Axon Tracing and Centerline Detection using Topologically-Aware 3D U-Nets

Pollack, Dylan; Gjesteby, Lars; Snyder, M; Chavez, David; Kamentsky, Lee; Chung, Kwanghun; Brattain, Laura J.

doi:10.1109/embc48229.2022.9870879

Cited by 6 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8D) ( 78 ). For end-to-end centerline detection, the algorithm uses a centerline-Dice (clDice) loss function ( 79 , 80 ), allowing us to incorporate parameter-free skeletonization directly into the optimization process.…”

Section: Axonal Projectome Mapping and Pathological Analysis Of The H...mentioning

confidence: 99%

Integrated platform for multiscale molecular imaging and phenotyping of the human brain

Park,

Wang,

Guan

et al. 2024

Science

View full text Add to dashboard Cite

Understanding cellular architectures and their connectivity is essential for interrogating system function and dysfunction. However, we lack technologies for mapping the multiscale details of individual cells and their connectivity in the human organ–scale system. We developed a platform that simultaneously extracts spatial, molecular, morphological, and connectivity information of individual cells from the same human brain. The platform includes three core elements: a vibrating microtome for ultraprecision slicing of large-scale tissues without losing cellular connectivity (MEGAtome), a polymer hydrogel–based tissue processing technology for multiplexed multiscale imaging of human organ–scale tissues (mELAST), and a computational pipeline for reconstructing three-dimensional connectivity across multiple brain slabs (UNSLICE). We applied this platform for analyzing human Alzheimer’s disease pathology at multiple scales and demonstrating scalable neural connectivity mapping in the human brain.

show abstract

Section: Axonal Projectome Mapping and Pathological Analysis Of The H...mentioning

confidence: 99%

Integrated platform for multiscale molecular imaging and phenotyping of the human brain

Park,

Wang,

Guan

et al. 2024

Science

View full text Add to dashboard Cite

show abstract

“…8I ) ( 59 ). To perform end-to-end centerline detection, the algorithm uses a centerline-Dice (clDice) loss function ( 60, 61 ), which allows us to incorporate parameter-free skeletonization directly into the optimization process.…”

Section: Main Textmentioning

confidence: 99%

Integrated platform for multi-scale molecular imaging and phenotyping of the human brain

Park

Wang

Guan

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

A detailed understanding of the anatomical and molecular architectures of brain cells and their brain-wide organization is essential for interrogating human brain function and dysfunction. Extensive efforts have been made toward mapping brain cells through various lenses, and have established invaluable databases yielding new insights. However, we still lack technologies that allow us to capture multi-scale multi-omic properties of individual brain cells in a holistic and scalable manner. To address this challenge, we developed a fully integrated technology platform for scalable three-dimensional (3D) mapping of human brain cells at subcellular resolution by simultaneously extracting brain-wide structure and high-dimensional features (e.g., spatial, molecular, morphological, and connectivity information) of individual cells from the same brain. We accomplished this by seamlessly integrating new chemical, mechanical, and computational tools to enable highly multiplexed multi-scale 3D proteomic imaging of human brain tissues with minimal information loss. We developed a novel microtome, termed MEGAtome, that enables ultra-precision slicing of a whole-mount intact human brain hemisphere and large arrays of animal organs with minimal loss of intra- and inter-slice information. To preserve structural and molecular information within intact human brain slabs and to enable highly multiplexed multiscale imaging, we developed a tissue-gel technology, termed mELAST, that transforms human brain tissues into an elastic, thermochemically stable, and reversibly expandable tissue-hydrogel. To reconstruct the intact brain to preserve the 3D connectivity information of neural fibers, we developed a semi-automatic tissue reconstruction computational pipeline termed HuBRIS. We demonstrated the utility and scalability of the technology platform by processing whole human brain hemispheres, investigating Alzheimer Disease (AD) pathology, and demonstrating the feasibility of projectome mapping.

show abstract

“…More recently, deep learning based techniques have been leveraged to tackle the axon segmentation problem [5]- [7]. Notably, Pollack et al [8] incorporates topological information of axon into the loss function to train the deep learning model in order to provide better voxel-based segmentation and axon centerline detection. Motta et al [9] takes a semi-automated approach to conduct the axon segmentation task in the mouse cortex.…”

Section: Introductionmentioning

confidence: 99%

The XPRESS Challenge: Xray Projectomic Reconstruction -- Extracting Segmentation with Skeletons

Nguyen¹,

Narwani²,

Larson³

et al. 2023

Preprint

View full text Add to dashboard Cite

The wiring and connectivity of neurons form a critical structural basis for the function of the nervous system. Advances in volume electron microscopy (EM) and image segmentation have enabled mapping of circuit diagrams (connectomics) within local regions of the mouse brain. However, applying volume EM over the whole brain is not currently feasible due to technological challenges. As a result, comprehensive maps of long-range connections between brain regions are lacking.Recently, we demonstrated that X-ray holographic nanotomography (XNH) can provide high-resolution images of brain tissue at a much larger scale than EM. In particular, XNH is wellsuited to resolve large, myelinated axon tracts (white matter) that make up the bulk of long-range connections (projections) and are critical for inter-region communication. Thus, XNH provides an imaging solution for brain-wide projectomics. However, because XNH data is typically collected at lower resolutions and larger fields-of-view than EM, accurate segmentation of XNH images remains an important challenge that we present here.In this task, we provide volumetric XNH images of cortical white matter axons from the mouse brain along with ground truth annotations for axon trajectories. Manual voxel-wise annotation of ground truth is a time-consuming bottleneck for training segmentation networks. On the other hand, skeleton-based ground truth is much faster to annotate, and sufficient to determine connectivity. Therefore, we encourage participants to develop methods to leverage skeleton-based training. To this end, we provide two types of ground-truth annotations: a small volume of voxel-wise annotations and a larger volume with skeleton-based annotations. The participants will have the flexibility to use either or both of the provided annotations to train their models, and are challenged to submit an accurate voxel-wise prediction on the test volume. Entries will be evaluated on how accurately the submitted segmentations agree with the ground-truth skeleton annotations.

show abstract

Axon Tracing and Centerline Detection using Topologically-Aware 3D U-Nets

Cited by 6 publications

References 13 publications

Integrated platform for multiscale molecular imaging and phenotyping of the human brain

Integrated platform for multiscale molecular imaging and phenotyping of the human brain

Integrated platform for multi-scale molecular imaging and phenotyping of the human brain

The XPRESS Challenge: Xray Projectomic Reconstruction -- Extracting Segmentation with Skeletons

Contact Info

Product

Resources

About