Search

For large-scale vision tasks in biomedical images, the labeled data is often limited to train effective deep models. Active learning is a common solution, where a query suggestion method selects representative unlabeled samples for annotation, and the new labels are used to improve the base model. However, most query suggestion models optimize their learnable parameters only on the limited labeled data and consequently become less effective for the more challenging unlabeled data. To tackle this, we propose a two-stream active query suggestion approach. In addition to the supervised feature extractor, we introduce an unsupervised one optimized on all raw images to capture diverse image features, which can later be improved by fine-tuning on new labels. As a use case, we build an end-to-end active learning framework with our query suggestion method for 3D synapse detection and mitochondria segmentation in connectomics. With the framework, we curate, to our best knowledge, the largest connectomics dataset with dense synapses and mitochondria annotation. On this new dataset, our method outperforms previous state-of-the-art methods by 3.1% for synapse and 3.8% for mitochondria in terms of region-of-interest proposal accuracy. We also apply our method to image classification, where it outperforms previous approaches on CIFAR-10 under the same limited annotation budget. The project page is https://zudi-lin.github.io/projects/#two_stream_active.

We propose a semi-supervised learning approach for video classification, VideoSSL, using convolutional neural networks (CNN). Like other computer vision tasks, existing supervised video classification methods demand a large amount of labeled data to attain good performance. However, annotation of a large dataset is expensive and time consuming. To minimize the dependence on a large annotated dataset, our proposed semi-supervised method trains from a small number of labeled examples and exploits two regulatory signals from unlabeled data. The first signal is the pseudo-labels of unlabeled examples computed from the confidences of the CNN being trained. The other is the normalized probabilities, as predicted by an image classifier CNN, that captures the information about appearances of the interesting objects in the video. We show that, under the supervision of these guiding signals from unlabeled examples, a video classification CNN can achieve impressive performances utilizing a small fraction of annotated examples on three publicly available datasets: UCF101, HMDB51, and Kinetics.

Most current state-of-the-art connectome reconstruction pipelines have two major steps: initial pixel-based segmentation with affinity prediction and watershed transform, and refined segmentation by merging over-segmented regions. These methods rely only on local context and are typically agnostic to the underlying biology. Since a few merge errors can lead to several incorrectly merged neuronal processes, these algorithms are currently tuned towards over-segmentation producing an overburden of costly proofreading. We propose a third step for connectomics reconstruction pipelines to refine an over-segmentation using both local and global context with an emphasis on adhering to the underlying biology. We first extract a graph from an input segmentation where nodes correspond to segment labels and edges indicate potential split errors in the over-segmentation. In order to increase throughput and allow for large-scale reconstruction, we employ biologically inspired geometric constraints based on neuron morphology to reduce the number of nodes and edges. Next, two neural networks learn these neuronal shapes to further aid the graph construction process. Lastly, we reformulate the region merging problem as a graph partitioning one to leverage global context. We demonstrate the performance of our approach on four real-world connectomics datasets with an average variation of information improvement of 21.3%.

Understanding the circuit mechanisms behind motion detection is a long-standing question in visual neuroscience. In Drosophila melanogaster, recently discovered synapse-level connectomes in the optic lobe, particularly in ON-pathway (T4) receptive-field circuits, in concert with physiological studies, suggest a motion model that is increasingly intricate when compared with the ubiquitous Hassenstein-Reichardt model. By contrast, our knowledge of OFF-pathway (T5) has been incomplete. Here, we present a conclusive and comprehensive connectome that, for the first time, integrates detailed connectivity information for inputs to both the T4 and T5 pathways in a single EM dataset covering the entire optic lobe. With novel reconstruction methods using automated synapse prediction suited to such a large connectome, we successfully corroborate previous findings in the T4 pathway and comprehensively identify inputs and receptive fields for T5. Although the two pathways are probably evolutionarily linked and exhibit many similarities, we uncover interesting differences and interactions that may underlie their distinct functional properties.

Synaptic connectivity detection is a critical task for neural reconstruction from Electron Microscopy (EM) data. Most of the existing algorithms for synapse detection do not identify the cleft location and direction of connectivity simultaneously. The few methods that computes direction along with contact location have only been demonstrated to work on either dyadic (most common in vertebrate brain) or polyadic (found in fruit fly brain) synapses, but not on both types. In this paper, we present an algorithm to automatically predict the location as well as the direction of both dyadic and polyadic synapses. The proposed algorithm first generates candidate synaptic connections from voxelwise predictions of signed proximity generated by a 3D U-net. A second 3D CNN then prunes the set of candidates to produce the final detection of cleft and connectivity orientation. Experimental results demonstrate that the proposed method outperforms the existing methods for determining synapses in both rodent and fruit fly brain. (Code at: https://github.com/paragt/EMSynConn).

Understanding memory formation, storage and retrieval requires knowledge of the underlying neuronal circuits. In Drosophila, the mushroom body (MB) is the major site of associative learning. We reconstructed the morphologies and synaptic connections of all 983 neurons within the three functional units, or compartments, that compose the adult MB’s α lobe, using a dataset of isotropic 8 nm voxels collected by focused ion-beam milling scanning electron microscopy. We found that Kenyon cells (KCs), whose sparse activity encodes sensory information, each make multiple en passant synapses to MB output neurons (MBONs) in each compartment. Some MBONs have inputs from all KCs, while others differentially sample sensory modalities. Only 6% of KC>MBON synapses receive a direct synapse from a dopaminergic neuron (DAN). We identified two unanticipated classes of synapses, KC>DAN and DAN>MBON. DAN activation produces a slow depolarization of the MBON in these DAN>MBON synapses and can weaken memory recall. DOI: http://dx.doi.org/10.7554/eLife.26975.001

We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. An interactive training scheme reduces the extremely tedious manual annotation task that is typically required for deep networks to perform well on image segmentation problems. Our proposed method employs a feedback loop that captures sparse annotations using a graphical user interface, trains a deep neural network based on recent and past annotations, and displays the prediction output to users in almost real-time. Our implementation of the algorithm also allows multiple users to provide annotations in parallel and receive feedback from the same classifier. Quick feedback on classifier performance in an interactive setting enables users to identify and label examples that are more important than others for segmentation purposes. Our experiments show that an interactively-trained pixel classifier produces better region segmentation results on Electron Microscopy (EM) images than those generated by a network of the same architecture trained offline on exhaustive ground-truth labels.

We reconstructed the synaptic circuits of seven columns in the second neuropil or medulla behind the fly's compound eye. These neurons embody some of the most stereotyped circuits in one of the most miniaturized of animal brains. The reconstructions allow us, for the first time to our knowledge, to study variations between circuits in the medulla's neighboring columns. This variation in the number of synapses and the types of their synaptic partners has previously been little addressed because methods that visualize multiple circuits have not resolved detailed connections, and existing connectomic studies, which can see such connections, have not so far examined multiple reconstructions of the same circuit. Here, we address the omission by comparing the circuits common to all seven columns to assess variation in their connection strengths and the resultant rates of several different and distinct types of connection error. Error rates reveal that, overall

Connectomics has recently begun to image brain tissue at nanometer resolution, which produces petabytes of data. This data must be aligned, labeled, proofread, and formed into graphs, and each step of this process requires visualization for human verification. As such, we present the BUTTERFLY middleware, a scalable platform that can handle massive data for interactive visualization in connectomics. Our platform outputs image and geometry data suitable for hardware-accelerated rendering, and abstracts low-level data wrangling to enable faster development of new visualizations. We demonstrate scalability and extendability with a series of open source Web-based applications for every step of the typical connectomics workflow: data management and storage, informative queries, 2D and 3D visualizations, interactive editing, and graph-based analysis. We report design choices for all developed applications and describe typical scenarios of isolated and combined use in everyday connectomics research. In addition, we measure and optimize rendering throughput—from storage to display—in quantitative experiments. Finally, we share insights, experiences, and recommendations for creating an open source data management and interactive visualization platform for connectomics.

Pixel and superpixel classifiers have become essential tools for EM segmentation algorithms. Training these classifiers remains a major bottleneck primarily due to the requirement of completely annotating the dataset which is tedious, error-prone and costly. In this paper, we propose an interactive learning scheme for the superpixel classifier for EM segmentation. Our algorithm is 'active semi-supervised' because it requests the labels of a small number of examples from user and applies label propagation technique to generate these queries. Using only a small set (20%) of all datapoints, the proposed algorithm consistently generates a classifier almost as accurate as that estimated from a complete groundtruth. We provide segmentation results on multiple datasets to show the strength of these classifiers.

Electron Microscopy (EM) image (or volume) segmentation has become significantly important in recent years as an instrument for connectomics. This paper proposes a novel agglomerative framework for EM segmentation. In particular, given an over-segmented image or volume, we propose a novel framework for accurately clustering regions of the same neuron. Unlike existing agglomerative methods, the proposed context-aware algorithm divides superpixels (over-segmented regions) of different biological entities into different subsets and agglomerates them separately. In addition, this paper describes a "delayed" scheme for agglomerative clustering that postpones some of the merge decisions, pertaining to newly formed bodies, in order to generate a more confident boundary prediction. We report significant improvements attained by the proposed approach in segmentation accuracy over existing standard methods on 2D and 3D datasets.