Gross failure rates and failure modes for a commercial AI-based auto-segmentation algorithm in head and neck cancer patients

CONCLUSION: True failures of the AI-based system were predominantly associated with a non-standard element within the CT scan. It is likely that these non-standard elements were the reason for the gross failure, and suggests that patient datasets used to train the AI model did not contain sufficient heterogeneity of data. Regardless of the reasons for failure, the true failure rate for the AI-based system in the H&N region for the OARs investigated was low (∼1%).PMID:38263866 | DOI:10.1002/acm2.14273
Source: Journal of Applied Clinical Medical Physics - Category: Physics Authors: Source Type: research