VascFlexMap: microvascular ultrasound imaging at low frame rates using sparse data and a transformer-decoder network
Source
bioRXiv
ISSN
2692-8205
Date Issued
2026-03-01
Author(s)
Abstract
Objective Super-resolution ultrasound (SR-US) reveals microvascular structures with exquisite resolution, but clinical translation remains limited by the need for ultrafast frame rates, massive data volumes, and long reconstruction times. This work proposes a deep learning framework that reconstructs microvascular maps from low-frame-rate enhanced ultrasound sequences, bypassing explicit microbubble localization and tracking.
Methods A transformer-decoder network with learned linear projections was designed to model spatiotemporal dependencies across sparse contrast-enhanced ultrasound sequences and reconstruct vessel probability maps, refined via a post-processing enhancement stage. Single-head self-attention captures temporal correlations under challenging conditions including overlapping microbubbles and low signal-to-noise ratios. Binary cross-entropy loss guided training to preserve vascular topology across synthetic and in vivo datasets. In vivo rat brain bolus data from the PALA challenge was used to evaluate this approach under up to 500 − fold data reduction (341 frames at 2 FPS vs. 170400 frames at 1000 FPS in standard ULM).
Results Despite aggressive undersampling, the proposed pipeline recovered coherent microvascular architecture where conventional ULM pipelines applied to the same sparse data failed to produce continuous vascular networks. Major branches and higher-order microvessels remained visible with apparent vessel widths broadened by approximately three-fold relative to reference SR-US. End-to-end reconstruction completed in 28–133 seconds on an NVIDIA H100 GPU depending on the number of frames employed.
Conclusion The reported approach preserved vascular topology with fast reconstruction and low data overhead, albeit at lower resolution. The substantial reduction in frames and computation time highlights the translational potential of this SR-US-inspired microvascular imaging approach.
Methods A transformer-decoder network with learned linear projections was designed to model spatiotemporal dependencies across sparse contrast-enhanced ultrasound sequences and reconstruct vessel probability maps, refined via a post-processing enhancement stage. Single-head self-attention captures temporal correlations under challenging conditions including overlapping microbubbles and low signal-to-noise ratios. Binary cross-entropy loss guided training to preserve vascular topology across synthetic and in vivo datasets. In vivo rat brain bolus data from the PALA challenge was used to evaluate this approach under up to 500 − fold data reduction (341 frames at 2 FPS vs. 170400 frames at 1000 FPS in standard ULM).
Results Despite aggressive undersampling, the proposed pipeline recovered coherent microvascular architecture where conventional ULM pipelines applied to the same sparse data failed to produce continuous vascular networks. Major branches and higher-order microvessels remained visible with apparent vessel widths broadened by approximately three-fold relative to reference SR-US. End-to-end reconstruction completed in 28–133 seconds on an NVIDIA H100 GPU depending on the number of frames employed.
Conclusion The reported approach preserved vascular topology with fast reconstruction and low data overhead, albeit at lower resolution. The substantial reduction in frames and computation time highlights the translational potential of this SR-US-inspired microvascular imaging approach.
Subjects
Deep learning
Microvascular imaging
Microbubble contrast
Real-time ultrasound
Sparse data reconstruction
Super-resolution ultrasound
Transformer decoder