Australian research to improve AI diagnosis from chest X-rays

STORY: Australian research to improve AI diagnosis from chest X-rays SHOOTING TIME: Nov. 20, 2023 DATELINE: Nov. 21, 2023 LENGTH: 00:00:31 LOCATION: Canberra CATEGORY: HEALTH/TECHNOLOGY SHOTLIST: 1. various of a radiology hospital STORYLINE: Australian researchers have identified methods for improving artificial intelligence (AI) diagnosis of heart and lung conditions. In a world-first study, a team from the Australian e-Health Research Centre (AEHRC) at the national science agency the Commonwealth Scientific and Industrial Research Organization (CSIRO) compared the accuracy of different AI models in interpreting chest X-rays. They found that by using the optimal combination of an encoder and decoder, automated AI diagnoses of heart and lung conditions from X-ray images can be made 26.9 percent more accurate. Current AI X-ray report generation technology uses an encoder to interpret images and a decoder to produce a report. The AEHRC research was the first globally into which encoder and decode

Piezo Sonic's PSM60N-ET ultrasonic motor. Motor (front) and driver (back)

Piezo Sonic's PSM60N-ET ultrasonic motor. Motor (front) and driver (back)

Piezo Sonic (Setagaya-ku, Tokyo) has released a high-torque ultrasonic motor, the PSM60N. The ultrasonic motor rotates by minute vibrations and frictional force. Since it does not use coils and magnets, it can be used in high magnetic field environments such as magnetic resonance tomography (MRI) systems.The company's ultrasonic motor uses a piezoelectric element to vibrate a ring with a comb-shaped slit. When the rotor (rotating body) is brought into contact with the ring, the vibration of the teeth is transmitted to the rotor, which rotates. The comb tooth structure amplifies the vibration. We chose a material with high friction to increase the torque. The maximum torque is 1.2 Newton meters, which is 5 to 10 times higher than a DC motor of the same size. The motor is also equipped with an optical encoder. (Photo taken on December 4, 2019, credit: Nikkan Kogyo Shimbun / Kyodo News Images)