4π Noncoplanar Stereotactic Body Radiation Therapy for Head-and-Neck Cancer: Potential to Improve Tumor Control and Late Toxicity

Rwigema, J.C.; Nguyen, Dan; Heron, Dwight E.; Chen, Allen M.; Lee, Percy; Wang, Pin-Chieh; Vargo, John A.; Low, Daniel A.; Huq, M. Saiful; Tenn, Stephen; Steinberg, Michael L.; Kupelian, Patrick A.; Sheng, Ke

doi:10.1016/j.ijrobp.2014.09.043

Cited by 67 publications

(80 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Collisions between the treatment hardware and the patient continue to present a challenge concerning patient safety and equipment damage in radiotherapy. Additionally, the lack of reliable collision avoidance is a critical barrier to the delivery of advanced trajectory treatments in the future . While accurate collision detection and avoidance in radiotherapy has been investigated in different forms over the last few decades, a solid clinical implementation has not been widely adopted across the community.…”

Section: Introductionmentioning

confidence: 99%

A priori patient-specific collision avoidance in radiotherapy using consumer grade depth cameras

2017

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A priori patient-specific collision avoidance in radiotherapy using consumer grade depth cameras

2017

View full text Add to dashboard Cite

show abstract

“…The DNN learns its behavior from the full implementation of one iteration of CG, the CP‐DL‐ST processes; therefore, the DNN also tries to predict the best beam orientation that can be added to the current state of the problem. Note that as a greedy algorithm, CG does not guarantee global optimality, but it has been shown to produce superior results for treatment planning problems in existing literature …”

Section: Discussionmentioning

confidence: 99%

“…Although it is not fully clear what the acceptable error margins are for clinical acceptance. CG already outperforms manually beam selected plans . Also, for these to be used in the clinic, the dosimetrist will be going through many trial‐and‐error iterations to obtain an acceptable plan.…”

Section: Discussionmentioning

confidence: 99%

“…The optimization algorithm used to find the optimal set of beams to train the model is a greedy iterative algorithm known as column generation (CG). Column generation algorithms such as the one in this study have demonstrated success in finding the best treatment plan . The proposed CG method starts with an empty set of beams, and in each iteration, CG selects one beam with the highest potential to improve the current solution and adds it to the set, and the respective FMO is solved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity‐modulated radiation therapy

et al. 2020

Self Cite

View full text Add to dashboard Cite

Purpose Beam orientation selection, whether manual or protocol‐based, is the current clinical standard in radiation therapy treatment planning, but it is tedious and can yield suboptimal results. Many algorithms have been designed to optimize beam orientation selection because of its impact on treatment plan quality, but these algorithms suffer from slow calculation of the dose influence matrices of all candidate beams. We propose a fast beam orientation selection method, based on deep learning neural networks (DNN), capable of developing a plan comparable to those developed by the state‐of‐the‐art column generation (CG) method. Our model's novelty lies in its supervised learning structure (using CG to teach the network), DNN architecture, and ability to learn from anatomical features to predict dosimetrically suitable beam orientations without using dosimetric information from the candidate beams. This may save hours of computation. Methods A supervised DNN is trained to mimic the CG algorithm, which iteratively chooses beam orientations one‐by‐one by calculating beam fitness values based on Karush‐Kush‐Tucker optimality conditions at each iteration. The DNN learns to predict these values. The dataset contains 70 prostate cancer patients — 50 training, 7 validation, and 13 test patients — to develop and test the model. Each patient’s data contains 6 contours: PTV, body, bladder, rectum, and left and right femoral heads. Column generation was implemented with a GPU‐based Chambolle‐Pock algorithm, a first‐order primal‐dual proximal‐class algorithm, to create 6270 plans. The DNN trained over 400 epochs, each with 2500 steps and a batch size of 1, using the Adam optimizer at a learning rate of 1 × 10−5 and a sixfold cross‐validation technique. Results The average and standard deviation of training, validation, and testing loss functions among the six folds were 0.62 ± 0.09%, 1.04 ± 0.06%, and 1.44 ± 0.11%, respectively. Using CG and supervised DNN, we generated two sets of plans for each scenario in the test set. The proposed method took at most 1.5 s to select a set of five beam orientations and 300 s to calculate the dose influence matrices for 5 beams and finally 20 s to solve the fluence map optimization (FMO). However, CG needed around 15 h to calculate the dose influence matrices of all beams and at least 400 s to solve both the beam orientation selection and FMO problems. The differences in the dose coverage of PTV between plans generated by CG and by DNN were 0.2%. The average dose differences received by organs at risk were between 1 and 6 percent: Bladder had the smallest average difference in dose received (0.956 ± 1.184%), then Rectum (2.44 ± 2.11%), Left Femoral Head (6.03 ± 5.86%), and Right Femoral Head (5.885 ± 5.515%). The dose received by Body had an average difference of 0.10 ± 0.1% between the generated treatment plans. Conclusions We developed a fast beam orientation selection method based on a DNN that selects beam orientations in seconds and is therefore suitable for clinical routines. In the ...

show abstract

“…The original investigations published provided evidence of benefit and proof of principle for smaller tumors. A study involving the 4 π approach to SF‐IMRT for HNC was also attempted but it was for small and recurrent cancers 16. The question of applicability of 4 π techniques to truly large target volumes and its feasibility for conventional IMRT/VMAT treatments remains unaddressed for HNC.…”

Section: Introductionmentioning

confidence: 99%

Multi‐isocentric 4π volumetric‐modulated arc therapy approach for head and neck cancer

Subramanian

Subramani

Chilukuri

et al. 2017

J Applied Clin Med Phys

View full text Add to dashboard Cite

ObjectivesTo explore the feasibility of multi‐isocentric 4π volumetric‐modulated arc therapy (MI4π‐VMAT) for the complex targets of head and neck cancers.MethodsTwenty‐five previously treated patients of HNC underwent re‐planning to improve the dose distributions with either coplanar VMAT technique (CP‐VMAT) or noncoplanar MI4π‐VMAT plans. The latter, involving 3–6 noncoplanar arcs and 2–3 isocenters were re‐optimized using the same priorities and objectives. Dosimetric comparison on standard metrics from dose‐volume histograms was performed to appraise relative merits of the two techniques. Pretreatment quality assurance was performed with IMRT phantoms to assess deliverability and accuracy of the MI4π‐VMAT plans. The gamma agreement index (GAI) analysis with criteria of 3 mm distance to agreement (DTA) and 3% dose difference (DD) was applied.Results CP‐VMAT and MI4π‐VMAT plans achieved the same degree of coverage for all target volumes related to near‐to‐minimum and near‐to‐maximum doses. MI4π‐VΜΑΤ plans resulted in an improved sparing of organs at risk. The average mean dose reduction to the parotids, larynx, oral cavity, and pharyngeal muscles were 3 Gy, 4 Gy, 5 Gy, and 4.3 Gy, respectively. The average maximum dose reduction to the brain stem, spinal cord, and oral cavity was 6.0 Gy, 3.8 Gy, and 2.4 Gy. Pretreatment QA results showed that plans can be reliably delivered with mean gamma agreement index of 97.0 ± 1.1%.Conclusions MI4π‐VMAT plans allowed to decrease the dose‐volume‐metrics for relevant OAR and results are reliable from a dosimetric standpoint. Early clinical experience has begun and future studies will report treatment outcome.

show abstract

4π Noncoplanar Stereotactic Body Radiation Therapy for Head-and-Neck Cancer: Potential to Improve Tumor Control and Late Toxicity

Cited by 67 publications

References 38 publications

A priori patient-specific collision avoidance in radiotherapy using consumer grade depth cameras

A priori patient-specific collision avoidance in radiotherapy using consumer grade depth cameras

A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity‐modulated radiation therapy

Multi‐isocentric 4π volumetric‐modulated arc therapy approach for head and neck cancer

Contact Info

Product

Resources

About