medical imaging tagged posts

Researchers at Monash University have designed a new co-training AI algorithm for medical imaging that can effectively mimic the process of seeking a second opinion.

Published recently in Nature Machine Intelligence, the research addressed the limited availability of human annotated, or labelled, medical images by using an adversarial, or competitive, learning approach against unlabelled data.

This research, by Monash University faculties of Engineering and IT, will advance the field of medical image analysis for radiologists and other health experts.

PhD candidate Himashi Peiris of the Faculty of Engineering, said the research design had set out to create a competition between the two components...

A new class of quantum dots deliver a stable stream of single, spectrally tunable infrared photons under ambient conditions and at room temperature, unlike other single photon emitters. This breakthrough opens a range of practical applications, including quantum communication, quantum metrology, medical imaging and diagnostics, and clandestine labeling.

“The demonstration of high single-photon purity in the infrared has immediate utility in areas such as quantum key di...

Engineers have demonstrated for the first time that it’s possible to connect a network of sensors through quantum entanglement. The experiment opens a door to unprecedented levels of sensitivity in GPS navigation, medical imaging and astronomy.

Your phone’s GPS, the WiFi in your house and communications on aircraft are all powered by radio-frequency waves, or waves, which carry information from a transmitter at one point to a sensor at another. The sensors interpret this information in different ways. For example, a GPS sensor uses the angle at which it receives an RF wave to determine its own relative location. The more precisely it can measure the angle, the more accurately it can determine location.

In a paper pu...

User opening a file in a PixelDrone cone tree. Credit: Image courtesy of Queen’s University

An interactive swarm of flying 3D pixels (voxels) is set to revolutionize the way people interact with virtual reality. The system, called BitDrones, allows users to explore virtual 3D information by interacting with physical self-levitating building blocks – materials capable of changing their 3D shape in a programmable fashion – using swarms of nano quadcopters. Apps include real-reality 3D modeling, gaming, molecular modeling, medical imaging, robotics and online information visualization.

“BitDrones brings flying programmable matter, such as featured in the futuristic Disney movie Big Hero 6, closer to reality,” says Dr. Vertegaal...