Adaptive radiotherapy for head and neck cancer

Castelli, J.; Simon, Antoine; Lafond, C.; Périchon, N.; Rigaud, B.; Chajon, É.; Bari, Berardino De; Özşahin, Mahmut; Bourhis, Jean; Crevoisier, R. de

doi:10.1080/0284186x.2018.1505053

Cited by 100 publications

(102 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Different studies have reported on anatomical and dosimetric changes in HNC in which the parotid gland as the most reviewed organ at risk [18]. In a review article of Castelli et al they stated that ART may decrease toxicity and improve local control for locally advanced HNC [19]. However, appropriate selection of patients in which the gain of ART outweighs the effort is challenging [19].…”

Section: Discussionmentioning

confidence: 99%

“…In a review article of Castelli et al they stated that ART may decrease toxicity and improve local control for locally advanced HNC [19]. However, appropriate selection of patients in which the gain of ART outweighs the effort is challenging [19]. More insight can be expected from ongoing clinical trials, such as the Artforce trial (ClinicalTrials.gov Identifier: NCT01504815) and the Admire trial (ClinicalTrials.gov Identifier: NCT03376386) or dose accumulation strategies to guide patient selection in order to reduce the amount of re-planning in HNC patients.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Protocolised way to cope with anatomical changes in head & neck cancer during the course of radiotherapy

Beek¹,

Jonker²,

Hamming‐Vrieze

et al. 2019

Technical Innovations & Patient Support in Radiation Oncolo

View full text Add to dashboard Cite

Introduction: During a course of radiotherapy for head-and-neck-cancer (HNC), non-rigid anatomical changes can be observed on daily Cone Beam CT (CBCT). To objectify responses to these changes, we use a decision support system (traffic light protocol). Action levels orange and red may lead to replanning. The purpose of this study was to evaluate how often re-planning was done for non-rigid anatomical changes, which anatomical changes led to re-planning and in which subgroups of patients treatment adaptation was deemed necessary. Materials and methods: A consecutive series of 388 HNC patients were retrospectively selected using the digital log of CBCT scans. The logs were analyzed for the number of new plans on an original planning CT scan (O-pCT) or a new pCT scan (N-pCT). Reasons for re-planning were categorized into: target volume increase/decrease, body contour decrease/increase and local shift of target volume. Subgroup analysis was performed to investigate relative differences of re-planning between treatment modalities. Results: For 33 patients the treatment plan was adapted due to anatomical changes, resulting in 37 new plans in total. Re-planning on a N-pCT with complete re-delineation was done 22 times. In fifteen cases a new plan was created after adjustment of contours on the O-pCT. Main reasons for re-planning were target volume increase, body contour decrease and local shifts of target volume. Most re-planning (23%) was seen in patients treated with chemoradiotherapy. Conclusion: Visual detection of anatomical changes on CBCT during treatment of HNC, results in replanning in 1 out of 10 patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Protocolised way to cope with anatomical changes in head & neck cancer during the course of radiotherapy

Beek¹,

Jonker²,

Hamming‐Vrieze

et al. 2019

Technical Innovations & Patient Support in Radiation Oncolo

View full text Add to dashboard Cite

show abstract

“…The process not only is tedious but also suffers from substantial intra‐ and interobserver variabilities . The time‐consuming process is further challenged by the need to adapt H&N treatment plans due to the interfractional changes commonly occur to these patients . The anatomical changes can be observed in daily cone beam CT (CBCT) images for patient positioning, but better quality fan beam simulation CTs are commonly acquired to more accurately assess the anatomical changes, delineate the OARs, and perform dose calculation in off‐line adaptive radiotherapy planning.…”

Section: Introductionmentioning

confidence: 99%

“…3 The time-consuming process is further challenged by the need to adapt H&N treatment plans due to the interfractional changes commonly occur to these patients. 4 The anatomical changes can be observed in daily cone beam CT (CBCT) images for patient positioning, but better quality fan beam simulation CTs are commonly acquired to more accurately assess the anatomical changes, delineate the OARs, and perform dose calculation in off-line adaptive radiotherapy planning. Recent advances in MRguided radiotherapy (MRgRT) provide H&N images with superior soft tissue contrast on the daily basis, 5 further paving the path to online adaptive radiotherapy, where automated segmentation of the OARs is more urgently needed.…”

Section: Introductionmentioning

confidence: 99%

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

et al. 2019

View full text Add to dashboard Cite

Purpose Image‐guided radiotherapy provides images not only for patient positioning but also for online adaptive radiotherapy. Accurate delineation of organs‐at‐risk (OARs) on Head and Neck (H&N) CT and MR images is valuable to both initial treatment planning and adaptive planning, but manual contouring is laborious and inconsistent. A novel method based on the generative adversarial network (GAN) with shape constraint (SC‐GAN) is developed for fully automated H&N OARs segmentation on CT and low‐field MRI. Methods and material A deep supervised fully convolutional DenseNet is employed as the segmentation network for voxel‐wise prediction. A convolutional neural network (CNN)‐based discriminator network is then utilized to correct predicted errors and image‐level inconsistency between the prediction and ground truth. An additional shape representation loss between the prediction and ground truth in the latent shape space is integrated into the segmentation and adversarial loss functions to reduce false positivity and constrain the predicted shapes. The proposed segmentation method was first benchmarked on a public H&N CT database including 32 patients, and then on 25 0.35T MR images obtained from an MR‐guided radiotherapy system. The OARs include brainstem, optical chiasm, larynx (MR only), mandible, pharynx (MR only), parotid glands (both left and right), optical nerves (both left and right), and submandibular glands (both left and right, CT only). The performance of the proposed SC‐GAN was compared with GAN alone and GAN with the shape constraint (SC) but without the DenseNet (SC‐GAN‐ResNet) to quantify the contributions of shape constraint and DenseNet in the deep neural network segmentation. Results The proposed SC‐GAN slightly but consistently improve the segmentation accuracy on the benchmark H&N CT images compared with our previous deep segmentation network, which outperformed other published methods on the same or similar CT H&N dataset. On the low‐field MR dataset, the following average Dice's indices were obtained using improved SC‐GAN: 0.916 (brainstem), 0.589 (optical chiasm), 0.816 (mandible), 0.703 (optical nerves), 0.799 (larynx), 0.706 (pharynx), and 0.845 (parotid glands). The average surface distances ranged from 0.68 mm (brainstem) to 1.70 mm (larynx). The 95% surface distance ranged from 1.48 mm (left optical nerve) to 3.92 mm (larynx). Compared with CT, using 95% surface distance evaluation, the automated segmentation accuracy is higher on MR for the brainstem, optical chiasm, optical nerves and parotids, and lower for the mandible. The SC‐GAN performance is superior to SC‐GAN‐ResNet, which is more accurate than GAN alone on both the CT and MR datasets. The segmentation time for one patient is 14 seconds using a single GPU. Conclusion The performance of our previous shape constrained fully CNNs for H&N segmentation is further improved by incorporating GAN and DenseNet. With the novel segmentation method, we showed that the low‐field MR images acquired on a MR‐guided radiation radiotherapy syste...

show abstract

“…Which patients would benefit from ART in head and neck cancer? What is the optimal timing? Should it be performed every five fractions, within the first 10 fractions? There are no randomized studies that show clinical benefit. How should treatment be altered when changes are detected?…”

Section: Opening Statementsmentioning

confidence: 99%

Three discipline collaborative radiation therapy special debate: All head and neck cancer patients with intact tumors/nodes should have scheduled adaptive replanning performed at least once during the course of radiotherapy

Soisson

Guerrieri

Balasubramanian

et al. 2019

J Applied Clin Med Phys

View full text Add to dashboard Cite

Adaptive radiotherapy for head and neck cancer

Cited by 100 publications

References 76 publications

Protocolised way to cope with anatomical changes in head & neck cancer during the course of radiotherapy

Protocolised way to cope with anatomical changes in head & neck cancer during the course of radiotherapy

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

Three discipline collaborative radiation therapy special debate: All head and neck cancer patients with intact tumors/nodes should have scheduled adaptive replanning performed at least once during the course of radiotherapy

Contact Info

Product

Resources

About