Target volume delineation is a vital but time-consuming and challenging part of radiotherapy, where the goal is to deliver sufficient dose to the target while reducing risks of side effects. For head and neck cancer (HNC) this is complicated by the complex anatomy of the head and neck region and the proximity of target volumes to organs at risk. The purpose of this study was to compare and evaluate conventional PET thresholding methods, six classical machine learning algorithms and a 2D U-Net convolutional neural network (CNN) for automatic gross tumor volume (GTV) segmentation of HNC in PET/CT images. For the latter two approaches the impact of single versus multimodality input on segmentation quality was also assessed. 197 patients were included in the study. The cohort was split into training and test sets (157 and 40 patients, respectively). Five-fold cross-validation was used on the training set for model comparison and selection. Manual GTV delineations represented the ground truth. Tresholding, classical machine learning and CNN segmentation models were ranked separately according to the cross-validation Sørensen–Dice similarity coefficient (Dice). PET thresholding gave a maximum mean Dice of 0.62, whereas classical machine learning resulted in maximum mean Dice scores of 0.24 (CT) and 0.66 (PET; PET/CT). CNN models obtained maximum mean Dice scores of 0.66 (CT), 0.68 (PET) and 0.74 (PET/CT). The difference in cross-validation Dice between multimodality PET/CT and single modality CNN models was significant (p ≤ 0.0001). The top-ranked PET/CT-based CNN model outperformed the best-performing thresholding and classical machine learning models, giving significantly better segmentations in terms of cross-validation and test set Dice, true positive rate, positive predictive value and surface distance-based metrics (p ≤ 0.0001). Thus, deep learning based on multimodality PET/CT input resulted in superior target coverage and less inclusion of surrounding normal tissue.
9 February 2021 in European Journal of Nuclear Medicine and Molecular Imaging
Purpose: Identification and delineation of the gross tumour and malignant nodal volume (GTV) in medical images are vital in radiotherapy. We assessed the applicability of convolutional neural networks (CNNs) for fully automatic delineation of the GTV from FDG-PET/CT images of patients with head and neck cancer (HNC). CNN models were compared to manual GTV delineations made by experienced specialists. New structure-based performance metrics were introduced to enable in-depth assessment of auto-delineation of multiple malignant structures in individual patients. Methods: U-Net CNN models were trained and evaluated on images and manual GTV delineations from 197 HNC patients. The dataset was split into training, validation and test cohorts (n= 142, n = 15 and n = 40, respectively). The Dice score, surface distance metrics and the new structure-based metrics were used for model evaluation. Additionally, auto-delineations were manually assessed by an oncologist for 15 randomly selected patients in the test cohort. Results: The mean Dice scores of the auto-delineations were 55%, 69% and 71% for the CT-based, PET-based and PET/CT-based CNN models, respectively. The PET signal was essential for delineating all structures. Models based on PET/CT images identified 86% of the true GTV structures, whereas models built solely on CT images identified only 55% of the true structures. The oncologist reported very high-quality auto-delineations for 14 out of the 15 randomly selected patients. Conclusions: CNNs provided high-quality auto-delineations for HNC using multimodality PET/CT. The introduced structure-wise evaluation metrics provided valuable information on CNN model strengths and weaknesses for multi-structure auto-delineation.
To evaluate the patterns of loco-regional recurrences in head and neck cancer patients Twenty-six out of 112 patients treated with primary or postoperative 3D CRT or IMRT for their primary and recurrent disease between 2007 and 2013 were included. The CT images of recurrent disease were rigidly registered with the primary CT images for each patient. To assess overlaps and overlap localization, the recurrence volume overlapping with the primary target volume was identified. For relapses occurring in the regional lymph nodes, the epicenter distance in recurrences and primary volumes and dose in recurrences were also identified. The recurrences were defined as in-field, marginal or out-of-field. The majority of the failures occurred within 1 year after completed primary treatment. The dose differences in recurrence volume were not statistically significant when patients were treated with IMRT or 3D CRT. Recurrence in 15/26 of the included patients occurred in the regional lymph nodes located fully or partly inside the primary target volume or the elective lymph node region. The majority of recurrences were recognized as in-field, independent of the primary treatment. Recurrence in the majority of the patients occurred in the regional lymph nodes located in high dose area. The cause of recurrence may be due to inadequate total dose in the primary treatment and/or lack of optimal primary diagnosis leading to inadequate primary target delineation.
Recurrences after radiochemotherapy for head and neck cancer (HNC) are often located within the region that received a high dose during the primary radiotherapy [1]. Moreover, there is an associati...