Friends of Cancer Research has identified multiple key operational problems in precision oncology, and help stakeholders craft solutions.
Here's a new effort of considerable interest - bringing AI to RECIST - the detection of cancer relapse.
Find the home page here:
https://friendsofcancerresearch.org/ai-recist/
See also a 3 page mini summary deck:
https://friendsofcancerresearch.org/wp-content/uploads/ai.RECIST-Project-Slides.pdf
Better measurement (consistency and precision) of imaging relapse is CRITICAL to molecular MRD development, as imaging is taken as the gold standard against which molecular MRD must out-perform. The more precise and tight the error bars are, around imaging, the easier and quicker it is to show better performance for liquid biopsy.
###
They summarize as follows:
What is the unmet need and why does it matter?
Tumor response metrics are used to determine the efficacy of cancer therapies in solid tumor clinical trials. These measurements rely on standardized and unbiased criteria through the Response Evaluation Criteria in Solid Tumors (RECIST) performed by expert human readers. RECIST-based assessments provide a systematic approach to objective tumor measurements at defined timepoints, but their implementation faces several challenges, including investigator bias, subjectivity in lesion selection, and variability in measurements across clinical sites and radiologists. Artificial intelligence (AI)-driven tumor measurement tools have the potential to address these challenges, reducing variability, increasing efficiency, and improving measurement accuracy.
How are we helping to find solutions?
Friends created a research partnership to evaluate AI-driven tumor measurement tools alongside human-reader RECIST assessments.
Key objectives:
- Assess AI tool agreement – Can AI-based tools provide consistent tumor measurements?
- Compare variability among AI tools and human assessments – How well do AI-driven measurements align with RECIST-based readings by human readers?
- Explore AI’s impact on efficiency – Can AI tools reduce variability and streamline clinical trials?
How does this impact patients?
Blinded Independent Central Review (BICR) is used in clinical trials to ensure accurate tumor assessments. Regulators often require BICR to minimize bias by blinding human readers to patient and treatment details when evaluating imaging-based endpoints like progression-free survival and objective response rate. However, BICR is resource-intensive, potentially prolonging trial timelines, delaying treatment decisions, and increasing costs. These delays may limit patient access to new therapies and, in some cases, may require additional imaging or adjudication when discrepancies occur between local and central assessments. AI-driven tumor measurement tools have the potential to streamline this process by ensuring consistent, unbiased verification of local assessments, reducing review time, and improving trial efficiency without compromising data integrity. By enhancing the speed and reliability of tumor measurements, AI could accelerate clinical trial progress and improve patient access to effective treatments.
###
