Deep learning models have traditionally been developed and trained to perform specific tasks, which limits their generalizability across different domains. Recently, the field has experienced a paradigm shift toward foundation models, wherein AI systems are pre-trained on extensive datasets to support a broad range of tasks across multiple domains. This shift is particularly promising for ultrasound imaging, a relatively low-cost and versatile modality in clinical practice. However, their adoption remains limited due to challenges such as scarce labeled data, domain-specific variability, and the need for user expertise. This review first outlines the workflow and design principles of deep learning-based ultrasound clinical applications, with emphasis on advancements in supervised and self-supervised learning, discriminative models, generative AI models, foundation models, and other miscellaneous models. Recent literature on ultrasound image analysis is then reviewed in detail. Furthermore, deep learning-based ultrasound clinical applications are summarized, and the potential of foundation models to enhance diagnostic performance and expand the scope of ultrasound in clinical settings is highlighted. Finally, key challenges are discussed, and future directions for deep learning in clinical ultrasound are proposed.

Connectomics, a subfield of neuroscience, aims to map and analyze synapse-level wiring diagrams of the nervous system. While recent advances in deep learning have accelerated automated neuron and synapse segmentation, reconstructing accurate connectomes still demands extensive human proofreading to correct segmentation errors. We present SynAnno, an interactive tool designed to streamline and enhance the proofreading of synaptic annotations in large-scale connectomics datasets. SynAnno integrates into existing neuroscience workflows by enabling guided, neuron-centric proofreading. To address the challenges posed by the complex spatial branching of neurons, it introduces a structured workflow with an optimized traversal path and a 3D mini-map for tracking progress. In addition, SynAnno incorporates fine-tuned machine learning models to assist with error detection and correction, reducing the manual burden and increasing proofreading efficiency. We evaluate SynAnno through a user and case study involving seven neuroscience experts. Results show that SynAnno significantly accelerates synapse proofreading while reducing cognitive load and annotation errors through structured guidance and visualization support. The source code and interactive demo are available at: https://github.com/PytorchConnectomics/SynAnno.

Pulmonary diseases rank prominently among the principal causes of death worldwide. Curing them will require, among other things, a better understanding of the complex 3D tree-shaped structures within the pulmonary system, such as airways, arteries, and veins. Traditional approaches using high-resolution image stacks and standard CNNs on dense voxel grids face challenges in computational efficiency, limited resolution, local context, and inadequate preservation of shape topology. Our method addresses these issues by shifting from dense voxel to sparse point representation, offering better memory efficiency and global context utilization. However, the inherent sparsity in point representation can lead to a loss of crucial connectivity in tree-shaped structures. To mitigate this, we introduce graph learning on skeletonized structures, incorporating differentiable feature fusion for improved topology and long-distance context capture. Furthermore, we employ an implicit function for efficient conversion of sparse representations into dense reconstructions end-to-end. The proposed method not only delivers state-of-the-art performance in labeling accuracy, both overall and at key locations, but also enables efficient inference and the generation of closed surface shapes. Addressing data scarcity in this field, we have also curated a comprehensive dataset to validate our approach. Data and code are available at https://github.com/M3DV/pulmonary-tree-labeling.

While imaging techniques at macro and mesoscales have garnered substantial attention and resources, microscale Volume Electron Microscopy (vEM) imaging, capable of revealing intricate vascular details, has lacked the necessary benchmarking infrastructure. In this paper, we address a significant gap in this field of neuroimaging by introducing the first-in-class public benchmark, BvEM, designed specifically for cortical blood vessel segmentation in vEM images. Our BvEM benchmark is based on vEM image volumes from three mammals: adult mouse, macaque, and human. We standardized the resolution, addressed imaging variations, and meticulously annotated blood vessels through semi-automatic, manual, and quality control processes, ensuring high-quality 3D segmentation. Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation. To extend SAM from 2D to 3D volume segmentation, TriSAM employs a multi-seed tracking framework, leveraging the reliability of certain image planes for tracking while using others to identify potential turning points. This approach effectively achieves long-term 3D blood vessel segmentation without model training or fine-tuning. Experimental results show that TriSAM achieved superior performances on the BvEM benchmark across three species.

Accurate segmentation of anatomical substructures within 3D curvilinear structures in medical imaging remains challenging due to their complex geometry and the scarcity of diverse, large-scale datasets for algorithm development and evaluation. In this paper, we use dendritic spine segmentation as a case study and address these challenges by introducing a novel Frenet-Serret Frame-based Decomposition, which decomposes 3D curvilinear structures into a globally smooth continuous curve that captures the overall shape, and a cylindrical primitive that encodes local geometric properties. This approach leverages Frenet-Serret Frames and arc length parameterization to preserve essential geometric features while reducing representational complexity, facilitating data-efficient learning, improved segmentation accuracy, and generalization on 3D curvilinear structures. To rigorously evaluate our method, we introduce two datasets: CurviSeg, a synthetic dataset for 3D curvilinear structure segmentation that validates our method's key properties, and DenSpineEM, a benchmark for dendritic spine segmentation, which comprises 4,476 manually annotated spines from 70 dendrites across three public electron microscopy datasets, covering multiple brain regions and species. Our experiments on DenSpineEM demonstrate exceptional cross-region and cross-species generalization: models trained on the mouse somatosensory cortex subset achieve 94.43% Dice, maintaining strong performance in zero-shot segmentation on both mouse visual cortex (95.61% Dice) and human frontal lobe (86.63% Dice) subsets. Moreover, we test the generalizability of our method on the IntrA dataset, where it achieves 77.08% Dice (5.29% higher than prior arts) on intracranial aneurysm segmentation from entire artery models. These findings demonstrate the potential of our approach for accurately analyzing complex curvilinear structures across diverse medical imaging fields. Our dataset, code, and models are available at https://github.com/VCG/FFD4DenSpineEM to support future research.

Rib fractures are a common and potentially severe injury that can be challenging and labor-intensive to detect in CT scans. While there have been efforts to address this field, the lack of large-scale annotated datasets and evaluation benchmarks has hindered the development and validation of deep learning algorithms. To address this issue, the RibFrac Challenge was introduced, providing a benchmark dataset of over 5,000 rib fractures from 660 CT scans, with voxel-level instance mask annotations and diagnosis labels for four clinical categories (buckle, nondisplaced, displaced, or segmental). The challenge includes two tracks: a detection (instance segmentation) track evaluated by an FROC-style metric and a classification track evaluated by an F1-style metric. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts. Nevertheless, the current rib fracture classification solutions are hardly clinically applicable, which can be an interesting area in the future. As an active benchmark and research resource, the data and online evaluation of the RibFrac Challenge are available at the challenge website (https://ribfrac.grand-challenge.org/). In addition, we further analyzed the impact of two post-challenge advancements-large-scale pretraining and rib segmentation-based on our internal baseline for rib fracture detection. These findings lay a foundation for future research and development in AI-assisted rib fracture diagnosis.

Current approaches to Video Question Answering (VideoQA) primarily focus on cross-modality matching, which is limited by the requirement for extensive data annotations and the insufficient capacity for causal reasoning (e.g. attributing accidents). To address these challenges, we introduce a causal framework for video reasoning, termed Learning Latent Causal Processes (LLCP). At the heart of LLCP lies a multivariate generative model designed to analyze the spatial-temporal dynamics of objects within events. Leveraging the inherent modularity of causal mechanisms, we train the model through self-supervised local auto-regression eliminating the need for annotated question-answer pairs. During inference, the model is applied to answer two types of reasoning questions: accident attribution, which infers the cause from observed effects, and counterfactual prediction, which predicts the effects of counterfactual conditions given the factual evidence. In the first scenario, we identify variables that deviate from the established distribution by the learned model, signifying the root cause of accidents. In the second scenario, we replace embeddings of previous variables with counterfactual ones, enabling us to forecast potential developments. Once we have identified these cause/effect variables, natural language answers are derived through a combination of grammatical parsing and a pre-trained vision-language model. We assess the efficacy of LLCP on both synthetic and real-world data, demonstrating comparable performance to supervised methods despite our framework using no paired textual annotations.

Few-shot action recognition aims at quickly adapting a pre-trained model to the novel data with a distribution shift using only a limited number of samples. Key challenges include how to identify and leverage the transferable knowledge learned by the pre-trained model. We therefore propose CDTD, or Causal Domain-Invariant Temporal Dynamics for knowledge transfer. To identify the temporally invariant and variant representations, we employ the causal representation learning methods for unsupervised pertaining, and then tune the classifier with supervisions in next stage. Specifically, we assume the domain information can be well estimated and the pre-trained temporal dynamic generation and transition models can be well transferred. During adaptation, we fix the transferable temporal dynamics and update the image encoder and domain estimator. The efficacy of our approach is revealed by the superior accuracy of CDTD over leading alternatives across standard few-shot action recognition datasets.

Social relation reasoning aims to identify relation categories such as friends, spouses, and colleagues from images. While current methods adopt the paradigm of training a dedicated network end-to-end using labeled image data, they are limited in terms of generalizability and interpretability. To address these issues, we first present a simple yet well-crafted framework named SocialGPT, which combines the perception capability of Vision Foundation Models (VFMs) and the reasoning capability of Large Language Models (LLMs) within a modular framework, providing a strong baseline for social relation recognition. Specifically, we instruct VFMs to translate image content into a textual social story, and then utilize LLMs for text-based reasoning. SocialGPT introduces systematic design principles to adapt VFMs and LLMs separately and bridge their gaps. Without additional model training, it achieves competitive zero-shot results on two databases while offering interpretable answers, as LLMs can generate language-based explanations for the decisions. The manual prompt design process for LLMs at the reasoning phase is tedious and an automated prompt optimization method is desired. As we essentially convert a visual classification task into a generative task of LLMs, automatic prompt optimization encounters a unique long prompt optimization issue. To address this issue, we further propose the Greedy Segment Prompt Optimization (GSPO), which performs a greedy search by utilizing gradient information at the segment level. Experimental results show that GSPO significantly improves performance, and our method also generalizes to different image styles. The code is available at https://github.com/Mengzibin/SocialGPT.

Traditional accessibility methods like alternative text and data tables typically underrepresent data visualization’s full potential. Keyboard-based chart navigation has emerged as a potential solution, yet efficient data exploration remains challenging. We present VizAbility, a novel system that enriches chart content navigation with conversational interaction, enabling users to use natural language for querying visual data trends. VizAbility adapts to the user’s navigation context for improved response accuracy and facilitates verbal command-based chart navigation. Furthermore, it can address queries for contextual information, designed to address the needs of visually impaired users. We designed a large language model (LLM)-based pipeline to address these user queries, leveraging chart data & encoding, user context, and external web knowledge. We conducted both qualitative and quantitative studies to evaluate VizAbility’s multimodal approach. We discuss further opportunities based on the results, including improved benchmark testing, incorporation of vision models, and integration with visualization workflows.

Automatic rib labeling and anatomical centerline extraction are common prerequisites for various clinical applications. Prior studies either use in-house datasets that are inaccessible to communities, or focus on rib segmentation that neglects the clinical significance of rib labeling. To address these issues, we extend our prior dataset (RibSeg) on the binary rib segmentation task to a comprehensive benchmark, named RibSeg v2, with 660 CT scans (15,466 individual ribs in total) and annotations manually inspected by experts for rib labeling and anatomical centerline extraction. Based on the RibSeg v2, we develop a pipeline including deep learning-based methods for rib labeling, and a skeletonization-based method for centerline extraction. To improve computational efficiency, we propose a sparse point cloud representation of CT scans and compare it with standard dense voxel grids. Moreover, we design and analyze evaluation metrics to address the key challenges of each task. Our dataset, code, and model are available online to facilitate open research at https://github.com/M3DV/RibSeg.

The size of image volumes in connectomics studies now reaches terabyte and often petabyte scales with a great diversity of appearance due to different sample preparation procedures. However, manual annotation of neuronal structures (e.g., synapses) in these huge image volumes is time-consuming, leading to limited labeled training data often smaller than 0.001% of the large-scale image volumes in application. Methods that can utilize in-domain labeled data and generalize to out-of-domain unlabeled data are in urgent need. Although many domain adaptation approaches are proposed to address such issues in the natural image domain, few of them have been evaluated on connectomics data due to a lack of domain adaptation benchmarks. Therefore, to enable developments of domain adaptive synapse detection methods for large-scale connectomics applications, we annotated 14 image volumes from a biologically diverse set of Megaphragma viggianii brain regions originating from three different whole-brain datasets and organized the WASPSYN challenge at ISBI 2023. The annotations include coordinates of pre-synapses and post-synapses in the 3D space, together with their one-to-many connectivity information. This paper describes the dataset, the tasks, the proposed baseline, the evaluation method, and the results of the challenge. Limitations of the challenge and the impact on neuroscience research are also discussed. The challenge is and will continue to be available at https://codalab.lisn.upsaclay.fr/competitions/9169. Successful algorithms that emerge from our challenge may potentially revolutionize real-world connectomics research and further the cause that aims to unravel the complexity of brain structure and function.

Recent advances in high-resolution connectomics provide researchers with access to accurate petascale reconstructions of neuronal circuits and brain networks for the first time. Neuroscientists are analyzing these networks to better understand information processing in the brain. In particular, scientists are interested in identifying specific small network motifs, i.e., repeating subgraphs of the larger brain network that are believed to be neuronal building blocks. Although such motifs are typically small (e.g., 2 - 6 neurons), the vast data sizes and intricate data complexity present significant challenges to the search and analysis process. To analyze these motifs, it is crucial to review instances of a motif in the brain network and then map the graph structure to detailed 3D reconstructions of the involved neurons and synapses. We present Vimo, an interactive visual approach to analyze neuronal motifs and motif chains in large brain networks. Experts can sketch network motifs intuitively in a visual interface and specify structural properties of the involved neurons and synapses to query large connectomics datasets. Motif instances (MIs) can be explored in high-resolution 3D renderings. To simplify the analysis of MIs, we designed a continuous focus&context metaphor inspired by visual abstractions. This allows users to transition from a highly-detailed rendering of the anatomical structure to views that emphasize the underlying motif structure and synaptic connectivity. Furthermore, Vimo supports the identification of motif chains where a motif is used repeatedly (e.g., 2 - 4 times) to form a larger network structure. We evaluate Vimo in a user study and an in-depth case study with seven domain experts on motifs in a large connectome of the fruit fly, including more than 21,000 neurons and 20 million synapses. We find that Vimo enables hypothesis generation and confirmation through fast analysis iterations and connectivity highlighting.

The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to push the generated image toward high similarities in both content and style. However, this type of approach cannot guarantee visual fidelity, i.e., the generated artworks should be indistinguishable from real ones. In this paper, we devise a new style transfer framework called QunntArt for high visual-fidelity stylization. QuantArt pushes the latent representation of the generated artwork toward the centroids of the real artwork distribution with vector quantization. By fusing the quantized and continuous latent representations, QuantArt allows flexible control over the generated artworks in terms of content preservation, style similarity, and visual fidelity. Experiments on various style transfer settings show that our QuantArt framework achieves significantly higher visual fidelity compared with the existing style transfer methods.

There has been a growing interest in developing multimodal machine translation (MMT) systems that enhance neural machine translation (NMT) with visual knowledge. This problem setup involves using images as auxiliary information during training, and more recently, eliminating their use during inference. Towards this end, previous works face a challenge in training powerful MMT models from scratch due to the scarcity of annotated multilingual vision-language data, especially for low-resource languages. Simultaneously, there has been an influx of multilingual pretrained models for NMT and multimodal pre-trained models for vision-language tasks, primarily in English, which have shown exceptional generalisation ability. However, these are not directly applicable to MMT since they do not provide aligned multimodal multilingual features for generative tasks. To alleviate this issue, instead of designing complex modules for MMT, we propose CLIPTrans, which simply adapts the independently pre-trained multimodal M-CLIP and the multilingual mBART. In order to align their embedding spaces, mBART is conditioned on the M-CLIP features by a prefix sequence generated through a lightweight mapping network. We train this in a two-stage pipeline which warms up the model with image captioning before the actual translation task. Through experiments, we demonstrate the merits of this framework and consequently push forward the state-of-the-art across standard benchmarks by an average of +2.67 BLEU. The code can be found at www.github.com/devaansh100/CLIPTrans.

Unpaired image-to-image translation (UNIT) aims to map images between two visual domains without paired training data. However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains because they often need to train the full model on both existing and new domains. To address this problem, we propose a new domain-scalable UNIT method, termed as latent space anchoring, which can be efficiently extended to new visual domains and does not need to fine-tune encoders and decoders of existing domains. Our method anchors images of different domains to the same latent space of frozen GANs by learning lightweight encoder and regressor models to reconstruct single-domain images. In the inference phase, the learned encoders and decoders of different domains can be arbitrarily combined to translate images between any two domains without fine-tuning. Experiments on various datasets show that the proposed method achieves superior performance on both standard and domain-scalable UNIT tasks in comparison with the state-of-the-art methods.

3D instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying pre-trained models optimized on diverse training data or sequentially conducting image translation and segmentation with two relatively independent networks. In this work, we propose a novel Cyclic Segmentation Generative Adversarial Network (CySGAN) that conducts image translation and instance segmentation simultaneously using a unified network with weight sharing. Since the image translation layer can be removed at inference time, our proposed model does not introduce additional computational cost upon a standard segmentation model. For optimizing CySGAN, besides the CycleGAN losses for image translation and supervised losses for the annotated source domain, we also utilize self-supervised and segmentation-based adversarial objectives to enhance the model performance by leveraging unlabeled target domain images. We benchmark our approach on the task of 3D neuronal nuclei segmentation with annotated electron microscopy (EM) images and unlabeled expansion microscopy (ExM) data. The proposed CySGAN outperforms pre-trained generalist models, feature-level domain adaptation models, and the baselines that conduct image translation and segmentation sequentially. Our implementation and the newly collected, densely annotated ExM zebrafish brain nuclei dataset, named NucExM, are publicly available at https://connectomics-bazaar.github.io/proj/CySGAN/index.html.

In this paper, we present the results of the MitoEM challenge on mitochondria 3D instance segmentation from electron microscopy images, organized in conjunction with the IEEE-ISBI 2021 conference. Our benchmark dataset consists of two large-scale 3D volumes, one from human and one from rat cortex tissue, which are 1,986 times larger than previously used datasets. At the time of paper submission, 257 participants had registered for the challenge, 14 teams had submitted their results, and six teams participated in the challenge workshop. Here, we present eight top-performing approaches from the challenge participants, along with our own baseline strategies. Posterior to the challenge, annotation errors in the ground truth were corrected without altering the final ranking. Additionally, we present a retrospective evaluation of the scoring system which revealed that: 1) challenge metric was permissive with the false positive predictions; and 2) size-based grouping of instances did not correctly categorize mitochondria of interest. Thus, we propose a new scoring system that better reflects the correctness of the segmentation results. Although several of the top methods are compared favorably to our own baselines, substantial errors remain unsolved for mitochondria with challenging morphologies. Thus, the challenge remains open for submission and automatic evaluation, with all volumes available for download.

Many video understanding tasks require analyzing multishot videos, but existing datasets for video object segmentation (VOS) only consider single-shot videos. To address this challenge, we collected a new dataset-YouMVaS-of 200 popular YouTube videos spanning ten genres, where each video is on average five minutes long and with 75 shots. We selected recurring actors and annotated 431K segmentation masks at a frame rate of six, exceeding previous datasets in average video duration, object variation, and narrative structure complexity. We incorporated good practices of model architecture design, memory management, and multi-shot tracking into an existing video segmentation method to build competitive baseline methods. Through error analysis, we found that these baselines still fail to cope with cross-shot appearance variation on our YouMVOS dataset. Thus, our dataset poses new challenges in multi-shot segmentation towards better video analysis. Data, code, and pre-trained models are available at https://donglaiw.github.io/proj/youMVOS

Evaluation practices for image super-resolution (SR) use a single-value metric, the PSNR or SSIM, to determine model performance. This provides little insight into the source of errors and model behavior. Therefore, it is beneficial to move beyond the conventional approach and reconceptualize evaluation with interpretability as our main priority. We focus on a thorough error analysis from a variety of perspectives. Our key contribution is to leverage a texture classifier, which enables us to assign patches with semantic labels, to identify the source of SR errors both globally and locally. We then use this to determine (a) the semantic alignment of SR datasets, (b) how SR models perform on each label, (c) to what extent high-resolution (HR) and SR patches semantically correspond, and more. Through these different angles, we are able to highlight potential pitfalls and blindspots. Our overall investigation highlights numerous unexpected insights. We hope this work serves as an initial step for debugging blackbox SR networks.

As connectomic datasets exceed hundreds of terabytes in size, accurate and efficient skeleton generation of the label volumes has evolved into a critical component of the computation pipeline used for analysis, evaluation, visualization, and error correction. We propose a novel topological thinning strategy that uses biological-constraints to produce accurate centerlines from segmented neuronal volumes while still maintaining biologically relevant properties. Current methods are either agnostic to the underlying biology, have non-linear running times as a function of the number of input voxels, or both. First, we eliminate from the input segmentation biologically-infeasible bubbles, pockets of voxels incorrectly labeled within a neuron, to improve segmentation accuracy, allow for more accurate centerlines, and increase processing speed. Next, a Convolutional Neural Network (CNN) detects cell bodies from the input segmentation, allowing us to anchor our skeletons to the somata. Lastly, a synapse-aware topological thinning approach produces expressive skeletons for each neuron with a nearly one-to-one correspondence between endpoints and synapses. We simultaneously estimate geometric properties of neurite width and geodesic distance between synapse and cell body, improving accuracy by 47.5% and 62.8% over baseline methods. We separate the skeletonization process into a series of computation steps, leveraging data-parallel strategies to increase throughput significantly. We demonstrate our results on over 1250 neurons and neuron fragments from three different species, processing over one million voxels per second per CPU with linear scalability.

Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-resolution (SR) research. However, current CNN models exhibit a major flaw: they are biased towards learning low-frequency signals. This bias becomes more problematic for the image SR task which targets reconstructing all fine details and image textures. To tackle this challenge, we propose to improve the learning of high-frequency features both locally and globally and introduce two novel architectural units to existing SR models. Specifically, we propose a dynamic highpass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals. We also propose a matrix multi-spectral channel attention (MMCA) module that predicts the attention map of features decomposed in the frequency domain. This module operates in a global context to adaptively recalibrate feature responses at different frequencies. Extensive qualitative and quantitative results demonstrate that our proposed modules achieve better accuracy and visual improvements against state-of-the-art methods on several benchmark datasets.

Deep convolutional neural networks (CNNs) are achieving great successes for image super-resolution (SR), where global context is crucial for accurate restoration. However, the basic convolutional layer in CNNs is designed to extract local patterns, lacking the ability to model global context. With global context information, lots of efforts have been devoted to augmenting SR networks, especially by global feature interaction methods. These works incorporate the global context into local feature representation. However, recent advances in neuroscience show that it is necessary for the neurons to dynamically modulate their functions according to context, which is neglected in most CNN based SR methods. Motivated by those observations and analyses, we propose context reasoning attention network (CRAN) to modulate the convolution kernel according to the global context adaptively. Specifically, we extract global context descriptors, which are further enhanced with semantic reasoning. Channel and spatial interactions are then introduced to generate context reasoning attention mask, which is applied to modify the convolution kernel adaptively. Such a modulated convolution layer is utilized as basic component to build the blocks and networks. Extensive experiments on benchmark datasets with multiple degradation models show that CRAN obtains superior results and favorable trade-off between performance and model complexity.

Segmenting 3D cell nuclei from microscopy image volumes is critical for biological and clinical analysis, enabling the study of cellular expression patterns and cell lineages. However, current datasets for neuronal nuclei usually contain volumes smaller than $10^{\text{-}3}\ mm^3$ with fewer than 500 instances per volume, unable to reveal the complexity in large brain regions and restrict the investigation of neuronal structures. In this paper, we have pushed the task forward to the sub-cubic millimeter scale and curated the NucMM dataset with two fully annotated volumes: one $0.1\ mm^3$ electron microscopy (EM) volume containing nearly the entire zebrafish brain with around 170,000 nuclei; and one $0.25\ mm^3$ micro-CT (uCT) volume containing part of a mouse visual cortex with about 7,000 nuclei. With two imaging modalities and significantly increased volume size and instance numbers, we discover a great diversity of neuronal nuclei in appearance and density, introducing new challenges to the field. We also perform a statistical analysis to illustrate those challenges quantitatively. To tackle the challenges, we propose a novel hybrid-representation learning model that combines the merits of foreground mask, contour map, and signed distance transform to produce high-quality 3D masks. The benchmark comparisons on the NucMM dataset show that our proposed method significantly outperforms state-of-the-art nuclei segmentation approaches. Code and data are available at https://connectomics-bazaar.github.io/proj/nucMM/index.html.

Existing deep learning real denoising methods require a large amount of noisy-clean image pairs for supervision. Nonetheless, capturing a real noisy-clean dataset is an unacceptable expensive and cumbersome procedure. To alleviate this problem, this work investigates how to generate realistic noisy images. Firstly, we formulate a simple yet reasonable noise model that treats each real noisy pixel as a random variable. This model splits the noisy image generation problem into two sub-problems: image domain alignment and noise domain alignment. Subsequently, we propose a novel framework, namely Pixel-level Noise-aware Generative Adversarial Network (PNGAN). PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space to perform image domain alignment. Simultaneously, PNGAN establishes a pixel-level adversarial training to conduct noise domain alignment. Additionally, for better noise fitting, we present an efficient architecture Simple Multi-scale Network (SMNet) as the generator. Qualitative validation shows that noise generated by PNGAN is highly similar to real noise in terms of intensity and distribution. Quantitative experiments demonstrate that a series of denoisers trained with the generated noisy images achieve state-of-the-art (SOTA) results on four real denoising benchmarks.

Image segmentation is a fundamental vision task and still remains a crucial step for many applications. In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD. Precisely, we define BPD on each pixel as a two-dimensional unit vector pointing from its nearest boundary to the pixel. In the BPD, nearby pixels from different regions have opposite directions departing from each other, and nearby pixels in the same region have directions pointing to the other or each other (i.e., around medial points). We make use of such property to partition image into super-BPDs, which are novel informative superpixels with robust direction similarity for fast grouping into segmentation regions. Extensive experimental results on BSDS500 and Pascal Context demonstrate the accuracy and efficiency of the proposed super-BPD in segmenting images. Specifically, we achieve comparable or superior performance with MCG while running at ~25fps vs 0.07fps. Super-BPD also exhibits a noteworthy transferability to unseen scenes.

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%.

We seek to understand the arrow of time in videos - what makes videos look like they are playing forwards or backwards? Can we visualize the cues? Can the arrow of time be a supervisory signal useful for activity analysis? To this end, we build three large-scale video datasets and apply a learning-based approach to these tasks. To learn the arrow of time efficiently and reliably, we design a ConvNet suitable for extended temporal footprints and for class activation visualization, and study the effect of artificial cues, such as cinematographic conventions, on learning. Our trained model achieves state-of-the-art performance on large-scale real-world video datasets. Through cluster analysis and localization of important regions for the prediction, we examine learned visual cues that are consistent among many samples and show when and where they occur. Lastly, we use the trained ConvNet for two applications: self-supervision for action recognition, and video forensics - determining whether Hollywood film clips have been deliberately reversed in time, often used as special effects.

Structures and objects are often supposed to have idealized geometries such as straight lines or circles. Although not always visible to the naked eye, in reality, these objects deviate from their idealized models. Our goal is to reveal and visualize such subtle geometric deviations, which can contain useful, surprising information about our world. Our framework, termed Deviation Magnification , takes a still image as input, fits parametric models to objects of interest, computes the geometric deviations, and renders an output image in which the departures from ideal geometries are exaggerated. We demonstrate the correctness and usefulness of our method through quantitative evaluation on a synthetic dataset and by application to challenging natural images.

Data-driven techniques can reliably build semantic correspondence among images. In this paper, we present a new regularization model for stereo or flow through transferring the shape information of the disparity or flow from semantically matched patches in the training database. Compared to previous regularization models based on image appearance alone, we can better resolve local ambiguity of the disparity or flow by considering the semantic information without explicit object modeling. We incorporate this data-driven regularization model into a standard Markov Random Field (MRF) model, inferred with a gradient descent algorithm and learned with a discriminative learning approach. Compared to prior state-of-the-art methods, our full model achieves comparable or better results on the KITTI stereo and flow datasets, and improves results on the Sintel Flow dataset under an online estimation setting.

We explore whether we can observe Time's Arrow in a temporal sequence - is it possible to tell whether a video is running forwards or backwards? We investigate this somewhat philosophical question using computer vision and machine learning techniques. We explore three methods by which we might detect Time's Arrow in video sequences, based on distinct ways in which motion in video sequences might be asymmetric in time. We demonstrate good video forwards/backwards classification results on a selection of YouTube video clips, and on natively-captured sequences (with no temporally-dependent video compression), and examine what motions the models have learned that help discriminate forwards from backwards time.

We develop a generative probabilistic model for temporally consistent super pixels in video sequences. In contrast to supermodel methods, object parts in different frames are tracked by the same temporal super pixel. We explicitly model flow between frames with a bilateral Gaussian process and use this information to propagate super pixels in an online fashion. We consider four novel metrics to quantify performance of a temporal super pixel representation and demonstrate superior performance when compared to supermodel methods.

MOTIVATION: RNA secondary structure plays an important role in the function of many RNAs, and structural features are often key to their interaction with other cellular components. Thus, there has been considerable interest in the prediction of secondary structures for RNA families. In this article, we present a new global structural alignment algorithm, RNAG, to predict consensus secondary structures for unaligned sequences. It uses a blocked Gibbs sampling algorithm, which has a theoretical advantage in convergence time. This algorithm iteratively samples from the conditional probability distributions P(Structure | Alignment) and P(Alignment | Structure). Not surprisingly, there is considerable uncertainly in the high-dimensional space of this difficult problem, which has so far received limited attention in this field. We show how the samples drawn from this algorithm can be used to more fully characterize the posterior space and to assess the uncertainty of predictions. RESULTS: Our analysis of three publically available datasets showed a substantial improvement in RNA structure prediction by RNAG over extant prediction methods. Additionally, our analysis of 17 RNA families showed that the RNAG sampled structures were generally compact around their ensemble centroids, and at least 11 families had at least two well-separated clusters of predicted structures. In general, the distance between a reference structure and our predicted structure was large relative to the variation among structures within an ensemble. AVAILABILITY: The Perl implementation of the RNAG algorithm and the data necessary to reproduce the results described in Sections 3.1 and 3.2 are available at http://ccmbweb.ccv.brown.edu/rnag.html CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.