Artificial intelligence assisted tools for prostate cancer diagnosis using whole slide biopsy images
Topic Status Complete
Artificial intelligence assisted tools for prostate cancer diagnosis using whole slide biopsy images
Outcome of the appraisal
There is insufficient evidence to support the routine adoption of AI-assisted review of prostate biopsies in the detection and diagnosis of prostate cancer.
There is currently limited peer-reviewed evidence on the effectiveness of AI technologies, but that which is available is promising and shows the potential for AI technologies to support pathologists in diagnosing prostate cancer.
Further research is recommended to understand the clinical and cost-effectiveness of the AI systems, as well as their impact on real-world clinical practice. In particular, Health Technology Wales would support the analysis of data from the ongoing pilot project using an AI system for prostate cancer diagnosis in NHS Wales.
Why was this topic appraised?
Prostate cancer is the most common cancer in men in the UK, affecting around 2,000 men in Wales each year. Confirmation of the diagnosis involves blood tests, scans and the assessment of biopsy tissue by a pathologist, either under the microscope or using digital review. Artificial Intelligence (AI) technologies have been developed to assist in this assessment, with the aim of improving diagnostic accuracy and reducing case review time. The AI can highlight areas of abnormality to the pathologist and can help assess the Gleason Grade of the biopsy to determine the extent and aggressiveness of the cancer. This information assists in the selection of different treatments. The topic was submitted to HTW by a company producing AI technology.
Plain language summary
While there is no official definition of Artificial Intelligence (AI), it is defined by the Oxford Dictionary as “the theory and development of computer systems able to perform tasks normally requiring human intelligence”. This can include tasks like visual perception, speech recognition, decision-making, and translation between languages. AI currently has many roles in healthcare, such as domestic, administrative, diagnosis, testing and treatment. Different terms can be used to describe the AI dependant on its role.
Prostate cancer is the abnormal growth of cells in the prostate. It is diagnosed through a biopsy of the suspected tissue. A biopsy is where a small amount of tissue is taken for examination. The slides containing the tissue are examined by a pathologist. The slides can be looked at under a microscope or by a computer using digital images. The pathologist decides if the tissue is cancerous and assigns it a grade. The grade indicates how advance the cancer is.
Artificial Intelligence assisted prostrate biopsy uses a form of AI to examine prostate biopsies. Digital images, known as whole slide images (WSIs) of suspected tissue that are compatible with the AI must be taken. The AI is programmed to be able to identify cancerous tissue. The AI will flag WSIs which require further review and can assist in the grading of the cancer and pre-ordering of testing. The pathologist makes the final decisions. It is proposed that the use of AI assisted prostate biopsy will reduce the possibility of cancer being missed or incorrectly graded and reduce the need for repeat procedures or testing.
Health Technology Wales looked for evidence of Artificial Intelligence (AI) assisted review of prostate biopsies in the detection and diagnosis of prostate cancer. There is insufficient evidence to support the routine adoption of AI-assisted review of prostate biopsies in the detection and diagnosis of prostate cancer.
Topic Exploration Report
TER480 09.2023
Evidence Appraisal Review
EAR057 05.2024
Guidance
GUI057 05.2024