We propose the use of dilated filters to construct an aggregation module in a multicolumn convolutional neural network for perspective-free counting. Counting is a common problem in computer vision (e.g. traffic on the street or pedestrians in a crowd). Modern approaches to the counting problem involve the production of a density map via regression whose integral is equal to the number of objects in the image. However, objects in the image can occur at different scales (e.g. due to perspective effects) which can make it difficult for a learning agent to learn the proper density map. While the use of multiple columns to extract multiscale information from images has been shown before, our approach aggregates the multiscale information gathered by the multicolumn convolutional neural network to improve performance. Our experiments show that our proposed network outperforms the state-of-the-art on many benchmark datasets, and also that using our aggregation module in combination with a higher number of columns is beneficial for multiscale counting.

The discovery that experimental delivery of dsRNA can induce gene silencing at target genes revolutionized genetics research, by both uncovering essential biological processes and creating new tools for developmental geneticists. However, wild-type C. elegans strains vary dramatically in their response to exogenous RNAi, challenging our characterization of RNAi in the lab relative to its activity and significance in nature. Here, we investigate why some strains fail to mount a robust RNAi response to germline targets. We observe diversity in mechanism: in some strains, the response is stochastic, either on or off among individuals, while in others the response is consistent but delayed. Increased activity of the Argonaute PPW-1, which is required for germline RNAi in the laboratory strain N2, rescues the response in some strains, but dampens it further in others. Across strains, we observe variability in expression of known RNAi genes and strain-specific instances of pseudogenization and allelic divergence. Our results support the conclusions that Argonautes share overlapping functions, that germline RNAi incompetence is strain-specific but likely caused by genetic variants at common genes, and that RNAi pathways are evolving rapidly and dynamically. This work expands our understanding of RNAi by identifying conserved and variable pathway components, and it offers new access into characterizing gene function, identifying pathway interactions, and elucidating the biological significance of RNAi.

We present a simple, yet effective, auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of Local Shape Descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors are designed to capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a large study comparing several existing methods across various specimen, imaging techniques, and resolutions, we find that auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinitybased segmentation methods to be on par with the current state of the art for neuron segmentation (Flood-Filling Networks, FFN), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets. Implementations of the new auxiliary learning task, network architectures, training, prediction, and evaluation code, as well as the datasets used in this study are publicly available as a benchmark for future method contributions.

We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a study comparing several existing methods across various specimen, imaging techniques, and resolutions, auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinity-based segmentation methods to be on par with the current state of the art for neuron segmentation (flood-filling networks), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets.

3D snapshot microscopy enables volumetric imaging as fast as a camera allows by capturing a 3D volume in a single 2D camera image, and has found a variety of biological applications such as whole brain imaging of fast neural activity in larval zebrafish. The optimal microscope design for this optical 3D-to-2D encoding to preserve as much 3D information as possible is generally unknown and sample-dependent. Highly-programmable optical elements create new possibilities for sample-specific computational optimization of microscope parameters, e.g. tuning the collection of light for a given sample structure, especially using deep learning. This involves a differentiable simulation of light propagation through the programmable microscope and a neural network to reconstruct volumes from the microscope image. We introduce a class of global kernel Fourier convolutional neural networks which can efficiently integrate the globally mixed information encoded in a 3D snapshot image. We show in silico that our proposed global Fourier convolutional networks succeed in large field-of-view volume reconstruction and microscope parameter optimization where traditional networks fail.Preprint.