activities. In spite of the potential damage that salt pollution can cause on freshwater ecosystems, this is an issue that is currently poorly managed. Here we explored intraspecific differences in the sensitivity of freshwater fauna to two major ions (Cl(-) and SO4(2-)) using the net-spinning caddisfly Hydropsyche exocellata Dufour 1841 (Trichoptera, Hydropsychidae) as a model organism. We exposed H. exocellata to saline solutions (reaching a conductivity of 2.5mScm(-1)) with Cl(-):SO4(2-) ratios similar to those occurring in effluents coming from the meat, mining and paper industries, which release dissolved salts to rivers and streams in Spain. We used two different populations, coming from low and high conductivity streams. To assess toxicity, we measured sub-lethal endpoints: locomotion, symmetry of the food-capturing nets and oxidative stress biomarkers. According to biomarkers and net building, the population historically exposed to lower conductivities (B10) showed higher levels of stress than the population historically exposed to higher conductivities (L102). However, the differences between populations were not strong. For example, net symmetry was lower in the B10 than in the L102 only 48h after treatment was applied, and biomarkers showed a variety of responses, with no discernable pattern. Also, treatment effects were rather weak, i.e. only some endpoints, and in most cases only in the B10 population, showed a significant response to treatment. The lack of consistent differences between populations and treatments could be related to the high salt tolerance of H. exocellata, since both populations were collected from streams with relatively high conductivities. The sub-lethal effects tested in this study can offer an interesting and promising tool to monitor freshwater salinization by combining physiological and behavioural bioindicators.