Histopathological Classification of Canine Cutaneous Round Cell Tumors Using Deep Learning: A Multi-Center Study
Grading (engineering)
DOI:
10.3389/fvets.2021.640944
Publication Date:
2021-03-26T04:52:07Z
AUTHORS (10)
ABSTRACT
Canine cutaneous round cell tumors (RCT) represent one of the routine diagnostic challenges for veterinary pathologists. Computer-aided approaches are developed to overcome these restrictions and increase accuracy consistency diagnosis. These systems also high benefit reducing errors when a large number cases screened daily. In this study we describe ARCTA (Automated Round Cell Tumors Assessment), fully automated algorithm RCT classification mast grading in canine histopathological images. employs deep learning strategy was on 416 images 213 test set, our exhibited an excellent performance both (accuracy: 91.66%) 100%). Misdiagnoses were encountered histiocytomas train set melanomas set. For reduction grade observed but not To best knowledge, proposed model is first histological specifically medicine. Being very fast (average computational time 2.63 s), paves way effective evaluation tumors.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (25)
CITATIONS (20)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....