Chunhao Wang

Overview:

  • Deep learning methods for automated radiotherapy treatment planning
  • Image-based radiotherapy outcome prediction and assessment
  • 4D imaging methods for motion management



Positions:

Assistant Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

Ph.D. 2016

Duke University

Medical Physics Resident, Radiation Oncology Physics Division

Duke University

Medical Physics Resident, Radiation Oncology Physics Division

Duke University

Grants:

Publications:

Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application

Authors
Wang, C; Liu, C; Chang, Y; Lafata, K; Cui, Y; Zhang, J; Sheng, Y; Mowery, Y; Brizel, D; Yin, F-F
MLA Citation
Wang, Chunhao, et al. “Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application.” Frontiers in Oncology, vol. 10, Frontiers Media SA. Crossref, doi:10.3389/fonc.2020.01592.
URI
https://scholars.duke.edu/individual/pub1454969
Source
crossref
Published In
Frontiers in Oncology
Volume
10
DOI
10.3389/fonc.2020.01592

Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future.

Treatment planning is an essential step of the radiotherapy workflow. It has become more sophisticated over the past couple of decades with the help of computer science, enabling planners to design highly complex radiotherapy plans to minimize the normal tissue damage while persevering sufficient tumor control. As a result, treatment planning has become more labor intensive, requiring hours or even days of planner effort to optimize an individual patient case in a trial-and-error fashion. More recently, artificial intelligence has been utilized to automate and improve various aspects of medical science. For radiotherapy treatment planning, many algorithms have been developed to better support planners. These algorithms focus on automating the planning process and/or optimizing dosimetric trade-offs, and they have already made great impact on improving treatment planning efficiency and plan quality consistency. In this review, the smart planning tools in current clinical use are summarized in 3 main categories: automated rule implementation and reasoning, modeling of prior knowledge in clinical practice, and multicriteria optimization. Novel artificial intelligence-based treatment planning applications, such as deep learning-based algorithms and emerging research directions, are also reviewed. Finally, the challenges of artificial intelligence-based treatment planning are discussed for future works.
Authors
Wang, C; Zhu, X; Hong, JC; Zheng, D
MLA Citation
Wang, Chunhao, et al. “Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future.Technol Cancer Res Treat, vol. 18, Jan. 2019, p. 1533033819873922. Pubmed, doi:10.1177/1533033819873922.
URI
https://scholars.duke.edu/individual/pub1409964
PMID
31495281
Source
pubmed
Published In
Technology in Cancer Research & Treatment
Volume
18
Published Date
Start Page
1533033819873922
DOI
10.1177/1533033819873922

Radiotherapy Treatment Planning in the Age of AI: Are We Ready Yet?

Authors
Zheng, D; Hong, JC; Wang, C; Zhu, X
MLA Citation
Zheng, Dandan, et al. “Radiotherapy Treatment Planning in the Age of AI: Are We Ready Yet?Technol Cancer Res Treat, vol. 18, Jan. 2019, p. 1533033819894577. Pubmed, doi:10.1177/1533033819894577.
URI
https://scholars.duke.edu/individual/pub1425200
PMID
31858890
Source
pubmed
Published In
Technology in Cancer Research & Treatment
Volume
18
Published Date
Start Page
1533033819894577
DOI
10.1177/1533033819894577

Spine SBRT With Halcyon™: Plan Quality, Modulation Complexity, Delivery Accuracy, and Speed.

Purpose: Spine SBRT requires treatment plans with steep dose gradients and tight limits to the cord maximal dose. A new dual-layer staggered 1-cm MLC in Halcyon™ treatment platform has improved leakage, speed, and DLG compared to 120-Millennium (0.5-cm) and High-Definition (0.25-cm) MLCs in the TrueBeam platform. Halcyon™ 2.0 with SX2 MLC modulates fluence with the upper and lower MLCs, while in Halcyon™ 1.0 with SX1 only the lower MLC modulates the fluence and the upper MLC functions as a back-up jaw. We investigated the effects of four MLC designs on plan quality for spine SBRT treatments. Methods: 15 patients previously treated at our institution were re-planned according to the NRG-BR-002 guidelines with a prescription of 3,000 cGy in 3 fractions, 6xFFF, 800 MU/min, and 3-arc VMAT technique. Planning objectives were adjusted manually by an experienced planner to generate optimal plans and kept the same for different MLCs within the same platform. Results: All treatment plans were able to achieve adequate target coverage while meeting NRG-BR002 dosimetric constraints. Planning parameters were evaluated including: conformity index, homogeneity index, gradient measure, and global point dose maximum. Delivery accuracy, modulation complexity, and delivery time were also analyzed for all MLCs. Conclusion: The Halcyon™ dual-layer MLC can generate comparable and clinically equivalent spine SBRT plans to TrueBeam plans with less rapid dose fall-off and lower conformity. MLC width leaf can impact maximum dose to organs at risk and plan quality, but does not cause limitations in achieving acceptable plans for spine SBRT treatments.
Authors
Petroccia, HM; Malajovich, I; Barsky, AR; Ghiam, AF; Jones, J; Wang, C; Zou, W; Teo, B-KK; Dong, L; Metz, JM; Li, T
MLA Citation
Petroccia, Heather M., et al. “Spine SBRT With Halcyon™: Plan Quality, Modulation Complexity, Delivery Accuracy, and Speed.Front Oncol, vol. 9, 2019, p. 319. Pubmed, doi:10.3389/fonc.2019.00319.
URI
https://scholars.duke.edu/individual/pub1386051
PMID
31106151
Source
pubmed
Published In
Frontiers in Oncology
Volume
9
Published Date
Start Page
319
DOI
10.3389/fonc.2019.00319

Knowledge-Based Tradeoff Hyperplanes for Head and Neck Treatment Planning.

PURPOSE: To develop a tradeoff hyperplane model to facilitate tradeoff decision-making before inverse planning. METHODS AND MATERIALS: We propose a model-based approach to determine the tradeoff hyperplanes that allow physicians to navigate the clinically viable space of plans with best achievable dose-volume parameters before planning. For a given case, a case reference set (CRS) is selected using a novel anatomic similarity metric from a large reference plan pool. Then, a regression model is built on the CRS to estimate the expected dose-volume histograms (DVHs) for the current case. This model also predicts the DVHs for all CRS cases and captures the variation from the corresponding DVHs in the clinical plans. Finally, these DVH variations are analyzed using the principal component analysis to determine the tradeoff hyperplane for the current case. To evaluate the effectiveness of the proposed approach, 244 head and neck cases were randomly partitioned into reference (214) and validation (30) sets. A tradeoff hyperplane was built for each validation case and evenly sampled for 12 tradeoff predictions. Each prediction yielded a tradeoff plan. The root-mean-square errors of the predicted and the realized plan DVHs were computed for prediction achievability evaluation. RESULTS: The tradeoff hyperplane with 3 principal directions accounts for 57.8% ± 3.6% of variations in the validation cases, suggesting the hyperplanes capture a significant portion of the clinical tradeoff space. The average root-mean-square errors in 3 tradeoff directions are 5.23 ± 2.46, 5.20 ± 2.52, and 5.19 ± 2.49, compared with 4.96 ± 2.48 of the knowledge-based planning predictions, indicating that the tradeoff predictions are comparably achievable. CONCLUSIONS: Clinically relevant tradeoffs can be effectively extracted from existing plans and characterized by a tradeoff hyperplane model. The hyperplane allows physicians and planners to explore the best clinically achievable plans with different organ-at-risk sparing goals before inverse planning and is a natural extension of the current knowledge-based planning framework.
Authors
MLA Citation
Zhang, Jiahan, et al. “Knowledge-Based Tradeoff Hyperplanes for Head and Neck Treatment Planning.Int J Radiat Oncol Biol Phys, vol. 106, no. 5, Apr. 2020, pp. 1095–103. Pubmed, doi:10.1016/j.ijrobp.2019.12.034.
URI
https://scholars.duke.edu/individual/pub1428932
PMID
31982497
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
106
Published Date
Start Page
1095
End Page
1103
DOI
10.1016/j.ijrobp.2019.12.034