.png)
Accurate HER2 status assessment is crucial in clinical decision-making. Moreover, scores 1+ and 2+ not amplified have been shown to benefit from treatment with the new HER2-based antibody-drug conjugates. In this context, we developed an artificial intelligence (AI) algorithm for automatic, precise and replicable quantification of HER2 protein overexpression, assisting pathologists in HER2 scoring.
We developed a fully-automated AI software for assisting pathologists in HER2 scoring. The proposed algorithm automatically detects invasive regions of the tumor and quantifies the tumor cells in these regions. It also characterizes each cell according to its membrane completeness and intensity and provides pathologists a readily interpretable score along with the details of the slide analysis, in accordance with the 2018 ASCO/CAP guidelines. Three breast expert pathologists scored a hold-out dataset of 70 WSI. After a washout period of two months, they re-scored these WSI with AI assistance. The performances of the model are evaluated by comparing the inter-observer agreement rate with and without AI, and by comparing the model results with the pathologists ground truth.
The model demonstrated an overall balanced accuracy of 90.3% on the validation dataset. The overall inter-observer agreement (Fleiss Kappa) significantly improved, going from 37% without A.I to 64% with AI assistance. The AI-based software achieved an accuracy of 98% in correctly scoring HER2-low carcinomas.
The proposed fully-automated solution could perform exhaustive tumor cell analysis in invasive tissue, without requiring any pathologist intervention. Moreover, such a solution could help to standardize the routine results between pathologists which can suffer from an important variability, thus improving the targeted therapeutic decision.
C Bossard, Y Salhi, T Florian, B Poulet, B Cormier, S Salhi, E Guinaudeau, L Lambros, I Chokri, F Jossic, J Chetritt