Testing remote feedback using a virtual semi-automated educational tool for the detection of pancreatic tumour-vessel
Robert Policelli1, Aaron Ward2, Salma Dammak3
1Western University, Department of Medical Biophysics, 1151 Richmond St, London, Ontario, N6A 3k7, Canada.
Purpose:
Assessing tumour-vessel contact in pancreatic adenocarcinoma on CT is challenging for trainees and time-intensive for educators. Semi-automating feedback on this task may optimize radiologist time and standardize resident education. We hypothesized that residents who reviewed expert annotations of tumour-vessel contact would outperform those without feedback on an independent test set.
Methods:
We retrospectively reviewed pre-operative staging CTs from 60 patients who underwent upfront surgical resection for pancreatic adenocarcinoma. Two resident groups (control and test) independently annotated tumour contact with the superior mesenteric artery. The test group received feedback-annotations from three expert radiologists-for the first 30 cases; the control group received none. Resident performance on the remaining 30 cases was compared against both surgical pathology and expert annotations.
Results:
Test group residents demonstrated higher sensitivity than control group residents (mean sensitivity = 93 % vs. 79 %), with comparable specificity and accuracy relative to surgical pathology. While both groups performed similarly relative to expert consensus, the test group showed greater consistency in sensitivity (mean variation = 29 % vs. 46 %).
Conclusion:
Virtual expert feedback improved resident sensitivity in identifying tumour-vessel contact without compromising specificity or accuracy. These findings support the use of semi-automated educational tools to enhance radiology training efficiency and effectiveness.
