PT  - JOURNAL ARTICLE
AU  - Christof A. Bertram
AU  - Marc Aubreville
AU  - Taryn A. Donovan
AU  - Alexander Bartel
AU  - Frauke Wilm
AU  - Christian Marzahl
AU  - Charles-Antoine Assenmacher
AU  - Kathrin Becker
AU  - Mark Bennett
AU  - Sarah Corner
AU  - Brieuc Cossic
AU  - Daniela Denk
AU  - Martina Dettwiler
AU  - Beatriz Garcia Gonzalez
AU  - Corinne Gurtner
AU  - Ann-Kathrin Haverkamp
AU  - Annabelle Heier
AU  - Annika Lehmbecker
AU  - Sophie Merz
AU  - Erica L. Noland
AU  - Stephanie Plog
AU  - Anja Schmidt
AU  - Franziska Sebastian
AU  - Dodd G. Sledge
AU  - Rebecca C. Smedley
AU  - Marco Tecilla
AU  - Tuddow Thaiwong
AU  - Andrea Fuchs-Baumgartinger
AU  - Don J. Meuten
AU  - Katharina Breininger
AU  - Matti Kiupel
AU  - Andreas Maier
AU  - Robert Klopfleisch
TI  - Computer-Assisted Mitotic Count Using a Deep Learning-based Algorithm Improves Inter-Observer Reproducibility and Accuracy in canine cutaneous mast cell tumors
AID  - 10.1101/2021.06.04.446287
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.06.04.446287
4099  - http://biorxiv.org/content/early/2021/06/05/2021.06.04.446287.short
4100  - http://biorxiv.org/content/early/2021/06/05/2021.06.04.446287.full
AB  - The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intra-observer discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying/classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, the computer-assisted review by pathologists may ensure reliability. In the present study we have compared partial (MC-ROI preselection) and full (additional visualization of MF candidate proposal and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MF and improving classification against imposters. The inter-observer consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38%. The results of this study prove that computer assistance may lead to a more reproducible and accurate MCs in ccMCTs.Competing Interest StatementThe authors have declared no competing interest.