Short Training Significantly Improves Ganglion Cell Detection Using an Algorithm-Assisted Approach

Abstract

Context.— Medical education in pathology relies on the accumulation of experience gained through inspection of numerous samples from each entity. Acquiring sufficient teaching material for rare diseases, such as Hirschsprung disease (HSCR), may be difficult, especially in smaller institutes. The current study makes use of a previously developed decision support system using a decision support algorithm meant to aid pathologists in the diagnosis of HSCR. Objective.— To assess the effect of a short training session on algorithm-assisted HSCR diagnosis. Design.— Five pathologists reviewed a data set of 568 image sets (1704 images in total) selected from 50 cases by the decision support algorithm and were tasked with scoring the images for the presence or absence of ganglion cells. The task was repeated a total of 3 times. Each pathologist had to complete a short educational presentation between the second and third iterations. Results.— The training resulted in a significantly increased rate of correct diagnoses (true positive/negative) and a decreased need for referrals for expert consultation. No statistically significant changes in the rate of false positives/negatives were detected. Conclusions.— A very short (<10 minutes) training session can greatly improve the pathologist's performance in the algorithm-assisted diagnosis of HSCR. The same approach may be feasible in training for the diagnosis of other rare diseases.

Algorithm-assisted diagnosis of Hirschsprung’s disease – evaluation of robustness and comparative image analysis on data from various labs and slide scanners

“…DL tools have been successfully implemented in tasks such as tumor classification and grading, assessment of cellularity, mutation prediction and more [ 5 – 11 ]. More recently, similar tools have been used for algorithm-assisted [ 12 , 13 ] or even fully-automated diagnosis [ 14 , 15 ]. Different slide scanner models may have differences in both features and performance [ 16 ].…”

“…A non-expert would have to send 20–58% of the cases to expert consultation to achieve similar performance [ 12 ]. Furthermore, in a follow-up study, a very short (10 min) training session with the same DSS was shown to greatly improve the pathologists performance in the algorithm-assisted diagnosis of HSCR while minimizing the need for expert consultation [ 13 ]. The DSS had been created based on a data set from a single hospital, processed at the same pathology laboratory and scanned by the same slide scanner model (Philips—IntelliSite Ultra-Fast Scanner).…”