Show simple item record

An Ensemble Approach to Knowledge-Based Intensity-Modulated Radiation Therapy Planning.

dc.contributor.author Zhang, Jiahan
dc.contributor.author Wu, Q Jackie
dc.contributor.author Xie, Tianyi
dc.contributor.author Sheng, Yang
dc.contributor.author Yin, Fang-Fang
dc.contributor.author Ge, Yaorong
dc.date.accessioned 2019-10-01T14:18:27Z
dc.date.available 2019-10-01T14:18:27Z
dc.date.issued 2018-01
dc.identifier.issn 2234-943X
dc.identifier.issn 2234-943X
dc.identifier.uri https://hdl.handle.net/10161/19374
dc.description.abstract Knowledge-based planning (KBP) utilizes experienced planners' knowledge embedded in prior plans to estimate optimal achievable dose volume histogram (DVH) of new cases. In the regression-based KBP framework, previously planned patients' anatomical features and DVHs are extracted, and prior knowledge is summarized as the regression coefficients that transform features to organ-at-risk DVH predictions. In our study, we find that in different settings, different regression methods work better. To improve the robustness of KBP models, we propose an ensemble method that combines the strengths of various linear regression models, including stepwise, lasso, elastic net, and ridge regression. In the ensemble approach, we first obtain individual model prediction metadata using in-training-set leave-one-out cross validation. A constrained optimization is subsequently performed to decide individual model weights. The metadata is also used to filter out impactful training set outliers. We evaluate our method on a fresh set of retrospectively retrieved anonymized prostate intensity-modulated radiation therapy (IMRT) cases and head and neck IMRT cases. The proposed approach is more robust against small training set size, wrongly labeled cases, and dosimetric inferior plans, compared with other individual models. In summary, we believe the improved robustness makes the proposed method more suitable for clinical settings than individual models.
dc.language eng
dc.publisher Frontiers Media SA
dc.relation.ispartof Frontiers in oncology
dc.relation.isversionof 10.3389/fonc.2018.00057
dc.subject dose volume histogram prediction
dc.subject ensemble model
dc.subject machine learning
dc.subject regression model
dc.subject statistical modeling
dc.subject treatment planning
dc.title An Ensemble Approach to Knowledge-Based Intensity-Modulated Radiation Therapy Planning.
dc.type Journal article
duke.contributor.id Wu, Q Jackie|0378401
duke.contributor.id Yin, Fang-Fang|0334491
dc.date.updated 2019-10-01T14:18:25Z
pubs.begin-page 57
pubs.issue MAR
pubs.organisational-group School of Medicine
pubs.organisational-group Duke
pubs.organisational-group Duke Kunshan University Faculty
pubs.organisational-group Duke Kunshan University
pubs.organisational-group Duke Cancer Institute
pubs.organisational-group Institutes and Centers
pubs.organisational-group Radiation Oncology
pubs.organisational-group Clinical Science Departments
pubs.publication-status Published
pubs.volume 8
duke.contributor.orcid Yin, Fang-Fang|0000-0002-2025-4740


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record