Skip to content
Information Technology, Medical Health Aged Care

Researchers train AI to diagnose lung diseases

Charles Darwin University 2 mins read

Artificial Intelligence (AI) could become a radiologist’s best friend, with researchers training the technology to accurately diagnose pneumonia, COVID-19 and other lung diseases.

The new study by researchers from Charles Darwin University (CDU), United International University, and Australian Catholic University (ACU) on developing and training an AI model to analyse lung ultrasound videos and diagnose respiratory diseases. 

The model works by examining each video frame to find important features of the lungs and assesses the order of the video frames to understand the patterns of the lungs over time. 

The model then identifies specific patterns indicating different lung diseases and based on this information, classifies the ultrasound into a diagnosis category such as normal, pneumonia, COVID-19 and other lung diseases. 

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 model uses explainable AI, a method which allows human users to understand and trust the results created by machine learning algorithms.

“The explainability of the proposed model aims to increase the reliability of this approach,” 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.”

Associate Professor Shafiabady said if fed the appropriate data, the model could be trained to identify more diseases such as tuberculosis, black lung, asthma, cancer, chronic lung disease, and pulmonary fibrosis. 

The study was led by researchers at United International University in Bangladesh, alongside CDU researchers Dr Asif KarimDr Sami AzamDr Kheng Cher YeoProfessor Friso De Boer and Associate Professor Niusha Shafiabady, who is also a researcher at ACU.

Potential avenues for research include training the model to assess other imaging, such as CT scans and x-rays. 

Automated diagnosis of respiratory diseases from lung ultrasound videos ensuring XAI: an innovative hybrid model approach was published in journal Frontiers in Computer Science


Contact details:

Raphaella Saroukos she/her
Research Communications Officer
Marketing, Media & Communications
Larrakia Country
T: +61 8 8946 6721
E: media@cdu.edu.au
W: cdu.edu.au

Media

More from this category

  • Medical Health Aged Care
  • 15/02/2025
  • 06:30
Dementia Australia

Join us today for Huskisson Memory Walk & Jog

What: Dementia Australia’sHuskissonMemory Walk & Jog   When: Today, Saturday 15 February from 8am   Who: More than 230 locals participating on the day. People who have been impacted by dementia, their family, friends and carers.   Where: Voyager Park, Huskisson Photos and video of previous Memory Walk & Jog events for publication are available for use. For more information visit: www.memorywalk.com.au Dementia Australia is the source of trusted information, education and services for the estimated more than 433,300 Australians living with dementia, and the more than 1.7 million people involved in their care. We advocate for positive change and…

  • Contains:
  • Medical Health Aged Care
  • 14/02/2025
  • 17:00
NIPPON EXPRESS HOLDINGS, INC.

NIPPON EXPRESS HOLDINGS Completes Procedure to Make Germany’s SH HoldCo Wholly-owned Subsidiary

TOKYO, Feb. 14, 2025 /Kyodo JBN/ -- - Completion of Acquisition (Subsidiarization) of SH HoldCo GmbH Shares - NIPPON EXPRESS HOLDINGS, INC. is pleased to announce that the agreement concluded on September 30, 2024, for the acquisition of entire shares in SH HoldCo GmbH, the parent company of the Germany-based Simon Hegele Group, was executed with effect from February 3, 2025 ("the Transaction"). NX Logo: https://kyodonewsprwire.jp/img/202502063911-O3-3GW0nv63 The founder, Dieter Hegele (left), and the President of NXHD, Satoshi Horikiri: https://cdn.kyodonewsprwire.jp/prwfile/release/M103866/202502063911/_prw_PI1fl_Q8fxy492.jpg Headquartered in Karlsruhe, Germany, Simon Hegele is a contract logistics provider founded in 1920 that specializes in providing logistics services for…

  • Medical Health Aged Care
  • 14/02/2025
  • 15:37
Dementia Australia

Last chance to join us for Canberra Memory Walk & Jog!

With only a few sleeps to go, walkers, joggers, runners and volunteers are gearing up to participate in the 2025 Canberra Memory Walk & Jog. More than 1000 people have already signed-up to take part – but there’s always room for more with online registrations still open, or sign-up on the day of the event. Dementia Australia CEO Professor Tanya Buchanan said it was fantastic to see Canberra locals throwing their support behind Memory Walk & Jog, all while getting active for their brain health. “We look forward to hosting Memory Walk & Jog on Sunday 23 February at Barrine…

  • Contains:

Media Outreach made fast, easy, simple.

Feature your press release on Medianet's News Hub every time you distribute with Medianet. Pay per release or save with a subscription.