Automatic segmentation of head and neck tumors and nodal metastases in PET-CT scans

Andrearczyk, Vincent (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Oreiller, Valentin (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland) ; Vallières, Martin (McGill University, Montréal, Canada ; Université de Sherbrooke, Sherbrooke, Canada) ; Castelli, Joel (Cancer Institute Eugène Marquis, Rennes, France ; INSERM, U1099, Rennes, France ; University of Rennes 1, LTSI, Rennes, France) ; Elhalawani, Hesham (Cleveland Clinic Foundation, Department of Radiation Oncology, Cleveland, OH, USA) ; Jreige, Mario (Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland) ; Boughdad, Sarah (Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland) ; Prior, John O. (Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland) ; Depeursinge, Adrien (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland)

Radiomics, the prediction of disease characteristics using quantitative image biomarkers from medical images, relies on expensive manual annotations of Regions of Interest (ROI) to focus the analysis. In this paper, we propose an automatic segmentation of Head and Neck (H&N) tumors and nodal metastases from FDG-PET and CT images. A fully-convolutional network (2D and 3D V-Net) is trained on PET-CT images using ground truth ROIs that were manually delineated by radiation oncologists for 202 patients. The results show the complementarity of the two modalities with a statistically significant improvement from 48.7% and 58.2% Dice Score Coefficients (DSC) with CT- and PET-only segmentation respectively, to 60.6% with a bimodal late fusion approach. We also note that, on this task, a 2D implementation slightly outperforms a similar 3D design (60.6% vs 59.7% for the best results respectively). The data is publicly available and the code will be shared on our GitHub repository.


Note: Due to the COVID-19 outbreak, the Medical Imaging with Deep Learning conference venue in Montréal was cancelled. The proceedings of the online conference are however published according to the original schedule.


Keywords:
Conference Type:
published full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Montréal, Canada, 6-9 July 2020
Date:
2020-07
Montréal, Canada
6-9 July 2020
Pagination:
Pp. 33-43
Published in:
Proceedings of International conference on medical imaging with deep learning
Series Statement:
Proceedings of Machine Learning Research, vol. 121
External resources:
Appears in Collection:



 Record created 2020-11-17, last modified 2021-02-05

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)