Cloud-native ultrasound imaging

CloudSound aims to revolutionize ultrasound imaging by leveraging cloud computing for high-quality, affordable, and accessible medical imaging through a closed-loop, goal-directed approach.

Subsidie
€ 150.000
2024

Projectdetails

Introduction

Ultrasound (US) can revolutionize and democratize medical imaging if it offers:

  1. Access for everyone, and
  2. Excellent image quality, always.

MRI offers excellent image quality but is expensive and will thus not likely be able to provide access for everyone. Low-cost US hardware will enable access in the future but is not expected to yield the needed breakthrough for excellent image quality. Any solution that addresses both will have a huge impact.

Challenges in Image Quality

The biggest adversaries for US image quality stem from patient- and user-specific factors. I therefore strongly believe that achieving excellent image quality requires closed-loop, goal-directed imaging through systems that actively pursue information gain in-situ.

Project Overview

My ERC stg project “US-ACT” develops this new closed-loop US paradigm, with deep generative models governing beliefs about anatomy and function. This, however, gives rise to a new dilemma:

  • How to embrace high-performant, but complex, algorithms to achieve excellent image quality, while at the same time lowering cost to achieve access for everyone?

Our recent result shows that US-ACT enables breaking the cost-complexity trade-off through a new approach that is rooted in the closed-loop proposition itself.

Proposed Solution: CloudSound

I propose CloudSound, a fully cloud-native US imaging paradigm, unlocking access to virtually unlimited computational power, memory, and storage for raw US sensor data.

We will move all the computational complexity away from the local device to a remote server. To achieve this with minimal latency and high frame rates, CloudSound introduces a new holistic rate control strategy for the entire transmit-receive scheme, based on algorithms developed in US-ACT. This will drive rate control of the full solution under a time-varying information bottleneck: the network channel.

Conclusion

Ultimately, CloudSound will disrupt ultrasound business models and unlock unprecedented image quality and ease of use, making advanced medical imaging affordable and globally accessible.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 150.000
Totale projectbegroting€ 150.000

Tijdlijn

Startdatum1-9-2024
Einddatum28-2-2026
Subsidiejaar2024

Partners & Locaties

Projectpartners

  • TECHNISCHE UNIVERSITEIT EINDHOVENpenvoerder

Land(en)

Netherlands

Vergelijkbare projecten binnen European Research Council

ERC Starting...

Next-gen ultrasound imaging by closing the perception-action loop

This project aims to revolutionize ultrasound imaging by integrating intelligent autonomous agents that utilize probabilistic inference for enhanced image quality and effective data acquisition.

€ 1.812.500
ERC Starting...

Super-resolution, ultrafast and deeply-learned contrast ultrasound imaging of the vascular tree.

Super-FALCON aims to revolutionize cardiovascular and cancer imaging by using advanced plane-wave ultrasound with microbubbles for precise, high-resolution flow imaging, enhancing diagnosis and treatment.

€ 1.500.000
ERC Advanced...

Remote controlling biological systems by sonopharmacology and sonogenetics

This project aims to develop biocompatible ultrasound technology to control drug, protein, and gene activity, enhancing therapies for cancer, diabetes, and tissue engineering while minimizing side effects.

€ 2.500.000
ERC Starting...

Intelligent Optoacoustic Radiomics via Synergistic Integration of System Models and Medical Knowledge

EchoLux aims to revolutionize radiomics by integrating imaging hardware, medical knowledge, and Bayesian reasoning for explainable diagnostics in optoacoustic imaging of peripheral neuropathy.

€ 1.499.976
ERC Proof of...

Real-time, High-throughput, Coherent X-ray Microscopy: from Large-Scale Installations to Tabletop Device

HYPER aims to develop a cost-effective tabletop coherent XUV microscope for advanced nanoscale imaging, enhancing accessibility and understanding in optoelectronics and biomedical applications.

€ 150.000

Vergelijkbare projecten uit andere regelingen

EIC Pathfinder

Quantitative Ultrasound Stochastic Tomography - Revolutionizing breast cancer diagnosis and screening with supercomputing-based radiation-free imaging.

The project aims to revolutionize breast cancer imaging by developing adjoint-based algorithms for uncertainty quantification, enhancing diagnostic confidence through high-resolution, radiation-free images.

€ 2.744.300
EIC Pathfinder

AEGEUS - A Novel EEG Ultrasound Device for Functional Brain Imaging and Neurostimulation

Develop a novel wearable device combining ultrasound imaging and EEG for enhanced diagnosis and treatment of neurological disorders, aiming for improved patient outcomes and research advancements.

€ 2.998.988
EIC Transition

A Novel Handheld Ultrasound Medical Imaging Probe: Prototyping, Initial Validation and Business Development

The LucidWave Project aims to develop a low-cost, advanced handheld ultrasound probe for improved bedside diagnostics, enhancing medical decision-making and reducing misdiagnosis.

€ 2.427.025
EIC Transition

Advancing stroke care with cutting-edge ultrasound biomarkers for Neurocritical Care

Resolve Stroke aims to enhance ultrasound imaging with the SYLVER system to improve stroke diagnosis and management through innovative biomarkers, making timely detection more accessible and effective.

€ 2.493.436
Mkb-innovati...

Cloud-IA: Een Cloud-based platform

Cloud-IA ontwikkelt een cloudplatform voor de integratie van AI-gedreven medische beeldverwerkingssoftware in ziekenhuizen, met als doel de diagnostische efficiëntie en kosteneffectiviteit te verbeteren.

€ 326.297