Researchers train AI to diagnose lung diseases
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 Karim, Dr Sami Azam, Dr Kheng Cher Yeo, Professor 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.
Related Articles
Forensic scientists issue call to arms to build forensic intelligence capability
Forensics has well-recognised application in the courtroom, but a new report is arguing the science has much more to give.
Read more about Forensic scientists issue call to arms to build forensic intelligence capabilityGlobal sewage study reveals condition of Darwin’s harbour
A global study of sewage contamination in harbours, with samples taken from 18 cities across five continents, has revealed that faecal contamination of Darwin Harbour from sewage is very low compared to the rest of the world.
Read more about Global sewage study reveals condition of Darwin’s harbourTransport study reveals why journey is as important as the destination
A days’ long canoe voyage along the Arnhem Land coast can now be completed within hours in a tinnie, but accelerating movement has unique and complex implications for Indigenous peoples’ relationship with their ancestral Country, according to a new research paper.
Read more about Transport study reveals why journey is as important as the destination