Free COVID-19 imaging tools launched by Sydney start-ups
University of Sydney spin-off DetectED-X has directed its online image-based breast cancer diagnosis tool at the novel coronavirus that causes COVID-19, drawing on pandemic cases globally with support from healthcare and industry leaders to ramp up disease detection.
The cloud-based technology, developed by radiation and imaging experts, is designed to help doctors and radiologists diagnose cases faster and more accurately. It follows on from DetectED-X’s BreastScreen Reader Assessment Strategy (BREAST) platform, created in 2010, and a similar solution for diagnosing dust disease with high-resolution computed tomography (HRCT).
Computed tomography (CT) lung scans, which produce cross-sectional images using X-rays and computers, have typically been used after swabs are taken to identify the extent and location of the disease; the CT scans produce images within minutes and are also able to diagnose COVID-19 in the very early stages that escape detection with the nucleic acid tests. DetectED-X’s approach includes algorithms to improve radiologist skills and identifying where errors were made on images in online training sessions, enabling clinicians to assess their performance and receive immediate feedback.
As COVID-19 testing ramps up, DetectED-X’s CovED platform could facilitate rapid training where required — with modules able to be completed in as little as an hour — upskilling staff unfamiliar with lung radiology to prepare standardised reports for expert review. The image files personalised for each clinician are instantly returned, showing any errors in their virtual diagnosis, and the difficulty level is increased over time.
“The number of patients that are suffering from this life-threatening illness is fast outpacing the number of skilled staff required to accurately diagnose the required lung CT scans,” said DetectED-X CEO Professor Patrick Brennan.
“Our platform does not replace expert medical and radiologic training but CovED provides an effective way to recognise rapidly the appearances of COVID-19, which could be critical in a situation of too many patients and not enough expert radiologists, with the modules taking just 1–2 hours to complete.
“This will be immediately crucial in developing countries, where numbers of radiologists are often insufficient — our tests will help people not only diagnose COVID-19 but also identify potentially life-threatening cases wherever they are.”
The CovED platform, which can be accessed anywhere with an internet connection, is being provided for free by the start-up and supported by healthcare experts and corporations globally. Medical professionals, hospitals and other institutions can register to gain access to the platform at www.detectedx.com.
Meanwhile, deep tech development company LENS Immersive has announced no-cost access to its image compression tool, TORII-DICOM, for all hospitals and radiology labs currently engaged in the battle with COVID-19. The release of the image archiving tool comes after several months of expedited development at the start-up’s Sydney headquarters.
The use of CT imaging for COVID-19 diagnosis is putting pressure on radiology labs and hospitals while creating a huge amount of necessary data. TORII-DICOM has been specifically designed to compress CT, radiography, ultrasonography and MRI image data, in some cases by up to 85% with no data loss. The storage saved allows up to six times the number of images to be stored in traditional hospital archive systems.
“We’ve built TORII to solve problems around image compression — when we saw COVID-19 spreading across the globe, we wanted to do our part to help,” said LENS Immersive CEO Yan Chen.
“The tech we’ve been building for data compression can be applied to reduce imaging data loads in hospitals, so we decided to make it available to major hospitals and imaging labs free of charge. The powerful TORII compression tech is now compatible with all existing DICOM data workflows and is ready to be put to work.”
Radiology labs and hospitals in any country can request access to the tool by visiting https://lens-immersive.com/about.
Nanostructured layers boast countless potential properties — but how can the most suitable...
The goal was to design and deploy a decision-support tool using AI capabilities — mostly...
Researchers have managed to make intact human organs transparent, and subsequently used...