Self-directed learning impacts prostate tumor detection from MRI, according to a study published in the American Journal of Roentgenology.
Researchers from NYU Langone Medical Center in New York evaluated the roles of self-directed learning and continual feedback in the learning curve for tumor detection by novice readers of prostate MRI.
The study included 124 prostate MRI examinations; 52 were classified as positive (PI-RADS category 3 or higher lesion showing Gleason score ≥ 7 tumor at MRI-targeted biopsy) and 72 as negative (PI-RADS category 2 or lower and negative biopsy). These were divided into four equal-sized batches, each with matching numbers of positive and negative examinations and given to six second-year radiology residents for review examinations. Three readers received feedback after each examination showing the preceding case's solution. The learning curve, plotting accuracy over time, was assessed by the Akaike information criterion (AIC).
The results showed some improvement for both groups:
-Accuracy improvement (without a difference in the extent of improvement): 58.1% (batch 1) to 71.0-75.3% (batches 2-4) without feedback
58.1% to 72.0-77.4% with feedback
- Specificity improvement (without a difference in the etxtent of improvement): 53.7% to 68.5%-81.5% without feedback
55.6% to 74.1-81.5% with feebac
-Sensitivity improvement: 59.0-61.5% (batches 1-2) to 71.8-76.9% (batches 3-4) with feedback
Did not improvement without feedback
Sensitivity for transition zone tumors exhibited larger changes with feedback than without feedback, but sensitivity for peripheral zone tumors did not improve in either group. Reader confidence increased only with feedback.
The researchers concluded that the learning curve in prostate tumor detection largely reflected self-directed learning and continual feedback had a lesser effect. Clinical prostate MRI interpretation by novice radiologists warrants caution.