Three-Dimensional GPU-Accelerated Active Contours for Automated Localization of Cells in Large Images
Cell segmentation in microscopy is a challenging problem, since cells are often asymmetric and densely packed. This becomes particularly challenging for extremely large images, since manual intervention and processing time can make segmentation intractable. In this paper, we present an efficient and highly parallel formulation for symmetric three-dimensional (3D) contour evolution that extends previous work on fast two-dimensional active contours. We provide a formulation for optimization on 3D images, as well as a strategy for accelerating computation on consumer graphics hardware. The proposed software takes advantage of Monte-Carlo sampling schemes in order to speed up convergence and reduce thread divergence. Experimental results show that this method provides superior performance for large 2D and 3D cell segmentation tasks when compared to existing methods on large 3D brain images.
Code (0)
등록된 구현이 없습니다.
Tasks
Cell SegmentationGPUSegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PDE Acceleration for Active Contours
Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimi…
parameter estimationActive Contours with Group Similarity
Active contours are widely used in image segmentation. To cope with missing or misleading features in images, researchers have introduced various ways to model the prior of shapes and use the prior to constrain active co…
Image SegmentationSemantic SegmentationLearning deep structured active contours end-to-end
The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building footprint segmentation models have shown s…
Instance SegmentationSegmentationSemantic SegmentationCosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulators
We present CosmoPower-JAX, a JAX-based implementation of the CosmoPower framework, which accelerates cosmological inference by building neural emulators of cosmological power spectra. We show how, using the automatic dif…
Bayesian InferenceComputational Efficiencyparameter estimationVocal Bursts Intensity PredictionRandomized Subspace Nesterov Accelerated Gradient
Randomized-subspace methods reduce the cost of first-order optimization by using only low-dimensional projected-gradient information, a feature that is attractive in forward-mode automatic differentiation and communicati…