Evaluation of the mitotic score of invasive breast carcinomas on digital slide: development and contribution of a mitosis detection algorithm

Introduction:Nottingham grading system is a major prognostic factor for invasive breast carcinoma (IBC).Its determination requires the evaluation of the mitotic score (MS) which is subject to low intraand interobserver reproducibility. The MS shall be performed in the most proliferative area ofthe tumor, which determination is hard but critical. Artificial intelligence based tools could helppathologists to detect mitosis on whole slide images (WSI).ObjectiveThe aim of this study was to evaluate the contribution of a mitosis detection algorithmspecifically developed to assist the pathologist during the evaluation of the MS on WSI.Methods:Algorithmic mitosis detection is a two-step process : first the algorithm detects candidateobjects resembling mitosis, then the selection is refined by a classifier. The densest mitoticregions are shown to the pathologist, then he can establish the MS with algorithm results. Forthis study, three expert pathologists have determined a consensual ground truth for MS onfifty WSI of IBC. Those slides were also submitted to two readers pathologists who evaluatedthe MS of each slide twice, with and without the assistance of the algorithm, with a four weekwash-out period. Interobserver reproducibility was measured by evaluating the scoresobtained with, and without assistance between two readers pathologists and was alsomeasured between each reader pathologist and the expert ground truth to determine theaccuracy of the established score.Results:Baseline linearly weighted Cohen's Kappa for interobserver agreement of MS between tworeaders pathologists was 0.482. Using the algorithm generated mitotic detection in WSI, theagreement score increased to 0.672. Baseline linearly weighted Cohen's Kappa forinterobserver agreement of MS between each reader pathologist and expert consensus was0.378 and 0.457 for pathologist 1 and 2 respectively. Using the algorithm generated mitoticdetection in WSI, the agreement score increased respectively to 0.629 and 0.726.Conclusion:The use of the developed algorithm constitutes a viable approach to assist the pathologist forthe evaluation of the MS of IBC on WSI. Its use makes it possible to improve interobserverreproducibility between pathologists and the accuracy of the score established by expertconsensus. The use of such a tool constitutes a new approach in the evaluation of the mitoticscore which could lead to an evolution of practices.