Automatic gross tumor segmentation of canine head and neck cancer using deep learning and cross-species transfer learning.

Autor:	Groendahl AR; Faculty of Science and Technology, Department of Physics, Norwegian University of Life Sciences, Ås, Norway., Huynh BN; Faculty of Science and Technology, Department of Physics, Norwegian University of Life Sciences, Ås, Norway., Tomic O; Faculty of Science and Technology, Department of Data Science, Norwegian University of Life Sciences, Ås, Norway., Søvik Å; Faculty of Veterinary Medicine, Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Ås, Norway., Dale E; Department of Oncology, Oslo University Hospital, Oslo, Norway., Malinen E; Department of Physics, University of Oslo, Oslo, Norway.; Department of Medical Physics, Oslo University Hospital, Oslo, Norway., Skogmo HK; Faculty of Veterinary Medicine, Department of Companion Animal Clinical Sciences, Norwegian University of Life Sciences, Ås, Norway., Futsaether CM; Faculty of Science and Technology, Department of Physics, Norwegian University of Life Sciences, Ås, Norway.
Jazyk:	angličtina
Zdroj:	Frontiers in veterinary science [Front Vet Sci] 2023 Mar 21; Vol. 10, pp. 1143986. Date of Electronic Publication: 2023 Mar 21 (Print Publication: 2023).
DOI:	10.3389/fvets.2023.1143986
Abstrakt:	Background: Radiotherapy (RT) is increasingly being used on dogs with spontaneous head and neck cancer (HNC), which account for a large percentage of veterinary patients treated with RT. Accurate definition of the gross tumor volume (GTV) is a vital part of RT planning, ensuring adequate dose coverage of the tumor while limiting the radiation dose to surrounding tissues. Currently the GTV is contoured manually in medical images, which is a time-consuming and challenging task. Purpose: The purpose of this study was to evaluate the applicability of deep learning-based automatic segmentation of the GTV in canine patients with HNC. Materials and Methods: Contrast-enhanced computed tomography (CT) images and corresponding manual GTV contours of 36 canine HNC patients and 197 human HNC patients were included. A 3D U-Net convolutional neural network (CNN) was trained to automatically segment the GTV in canine patients using two main approaches: (i) training models from scratch based solely on canine CT images, and (ii) using cross-species transfer learning where models were pretrained on CT images of human patients and then fine-tuned on CT images of canine patients. For the canine patients, automatic segmentations were assessed using the Dice similarity coefficient ( Dice ), the positive predictive value, the true positive rate, and surface distance metrics, calculated from a four-fold cross-validation strategy where each fold was used as a validation set and test set once in independent model runs. Results: CNN models trained from scratch on canine data or by using transfer learning obtained mean test set Dice scores of 0.55 and 0.52, respectively, indicating acceptable auto-segmentations, similar to the mean Dice performances reported for CT-based automatic segmentation in human HNC studies. Automatic segmentation of nasal cavity tumors appeared particularly promising, resulting in mean test set Dice scores of 0.69 for both approaches. Conclusion: In conclusion, deep learning-based automatic segmentation of the GTV using CNN models based on canine data only or a cross-species transfer learning approach shows promise for future application in RT of canine HNC patients. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2023 Groendahl, Huynh, Tomic, Søvik, Dale, Malinen, Skogmo and Futsaether.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu