AI diagnoses prostate cancer as accurately as specialists


Friday, 25 February, 2022

AI diagnoses prostate cancer as accurately as specialists

An international team of researchers, including Professor Brett Delahunt from the University of Otago, has found that artificial intelligence (AI) systems can diagnose prostate cancer biopsies with the same level of accuracy as specialist uropathologists, and better than many general pathologists.

Pathologists characterise tumours in terms of different ‘Gleason’ growth patterns, with biopsy specimens categorised into one of five International Society of Urological Pathology grade groups. Prof Delahunt said the process is quite subjective and can lead to both ‘undergrading’ and ‘overgrading’ of prostate cancer biopsies.

“Assessment of biopsies is crucial when it comes to making decisions on prostate cancer treatment — but there can be significant variations in the assessments made by different pathologists,” he said.

In 2020, Prof Delahunt participated in a research consortium which found the accuracy of computer-based diagnosis of prostate cancer was comparable to that of specialist urological pathologists, with the results published in The Lancet Oncology. In a newly published follow-up study in the journal Nature Medicine, the performance of different AI models was tested against the gold-standard diagnosis of prostate cancer provided by Prof Delahunt and two colleagues from Sweden’s Karolinska Institutet and The University of Queensland.

The researchers organised a global competition to build AI models to diagnose more than 10,000 prostate biopsies. More than 1000 AI developers from 65 countries participated in the competition, sending in 1010 algorithms to be assessed for accuracy in diagnosis, making it the largest known competition to be held into the use of AI in pathology. Fifteen of the algorithms were selected to have their performance measured against diagnoses made by specialist uropathologists and general pathologists, and were found to achieve high agreement with uropathologists and high sensitivity for malignant biopsies.

Prof Delahunt said because the algorithms would likely miss fewer cancers than the pathologists did, AI could be used to reduce the workload of pathologists by automating the identification and exclusion of most benign biopsies.

“Standardised AI models could really make a difference when it comes to improving outcomes for this disease,” he said.

Image credit: ©stock.adobe.com/au/SunnySmile

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.

Related News

AR tech gives haemophilia patients a glimpse of the future

The Australian-designed technology will enable young people living with haemophilia to view the...

Machine learning helps to determine leukaemia subtypes

ALLSorts software uses RNA sequencing data to identify a patient's subtype of acute...

Computer vision system analyses cells in microscopy videos

The system allows automatic analysis of biomedical videos captured by microscopy in order to...


  • All content Copyright © 2022 Westwick-Farrow Pty Ltd