Chest CT Lung Nodule MRMC Reader Study

Challenge

Demonstrating the clinical value of a lung nodule detection tool required a multi-reader multi-case study comparing reader performance with and without algorithmic assistance. The design demanded readers spanning a range of experience levels to support generalizable conclusions, together with a reading workflow that would prevent recall of prior interpretations from contaminating the comparison between aided and unaided sessions. Every element of the design had to satisfy the evidentiary expectations of a 510(k) submission.

Our Solution

Intrinsic Imaging recruited and trained a reader group of 18 radiologists spanning the required experience spectrum, then administered randomized reading sequences separated by a four-week washout period to eliminate recall bias between sessions. A reference-standard panel of thoracic radiologists established truth for every case, and all reading activity was captured in a controlled, fully documented environment suitable for regulatory review.

Results

• All reader assessments completed within 10 weeks
• Improved reader sensitivity with algorithmic assistance
• Study data accepted in the 510(k) submission