Improved ground truth annotation by multimodal image registration from 3D ultrasound to histopathology for resected tongue carcinoma
European Archives of Oto-Rhino-Laryngology · 2025-03 · 282 (3) · 1399-1409
DOI: 10.1007/s00405-024-08979-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Archives of Oto-Rhino-Laryngology, online erschienen am 30.09.2024. Verfasst von N M Bekedam und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni Van Leeuwenhoek, Plesmanlaan 121, 1066 CX, Amsterdam, The Neth…. Hauptthemen laut MEDLINE: Tongue Neoplasms, Imaging, Three-Dimensional, Multimodal Imaging. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objectives
This study’s objectives are (1) to investigate the registration accuracy from intraoperative ultrasound (US) to histopathological images, (2) to assess the agreement and correlation between measurements in registered 3D US and histopathology, and (3) to train a nnUNet model for automatic segmentation of 3D US volumes of resected tongue specimens.
Methods
Ten 3D US volumes were acquired, including the corresponding digitalized histopathological images (n = 29). Based on corresponding landmarks, the registrations between 3D US and histopathology images were calculated and evaluated using the target registration error (TRE). Tumor thickness and resection margins were measured based on three annotations: (1) manual histopathological tumor annotation (HTA), manual 3D US tumor annotation, and (2) the HTA registered in the 3D US. The agreement and correlation were computed between the measurements based on the HTA and those based on the manual US and registered HTA in US. A deep-learning model with nnUNet was trained on 151 3D US volumes. Segmentation metrics quantified the model’s performance.
Results
The median TRE was 0.42 mm. The smallest mean difference was between registered HTA in US and histopathology with 2.16 mm (95% CI − 1.31; 5.63) and a correlation of 0.924 (p < 0.001). The nnUNet predicted the tumor with a Dice similarity coefficient of 0.621, an average surface distance of 1.15 mm, and a Hausdorff distance of 3.70 mm.
Conclusion
Multimodal image registration enabled the HTA’s registration in the US images and improved the agreement and correlation between the modalities. In the future, this could be used to annotate ground truth labels accurately.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni Van Leeuwenhoek, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands. n.bekedam@nki.nl.
- Academic Centre of Dentistry Amsterdam, Vrije Universiteit, Gustav Mahlerlaan 3004, 1081 LA, Amsterdam, The Netherlands. n.bekedam@nki.nl.
- Department of Head and Neck Surgery and Oncology, Verwelius 3D Lab, Netherlands Cancer Institute, Antoni Van Leeuwenhoek, Amsterdam, The Netherlands.
- Department of Pathology, Netherlands Cancer Institute, Antoni Van Leeuwenhoek, Amsterdam, The Netherlands.
- Department of Head and Neck Surgery and Oncology, Netherlands Cancer Institute, Antoni Van Leeuwenhoek, Plesmanlaan 121, 1066 CX, Amsterdam, The Netherlands.
Zitieren
APA
Bekedam, N. M., van Alphen, M. J. A., de Cuba, E. M. V., Karssemakers, L. H. E., Karakullukcu, M. B., & Smeele, L. E. (2025). Improved ground truth annotation by multimodal image registration from 3D ultrasound to histopathology for resected tongue carcinoma. European Archives of Oto-Rhino-Laryngology, 282(3), 1399-1409. https://doi.org/10.1007/s00405-024-08979-1
Vancouver
Bekedam NM, van Alphen MJA, de Cuba EMV, Karssemakers LHE, Karakullukcu MB, Smeele LE. Improved ground truth annotation by multimodal image registration from 3D ultrasound to histopathology for resected tongue carcinoma. European Archives of Oto-Rhino-Laryngology. 2025;282(3):1399-1409. doi:10.1007/s00405-024-08979-1
BibTeX
@article{Bekedam2025,
author = {Bekedam, N M and van Alphen, M J A and de Cuba, E M V and Karssemakers, L H E and Karakullukcu, M B and Smeele, L E},
title = {Improved ground truth annotation by multimodal image registration from 3D ultrasound to histopathology for resected tongue carcinoma},
journal = {European Archives of Oto-Rhino-Laryngology},
year = {2025},
volume = {282},
number = {3},
pages = {1399--1409},
doi = {10.1007/s00405-024-08979-1}
}
EUVIMED