Machine learning systems are not like thermometers, reliably measuring the temperature via universal rules of physics; nor are they like trained clinicians, gracefully adapting to new circumstances. Rather, these systems should be viewed as a set of rules that were trained to operate under certain contexts and rely on certain assumptions and might work seamlessly at one centre but fail somewhere else.
In this update we can conclude:
Current AI prostate cancer software delivers consistent, average radiologists’ performance with average levels of false alarms/false assurances. The current role is to improve the consistency of MRI reporting of radiologists.
A generalizable, biopsy decision support tool requires multicentric, multivendor validation studies against a stronger histologic standard (few rigorous studies to date)
The contribution to the current standard of PI-RADS-based multidisciplinary care needs assessing before full deployment into a community-wide, prostate cancer diagnosis pathway
7 сен 2024
