Skip to Main content Skip to Navigation
Journal articles

Voxel-based identification of local recurrence sub-regions from pre-treatment PET/CT for locally advanced head and neck cancers

Abstract : Background - Overall, 40% of patients with a locally advanced head and neck cancer (LAHNC) treated by chemoradiotherapy (CRT) present local recurrence within 2 years after the treatment. The aims of this study were to characterize voxel-wise the sub-regions where tumor recurrence appear and to predict their location from pre-treatment F-fluorodeoxyglucose (FDG) positron emission tomography (PET) images. Materials and methods - Twenty-six patients with local failure after treatment were included in this study. Local recurrence volume was identified by co-registering pre-treatment and recurrent PET/CT images using a customized rigid registration algorithm. A large set of voxel-wise features were extracted from pre-treatment PET to train a random forest model allowing to predict local recurrence at the voxel level. Results - Out of 26 expert-assessed registrations, 15 provided enough accuracy to identify recurrence volumes and were included for further analysis. Recurrence volume represented on average 23% of the initial tumor volume. The MTV with a threshold of 50% of SUVmax plus a 3D margin of 10 mm covered on average 89.8% of the recurrence and 96.9% of the initial tumor. SUV and MTV alone were not sufficient to identify the area of recurrence. Using a random forest model, 15 parameters, combining radiomics and spatial location, were identified, allowing to predict the recurrence sub-regions with a median area under the receiver operating curve of 0.71 (range 0.14-0.91). Conclusion - As opposed to regional comparisons which do not bring enough evidence for accurate prediction of recurrence volume, a voxel-wise analysis of FDG-uptake features suggested a potential to predict recurrence with enough accuracy to consider tailoring CRT by dose escalation within likely radioresistant regions.
Document type :
Journal articles
Complete list of metadatas

Cited literature [51 references]  Display  Hide  Download

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02304386
Contributor : Laurent Jonchère <>
Submitted on : Friday, July 10, 2020 - 11:12:16 AM
Last modification on : Wednesday, July 15, 2020 - 12:14:03 PM

File

Beaumont-2019-Voxel-based iden...
Publisher files allowed on an open archive

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

J Beaumont, O Acosta, A Devillers, X Palard-Novello, E Chajon, et al.. Voxel-based identification of local recurrence sub-regions from pre-treatment PET/CT for locally advanced head and neck cancers. EJNMMI Research, SpringerOpen, 2019, 9 (1), pp.90. ⟨10.1186/s13550-019-0556-z⟩. ⟨hal-02304386⟩

Share

Metrics

Record views

63

Files downloads

45