Artificial intelligence driving digital pathology

An upgrade in The University of Queensland’s artificial intelligence capabilities could help to revolutionise pathology laboratories across Australia.

 

Professor Brian Lovell said UQ’s high-performance computer, Weiner, was now able to deliver unprecedented performance for image processing and deep learning algorithms, allowing advancements in digital pathology.

 

“We’ve also managed to run a number of graphics processing units in parallel, speeding up artificial intelligence training to run up to hundreds of times faster than before,” Professor Lovell said.

 

Sullivan Nicolaides Pathology (SNP) CEO Dr Michael Harrison said the developments would bring a number of benefits for the industry, with almost 70 per cent of general practitioner diagnoses based on pathology tests.

 

“Developing AI for digital microscopy in pathology is an iterative process requiring extensive validation and standardisation,” Dr Harrison said.

 

“These advances will significantly hasten the development of AI algorithms in digital pathology and enable earlier movement into the routine pathology setting.

 

“We see AI as augmenting the quality and efficiency of pathology rather than replacing pathologists and scientists, and it is successfully being used at SNP to augment the quality and interpretation of some testing.”

 

The project will have applications in all areas of microscopy in pathology, including immunology, histopathology and microbiology specialities.

 

UQ Deputy Vice-Chancellor (Research) Professor Bronwyn Harch said digital pathology was just one example of how AI and machine learning was developing at UQ.

 

“The University’s AI capabilities continue to grow, allowing us to deliver novel solutions in the new Industry 4.0 age with our industry and government partners,” Professor Harch said.

 

“The applicability of this technology is huge, and this upgrade will assist in accelerating a wide variety of research projects across UQ.”