TY - JOUR A1 - Vohra, Sumit Kumar A1 - Prodanov, Dimiter T1 - The Active Segmentation Platform for Microscopic Image Classification and Segmentation JF - Brain Sciences. 2021 N2 - Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different classifiers, providing pixel-level classification and segmentation. However, machine learning only can not address the question as to which features are appropriate for a certain classification problem. The article presents an automated image segmentation and classification platform, called Active Segmentation, which is based on ImageJ. The platform integrates expert domain knowledge, providing partial ground truth, with geometrical feature extraction based on multi-scale signal processing combined with machine learning. The approach in image segmentation is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application we demonstrate whole image classification functionality based on the same principles. The approach is exemplified using the HeLa and HEp-2 data sets. Obtained results indicate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches. In summary, differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical invariant objects. Y1 - 2021 U6 - https://doi.org/https://doi.org/10.3390/brainsci11121645 VL - 11 IS - 12 SP - 1645 ER - TY - JOUR A1 - Vohra, Sumit Kumar A1 - Herrera, Kristian A1 - Tavhelidse-Suck, Tinatini A1 - Knoblich, Simon A1 - Seleit, Ali A1 - Boulanger-Weill, Jonathan A1 - Chambule, Sydney A1 - Aspiras, Ariel A1 - Santoriello, Cristina A1 - Randlett, Owen A1 - Wittbrodt, Joachim A1 - Aulehla, Alexander A1 - Lichtman, Jeff W. A1 - Fishman, Mark A1 - Hege, Hans-Christian A1 - Baum, Daniel A1 - Engert, Florian A1 - Isoe, Yasuko T1 - Multi-species community platform for comparative neuroscience in teleost fish JF - bioRxiv N2 - Studying neural mechanisms in complementary model organisms from different ecological niches in the same animal class can leverage the comparative brain analysis at the cellular level. To advance such a direction, we developed a unified brain atlas platform and specialized tools that allowed us to quantitatively compare neural structures in two teleost larvae, medaka (Oryzias latipes) and zebrafish (Danio rerio). Leveraging this quantitative approach we found that most brain regions are similar but some subpopulations are unique in each species. Specifically, we confirmed the existence of a clear dorsal pallial region in the telencephalon in medaka lacking in zebrafish. Further, our approach allows for extraction of differentially expressed genes in both species, and for quantitative comparison of neural activity at cellular resolution. The web-based and interactive nature of this atlas platform will facilitate the teleost community’s research and its easy extensibility will encourage contributions to its continuous expansion. Y1 - 2024 U6 - https://doi.org/10.1101/2024.02.14.580400 ER - TY - JOUR A1 - Boulanger-Weill, Jonathan A1 - Kaempf, Florian A1 - L. Schalek, Richard A1 - Petkova, Mariela A1 - Vohra, Sumit Kumar A1 - Savaliya, Jay H. A1 - Wu, Yuelong A1 - Schuhknecht, Gregor F. P. A1 - Naumann, Heike A1 - Eberle, Maren A1 - Kirchberger, Kim N. A1 - Rencken, Simone A1 - Bianco, Isaac H. A1 - Baum, Daniel A1 - Bene, Filippo Del A1 - Engert, Florian A1 - Lichtman, Jeff W. A1 - Bahl, Armin T1 - Correlative light and electron microscopy reveals the fine circuit structure underlying evidence accumulation in larval zebrafish JF - bioRxiv N2 - Accumulating information is a critical component of most circuit computations in the brain across species, yet its precise implementation at the synaptic level remains poorly understood. Dissecting such neural circuits in vertebrates requires precise knowledge of functional neural properties and the ability to directly correlate neural dynamics with the underlying wiring diagram in the same animal. Here we combine functional calcium imaging with ultrastructural circuit reconstruction, using a visual motion accumulation paradigm in larval zebrafish. Using connectomic analyses of functionally identified cells and computational modeling, we show that bilateral inhibition, disinhibition, and recurrent connectivity are prominent motifs for sensory accumulation within the anterior hindbrain. We also demonstrate that similar insights about the structure-function relationship within this circuit can be obtained through complementary methods involving cell-specific morphological labeling via photo-conversion of functionally identified neuronal response types. We used our unique ground truth datasets to train and test a novel classifier algorithm, allowing us to assign functional labels to neurons from morphological libraries where functional information is lacking. The resulting feature-rich library of neuronal identities and connectomes enabled us to constrain a biophysically realistic network model of the anterior hindbrain that can reproduce observed neuronal dynamics and make testable predictions for future experiments. Our work exemplifies the power of hypothesis-driven electron microscopy paired with functional recordings to gain mechanistic insights into signal processing and provides a framework for dissecting neural computations across vertebrates. Y1 - 2025 U6 - https://doi.org/10.1101/2025.03.14.643363 ER - TY - JOUR A1 - Petkova, Mariela D. A1 - Januszewski, Michał A1 - Blakely, Tim A1 - Herrera, Kristian J. A1 - Schuhknecht, Gregor F.P. A1 - Tiller, Robert A1 - Choi, Jinhan A1 - Schalek, Richard L. A1 - Boulanger-Weill, Jonathan A1 - Peleg, Adi A1 - Wu, Yuelong A1 - Wang, Shuohong A1 - Troidl, Jakob A1 - Vohra, Sumit Kumar A1 - Wei, Donglai A1 - Lin, Zudi A1 - Bahl, Armin A1 - Tapia, Juan Carlos A1 - Iyer, Nirmala A1 - Miller, Zachary T. A1 - Hebert, Kathryn B. A1 - Pavarino, Elisa C. A1 - Taylor, Milo A1 - Deng, Zixuan A1 - Stingl, Moritz A1 - Hockling, Dana A1 - Hebling, Alina A1 - Wang, Ruohong C. A1 - Zhang, Lauren L. A1 - Dvorak, Sam A1 - Faik, Zainab A1 - King, Jr., Kareem I. A1 - Goel, Pallavi A1 - Wagner-Carena, Julian A1 - Aley, David A1 - Chalyshkan, Selimzhan A1 - Contreas, Dominick A1 - Li, Xiong A1 - Muthukumar, Akila V. A1 - Vernaglia, Marina S. A1 - Carrasco, Teodoro Tapia A1 - Melnychuck, Sofia A1 - Yan, TingTing A1 - Dalal, Ananya A1 - DiMartino, James A1 - Brown, Sam A1 - Safo-Mensa, Nana A1 - Greenberg, Ethan A1 - Cook, Michael A1 - Finley, Samantha A1 - Flynn, Miriam A. A1 - Hopkins, Gary Patrick A1 - Kovalyak, Julie A1 - Leonard, Meghan A1 - Lohff, Alanna A1 - Ordish, Christopher A1 - Scott, Ashley L. A1 - Takemura, Satoko A1 - Smith, Claire A1 - Walsh, John J. A1 - Berger, Daniel R. A1 - Pfister, Hanspeter A1 - Berg, Stuart A1 - Knecht, Christopher A1 - Meissner, Geoffrey W. A1 - Korff, Wyatt A1 - Ahrens, Misha B A1 - Jain, Viren A1 - Lichtman, Jeff W. A1 - Engert, Florian T1 - A connectomic resource for neural cataloguing and circuit dissection of the larval zebrafish brain JF - bioRxiv N2 - We present a correlated light and electron microscopy (CLEM) dataset from a 7-day-old larval zebrafish, integrating confocal imaging of genetically labeled excitatory (vglut2a) and inhibitory (gad1b) neurons with nanometer-resolution serial section EM. The dataset spans the brain and anterior spinal cord, capturing >180,000 segmented soma, >40,000 molecularly annotated neurons, and 30 million synapses, most of which were classified as excitatory, inhibitory, or modulatory. To characterize the directional flow of activity across the brain, we leverage the synaptic and cell body annotations to compute region-wise input and output drive indices at single cell resolution. We illustrate the dataset’s utility by dissecting and validating circuits in three distinct systems: water flow direction encoding in the lateral line, recurrent excitation and contralateral inhibition in a hindbrain motion integrator, and functionally relevant targeted long-range projections from a tegmental excitatory nucleus, demonstrating that this resource enables rigorous hypothesis testing as well as exploratory-driven circuit analysis. The dataset is integrated into an open-access platform optimized to facilitate community reconstruction and discovery efforts throughout the larval zebrafish brain. Y1 - 2025 U6 - https://doi.org/10.1101/2025.06.10.658982 ER - TY - JOUR A1 - Vohra, Sumit Kumar A1 - Eberle, Maren A1 - Boulanger-Weill, Jonathan A1 - Petkova, Mariela D. A1 - Schuhknecht, Gregor F. P. A1 - Herrera, Kristian J. A1 - Kämpf, Florian A1 - Ruetten, Virginia M. S. A1 - Lichtman, Jeff W. A1 - Engert, Florian A1 - Randlett, Owen A1 - Bahl, Armin A1 - Isoe, Yasuko A1 - Hege, Hans-Christian A1 - Baum, Daniel T1 - Fishexplorer: A multimodal cellular atlas platform for neuronal circuit dissection in larval zebrafish JF - bioRxiv N2 - Understanding how neural circuits give rise to behavior requires comprehensive knowledge of neuronal morphology, connectivity, and function. Atlas platforms play a critical role in enabling the visualization, exploration, and dissemination of such information. Here, we present FishExplorer, an interactive and expandable community platform designed to integrate and analyze multimodal brain data from larval zebrafish. FishExplorer supports datasets acquired through light microscopy (LM), electron microscopy (EM), and X-ray imaging, all co-registered within a unified spatial coordinate system which enables seamless comparison of neuronal morphologies and synaptic connections. To further assist circuit analysis, FishExplorer includes a suite of tools for querying and visualizing connectivity at the whole-brain scale. By integrating data from recent large-scale EM reconstructions (presented in companion studies), FishExplorer enables researchers to validate circuit models, explore wiring principles, and generate new hypotheses. As a continuously evolving resource, FishExplorer is designed to facilitate collaborative discovery and serve the growing needs of the teleost neuroscience community. Y1 - 2025 U6 - https://doi.org/10.1101/2025.07.14.664689 ER - TY - JOUR A1 - Vohra, Sumit Kumar A1 - Harth, Philipp A1 - Isoe, Yasuko A1 - Bahl, Armin A1 - Fotowat, Haleh A1 - Engert, Florian A1 - Hege, Hans-Christian A1 - Baum, Daniel T1 - A Visual Interface for Exploring Hypotheses about Neural Circuits JF - IEEE Transactions on Visualization and Computer Graphics N2 - One of the fundamental problems in neurobiological research is to understand how neural circuits generate behaviors in response to sensory stimuli. Elucidating such neural circuits requires anatomical and functional information about the neurons that are active during the processing of the sensory information and generation of the respective response, as well as an identification of the connections between these neurons. With modern imaging techniques, both morphological properties of individual neurons as well as functional information related to sensory processing, information integration and behavior can be obtained. Given the resulting information, neurobiologists are faced with the task of identifying the anatomical structures down to individual neurons that are linked to the studied behavior and the processing of the respective sensory stimuli. Here, we present a novel interactive tool that assists neurobiologists in the aforementioned task by allowing them to extract hypothetical neural circuits constrained by anatomical and functional data. Our approach is based on two types of structural data: brain regions that are anatomically or functionally defined, and morphologies of individual neurons. Both types of structural data are interlinked and augmented with additional information. The presented tool allows the expert user to identify neurons using Boolean queries. The interactive formulation of these queries is supported by linked views, using, among other things, two novel 2D abstractions of neural circuits. The approach was validated in two case studies investigating the neural basis of vision-based behavioral responses in zebrafish larvae. Despite this particular application, we believe that the presented tool will be of general interest for exploring hypotheses about neural circuits in other species, genera and taxa. Y1 - 2024 U6 - https://doi.org/10.1109/TVCG.2023.3243668 VL - 30 IS - 7 SP - 3945 EP - 3958 ER - TY - GEN A1 - Vohra, Sumit Kumar A1 - Harth, Philipp A1 - Isoe, Yasuko A1 - Bahl, Armin A1 - Fotowat, Haleh A1 - Engert, Florian A1 - Hege, Hans-Christian A1 - Baum, Daniel T1 - A Visual Interface for Exploring Hypotheses about Neural Circuits N2 - One of the fundamental problems in neurobiological research is to understand how neural circuits generate behaviors in response to sensory stimuli. Elucidating such neural circuits requires anatomical and functional information about the neurons that are active during the processing of the sensory information and generation of the respective response, as well as an identification of the connections between these neurons. With modern imaging techniques, both morphological properties of individual neurons as well as functional information related to sensory processing, information integration and behavior can be obtained. Given the resulting information, neurobiologists are faced with the task of identifying the anatomical structures down to individual neurons that are linked to the studied behavior and the processing of the respective sensory stimuli. Here, we present a novel interactive tool that assists neurobiologists in the aforementioned task by allowing them to extract hypothetical neural circuits constrained by anatomical and functional data. Our approach is based on two types of structural data: brain regions that are anatomically or functionally defined, and morphologies of individual neurons. Both types of structural data are interlinked and augmented with additional information. The presented tool allows the expert user to identify neurons using Boolean queries. The interactive formulation of these queries is supported by linked views, using, among other things, two novel 2D abstractions of neural circuits. The approach was validated in two case studies investigating the neural basis of vision-based behavioral responses in zebrafish larvae. Despite this particular application, we believe that the presented tool will be of general interest for exploring hypotheses about neural circuits in other species, genera and taxa. T3 - ZIB-Report - 23-07 Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-89932 SN - 1438-0064 ER - TY - CHAP A1 - Harth, Philipp A1 - Vohra, Sumit A1 - Udvary, Daniel A1 - Oberlaender, Marcel A1 - Hege, Hans-Christian A1 - Baum, Daniel T1 - A Stratification Matrix Viewer for Analysis of Neural Network Data T2 - Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM) N2 - The analysis of brain networks is central to neurobiological research. In this context the following tasks often arise: (1) understand the cellular composition of a reconstructed neural tissue volume to determine the nodes of the brain network; (2) quantify connectivity features statistically; and (3) compare these to predictions of mathematical models. We present a framework for interactive, visually supported accomplishment of these tasks. Its central component, the stratification matrix viewer, allows users to visualize the distribution of cellular and/or connectional properties of neurons at different levels of aggregation. We demonstrate its use in four case studies analyzing neural network data from the rat barrel cortex and human temporal cortex. Y1 - 2022 U6 - https://doi.org/10.2312/vcbm.20221194 CY - Vienna, Austria ER - TY - CHAP A1 - Prodanov, Dimiter A1 - Vohra, Sumit Kumar T1 - Active Segmentation: Differential Geometry meets Machine Learning T2 - Proceedings of the 23rd International Conference on Computer Systems and Technologies N2 - Image segmentation is an active area of research for more than 30 years. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different classifiers, providing pixel-level classification and segmentation. However, machine learning only can not address the question as to which features are appropriate for a certain classification problem. This paper presents a project supported in part by the International Neuroinformatics Coordination Facility through the Google Summer of code. The project resulted in an automated image segmentation and classification platform, called Active Segmentation for ImageJ (AS/IJ). The platform integrates a set of filters computing differential geometrical invariants and combines them with machine learning approaches. Y1 - 2022 U6 - https://doi.org/10.1145/3546118.3546154 SP - 1 EP - 6 ER -