A research team from the Charles Darwin University, United International University, and Australian Catholic University (ACU) is developing and training artificial intelligence (AI) models to analyse lung ultrasound videos and diagnose respiratory diseases.
In one of the latest applications of AI in diagnostic medicine, the study has designed a model that examines each video frame to find important features of the lungs and assesses the order of frames to understand patterns over time.
The model than matches these Patterson to different lung diseases and classifies the ultrasound in a diagnosis category such as normal, pneumonia, COVID-19, etc.
Diagnostic accuracy of 96.57%
Study co-author and CDU adjunct Associate Professor Niusha Shafiabady said the model had an accuracy of 96.57 per cent, with the AI analyses verified by medical professionals.
“The model also uses AI techniques to show radiologists why it made certain decisions, making it easier for them to trust and understand the results,” Associate Professor Shafiabady said.
“The system shows doctors why it made certain decisions using visuals like heatmaps. This interpretation technique will aid a radiologist in localising the focus area and improve clinical transparency substantially.
“This model helps doctors diagnose lung diseases quickly and accurately, supports their decision-making, saves time, and serves as a valuable training tool.”
The model could be trained to identify more disease, including tuberculosis, black lung, asthma, cancer, chronic lung disease, and pulmonary fibrosis, or leverage other imaging such as CT scans and x-rays to make diagnostic assessments.
The study was led by researchers at United International University in Bangladesh, alongside CDU researchers Dr Asif Karim, Dr Sami Azam, Dr Kheng Cher Yeo, Professor Friso De Boer and Associate Professor Niusha Shafiabady, who is also a researcher at ACU.