Implementing a deep learning model for automatic tongue tumour segmentation in ex-vivo 3-dimensional ultrasound volumes.

Autor: Bekedam NM; Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands; Academic Centre of Dentistry Amsterdam, Vrije Universiteit, Gustav Mahlerlaan 3004, 1081 LA Amsterdam, The Netherlands. Electronic address: n.bekedam@nki.nl., Idzerda LHW; Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands., van Alphen MJA; Department of Head and Neck Surgery and Oncology, Verwelius 3D Lab, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands., van Veen RLP; Department of Head and Neck Surgery and Oncology, Verwelius 3D Lab, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands., Karssemakers LHE; Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands., Karakullukcu MB; Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands., Smeele LE; Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni van Leeuwenhoek, Amsterdam, The Netherlands.
Jazyk: angličtina
Zdroj: The British journal of oral & maxillofacial surgery [Br J Oral Maxillofac Surg] 2024 Apr; Vol. 62 (3), pp. 284-289. Date of Electronic Publication: 2024 Jan 03.
DOI: 10.1016/j.bjoms.2023.12.017
Abstrakt: Three-dimensional (3D) ultrasound can assess the margins of resected tongue carcinoma during surgery. Manual segmentation (MS) is time-consuming, labour-intensive, and subject to operator variability. This study aims to investigate use of a 3D deep learning model for fast intraoperative segmentation of tongue carcinoma in 3D ultrasound volumes. Additionally, it investigates the clinical effect of automatic segmentation. A 3D No New U-Net (nnUNet) was trained on 113 manually annotated ultrasound volumes of resected tongue carcinoma. The model was implemented on a mobile workstation and clinically validated on 16 prospectively included tongue carcinoma patients. Different prediction settings were investigated. Automatic segmentations with multiple islands were adjusted by selecting the best-representing island. The final margin status (FMS) based on automatic, semi-automatic, and manual segmentation was computed and compared with the histopathological margin. The standard 3D nnUNet resulted in the best-performing automatic segmentation with a mean (SD) Dice volumetric score of 0.65 (0.30), Dice surface score of 0.73 (0.26), average surface distance of 0.44 (0.61) mm, Hausdorff distance of 6.65 (8.84) mm, and prediction time of 8 seconds. FMS based on automatic segmentation had a low correlation with histopathology (r = 0.12, p = 0.67); MS resulted in a moderate but insignificant correlation with histopathology (r = 0.4, p = 0.12, n = 16). Implementing the 3D nnUNet yielded fast, automatic segmentation of tongue carcinoma in 3D ultrasound volumes. Correlation between FMS and histopathology obtained from these segmentations was lower than the moderate correlation between MS and histopathology.
(Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: