BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

Manubens-Gil, Linus; Zhou, Zhi; Chen, Hanbo; Ramanathan, Arvind; Liu, Huan; Liu, Yufeng; Bria, Alessandro; Gillette, Todd A.; Ruan, Zongcai; Yang, Jian; Radojević, Miroslav; Zhao, Ting; Cheng, Li; Qu, Lei; Liu, Siqi; Bouchard, Kristofer E.; Gu, Lin; Cai, Weidong; Ji, Shuiwang; Roysam, Badrinath; Wang, Ching-Wei; Yu, Hongchuan; Sironi, Amos; Iascone, Daniel Maxim; Zhou, Jie; Bas, Erhan; Conde-Sousa, Eduardo; Aguiar, Paulo; Li, Xiang; Li, Yujie; Nanda, Sumit; Wang, Yuan; Mureşan, Leila; Fua, Pascal; Ye, Bing; He, Hai-yan; Staiger, Jochen F.; Peter, Manuel; Cox, Daniel N.; Simonneau, Michel; Oberlaender, Marcel; Jefferis, Gregory S.X.E.; Ito, Kei; Gonzalez-Bellido, Paloma T.; Kim, Jinhyun; Rubel, Edwin W.; Cline, Hollis T.; Zeng, Hongkui; Nern, Aljoscha; Chiang, Ann‐Shyn; Yao, Jianhua; Roskams, Jane; Livesey, Rick; Stevens, Janine; Liu, Tianming; Dang, Chinh; Guo, Yike; Zhong, Ning; Tourassi, Georgia D.; Hill, Sean; Hawrylycz, Michael; Koch, Christof; Meijering, Erik; Ascoli, Giorgio A.; Peng, Hanchuan

doi:10.1038/s41592-023-01848-5

Cited by 37 publications

(23 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One salient feature of mammalian neurons is their extensive, long-range axonal projections across brain regions (Zeng & Sanes, 2017). However, our understanding of neuronal morphology and function is limited by the incomplete digital representation of neuron patterns (Peng et al, 2015;Manubens-Gil et al, 2023). Recent studies have focused on more complete representations of neuronal morphology, including both dendrites and axons, using genetic and viral techniques that label neurons sparsely (Ghosh et al, 2011;Kuramoto et al, 2009;Luo et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Full-Spectrum Neuronal Diversity and Stereotypy through Whole Brain Morphometry

Peng

Liu

Jiang³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

We conducted a large-scale study of whole-brain morphometry, analyzing 3.7 peta-voxels of mouse brain images at the single-cell resolution, producing one of the largest multi-morphometry databases of mammalian brains to date. We spatially registered 205 mouse brains and associated data from six Brain Initiative Cell Census Network (BICCN) data sources covering three major imaging modalities from five collaborative projects to the Allen Common Coordinate Framework (CCF) atlas, annotated 3D locations of cell bodies of 227,581 neurons, modeled 15,441 dendritic microenvironments, characterized the full morphology of 1,891 neurons along with their axonal motifs, and detected 2.58 million putative synaptic boutons. Our analysis covers six levels of information related to neuronal populations, dendritic microenvironments, single-cell full morphology, sub-neuronal dendritic and axonal arborization, axonal boutons, and structural motifs, along with a quantitative characterization of the diversity and stereotypy of patterns at each level. We identified 16 modules consisting of highly intercorrelated brain regions in 13 functional brain areas corresponding to 314 anatomical regions in CCF. Our analysis revealed the dendritic microenvironment as a powerful method for delineating brain regions of cell types and potential subtypes. We also found that full neuronal morphologies can be categorized into four distinct classes based on spatially tuned morphological features, with substantial cross-areal diversity in apical dendrites, basal dendrites, and axonal arbors, along with quantified stereotypy within cortical, thalamic and striatal regions. The lamination of somas was found to be more effective in differentiating neuron arbors within the cortex. Further analysis of diverging and converging projections of individual neurons in 25 regions throughout the brain reveals branching preferences in the brain-wide and local distributions of axonal boutons. Overall, our study provides a comprehensive description of key anatomical structures of neurons and their types, covering a wide range of scales and features, and contributes to our understanding of neuronal diversity and its function in the mammalian brain.

show abstract

Section: Introductionmentioning

confidence: 99%

Full-Spectrum Neuronal Diversity and Stereotypy through Whole Brain Morphometry

Peng

Liu

Jiang³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite a number of claimed successes in automated neuron tracing, practically the majority of automation has only been applied to fairly simple use-cases where the signal-to-noise ratio is high, or the entirety of neurite-signal is not required to be traced (Liu, et al, 2022). Indeed, as the worldwide community has recognized that there exists no single best algorithm for all possible light-microscopy neuronal images (Peng, Hawrylycz, et al, 2015;, careful evaluation of automated tracings must be crossvalidated before they may acclaim biological relevance (Manubens-Gil, et al, 2023). Therefore, a remarkable, unanswered key question in the field is how to produce 3-D reconstructions of complicated neuron morphology at scale, while ensuring these reconstructions are both neuroanatomically accurate and reliable.…”

Section: Introductionmentioning

confidence: 99%

“…Due to these hurdles, currently there remains a substantial scarcity of high-quality training datasets of neuron morphology, making the development of deep-learning and similar machine-learning methods for this task a formidable challenge (Liu, et al, 2022). In this context, the recent achievements in the series of generative pre-trained transformers (GPT) (Open AI, 2023) have opened promising avenues for the development of Large Language Models (LLM) (Brown, et al, 2020;Zhao, et al, 2023) and the pursuit of Artificial General Intelligence (AGI) (Goertzel, et al, 2007). Meanwhile, there have been concerted efforts to develop general-purpose models for computer vision tasks (Radford, et al, 2021;Kirillov, et al, 2023), including extended applications in the domain of medical image processing (Mazurowski, et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

“…Our data indicate that the CAR platform is suitable for generating tens of thousands of neuronal reconstructions used in our companion studies. We have adopted CAR as a major morphological data generation platform in several ongoing projects including The BRAIN Initiative Cell Census Network (BICCN) and BigNeuron (Manubens-Gil, et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

“…The generation of these morphology datasets became possible thanks to both recent advancements in sparse neuron labeling and light microscopy imaging of whole brains (e.g. Rotolo, et al, 2008; Kuramoto, et al, 2009; Ghosh, et al, 2011; Gong, et al, 2016; Lin, et al, 2018; Matho, et al, 2021; Munoz-Castaneda, et al, 2021; Wang, et al, 2021; Han, et al, 2022), and particularly new development of neuron reconstruction (also called neuron tracing) technologies from 3-D light microscopy images (Liu, et al, 2022; Manubens-Gil, et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Collaborative Augmented Reconstruction for Scaled Production of 3D Neuron Morphology in Mouse and Human Brains

Zhang,

Huang,

Yuan

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Digital reconstruction of the intricate 3D morphology of individual neurons from microscopic images is widely recognized as a crucial challenge in both individual research laboratories and large-scale scientific projects focusing on cell types and brain anatomy. This task often fails both conventional manual reconstruction and state-of-the-art automatic reconstruction algorithms, even many of which are based on artificial intelligence (AI). It is also critical but challenging to organize multiple neuroanatomists to produce and cross-validate biologically relevant and agreeable reconstructions in scaled data production. Here we propose an approach based on collaborative human intelligence augmented by AI. Specifically, we have developed a Collaborative Augmented Reconstruction (CAR) platform for neuron reconstruction at scale. This platform allows for immersive interaction and efficient collaborative-editing of neuron anatomy using a variety of client devices, such as desktop workstations, virtual reality headsets, and mobile phones, enabling users to contribute anytime and anywhere and take advantage of several AI-based automation tools. We have tested CAR’s applicability for challenging mouse and human neurons towards a scaled and faithful data production. Our data indicate that the CAR platform is suitable for generating tens of thousands of neuronal reconstructions used in our companion studies.

show abstract