| Autor: |
Rai T; Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford GU2 7XH, UK.; Surrey DataHub, University of Surrey, Guildford GU2 7AL, UK., Morisi A; School of Veterinary Medicine, University of Surrey, Guildford GU2 7AL, UK., Bacci B; Department of Veterinary Medical Sciences, University of Bologna, 40126 Bologna, Italy., Bacon NJ; AURA Veterinary, Guildford GU2 7AJ, UK., Dark MJ; Department of Comparative, Diagnostic and Population Medicine, College of Veterinary Medicine, University of Florida, Gainesville, FL 32611, USA., Aboellail T; Department of Diagnostic Pathology and Pathobiology, Kansas State University, Manhattan, KS 66506, USA., Thomas SA; Department of Computer Science, University of Surrey, Guildford GU2 7XH, UK.; National Physical Laboratory, London TW11 0LW, UK., La Ragione RM; School of Veterinary Medicine, University of Surrey, Guildford GU2 7AL, UK.; School of Biosciences, University of Surrey, Guildford GU2 7XH, UK., Wells K; Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford GU2 7XH, UK.; Surrey DataHub, University of Surrey, Guildford GU2 7AL, UK. |
| Abstrakt: |
Performing a mitosis count (MC) is the diagnostic task of histologically grading canine Soft Tissue Sarcoma (cSTS). However, mitosis count is subject to inter- and intra-observer variability. Deep learning models can offer a standardisation in the process of MC used to histologically grade canine Soft Tissue Sarcomas. Subsequently, the focus of this study was mitosis detection in canine Perivascular Wall Tumours (cPWTs). Generating mitosis annotations is a long and arduous process open to inter-observer variability. Therefore, by keeping pathologists in the loop, a two-step annotation process was performed where a pre-trained Faster R-CNN model was trained on initial annotations provided by veterinary pathologists. The pathologists reviewed the output false positive mitosis candidates and determined whether these were overlooked candidates, thus updating the dataset. Faster R-CNN was then trained on this updated dataset. An optimal decision threshold was applied to maximise the F1-score predetermined using the validation set and produced our best F1-score of 0.75, which is competitive with the state of the art in the canine mitosis domain. |
