# A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy

arXiv: https://arxiv.org/abs/2310.08143 · HTML: https://mlsanity.com/paper/2310.08143/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 47 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation](https://mlsanity.com/paper/1611.05250/) (2016)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [Super-resolution Ultrasound Localization Microscopy through Deep Learning](https://mlsanity.com/paper/1804.07661/) (2018)
- [On the influence of Dice loss function in multi-class organ segmentation of abdominal CT using 3D fully convolutional networks](https://mlsanity.com/paper/1801.05912/) (2018)
- [Laplacian Flow Dynamics on Geometric Graphs for Anatomical Modeling of Cerebrovascular Networks](https://mlsanity.com/paper/1912.10003/) (2019)

## Built on by (most cited first, 6 of 6)

- [Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy](https://mlsanity.com/paper/2402.09359/) (2024)
- [Vascular Segmentation of Functional Ultrasound Images using Deep Learning](https://mlsanity.com/paper/2410.22365/) (2024)
- [Ensemble Learning for Microbubble Localization in Super-Resolution Ultrasound](https://mlsanity.com/paper/2411.07376/) (2024)
- [Evaluating Detection Thresholds: The Impact of False Positives and Negatives on Super-Resolution Ultrasound Localization Microscopy](https://mlsanity.com/paper/2411.07426/) (2024)
- [4D-UNet improves clutter rejection in human transcranial contrast enhanced ultrasound](https://mlsanity.com/paper/2602.18542/) (2026)
- [CycleULM: A unified label-free deep learning framework for ultrasound localisation microscopy](https://mlsanity.com/paper/2603.09840/) (2026)

## Abstract (arXiv)

Ultrasound Localization Microscopy can resolve the microvascular bed down to a few micrometers. To achieve such performance microbubble contrast agents must perfuse the entire microvascular network. Microbubbles are then located individually and tracked over time to sample individual vessels, typically over hundreds of thousands of images. To overcome the fundamental limit of diffraction and achieve a dense reconstruction of the network, low microbubble concentrations must be used, which lead to acquisitions lasting several minutes. Conventional processing pipelines are currently unable to deal with interference from multiple nearby microbubbles, further reducing achievable concentrations. This work overcomes this problem by proposing a Deep Learning approach to recover dense vascular networks from ultrasound acquisitions with high microbubble concentrations. A realistic mouse brain microvascular network, segmented from 2-photon microscopy, was used to train a three-dimensional convolutional neural network based on a V-net architecture. Ultrasound data sets from multiple microbubbles flowing through the microvascular network were simulated and used as ground truth to train the 3D CNN to track microbubbles. The 3D-CNN approach was validated in silico using a subset of the data and in vivo on a rat brain acquisition. In silico, the CNN reconstructed vascular networks with higher precision (81%) than a conventional ULM framework (70%). In vivo, the CNN could resolve micro vessels as small as 10 μm with an increase in resolution when compared against a conventional approach.