Browsing by Author "Wu, Q Jackie"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item Open Access An Ensemble Approach to Knowledge-Based Intensity-Modulated Radiation Therapy Planning.(Frontiers in oncology, 2018-01) Zhang, Jiahan; Wu, Q Jackie; Xie, Tianyi; Sheng, Yang; Yin, Fang-Fang; Ge, YaorongKnowledge-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.Item Open Access Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models.(Frontiers in Oncology, 2019-01) Sheng, Yang; Li, Taoran; Yoo, Sua; Yin, Fang-Fang; Blitzblau, Rachel; Horton, Janet K; Ge, Yaorong; Wu, Q JackiePurpose: To develop an automatic treatment planning system for whole breast radiation therapy (WBRT) based on two intensity-modulated tangential fields, enabling near-real-time planning. Methods and Materials: A total of 40 WBRT plans from a single institution were included in this study under IRB approval. Twenty WBRT plans, 10 with single energy (SE, 6MV) and 10 with mixed energy (ME, 6/15MV), were randomly selected as training dataset to develop the methodology for automatic planning. The rest 10 SE cases and 10 ME cases served as validation. The auto-planning process consists of three steps. First, an energy prediction model was developed to automate energy selection. This model establishes an anatomy-energy relationship based on principle component analysis (PCA) of the gray level histograms from training cases' digitally reconstructed radiographs (DRRs). Second, a random forest (RF) model generates an initial fluence map using the selected energies. Third, the balance of overall dose contribution throughout the breast tissue is realized by automatically selecting anchor points and applying centrality correction. The proposed method was tested on the validation dataset. Non-parametric equivalence test was performed for plan quality metrics using one-sided Wilcoxon Signed-Rank test. Results: For validation, the auto-planning system suggested same energy choices as clinical-plans in 19 out of 20 cases. The mean (standard deviation, SD) of percent target volume covered by 100% prescription dose was 82.5% (4.2%) for auto-plans, and 79.3% (4.8%) for clinical-plans (p > 0.999). Mean (SD) volume receiving 105% Rx were 95.2 cc (90.7 cc) for auto-plans and 83.9 cc (87.2 cc) for clinical-plans (p = 0.108). Optimization time for auto-plan was <20 s while clinical manual planning takes between 30 min and 4 h. Conclusions: We developed an automatic treatment planning system that generates WBRT plans with optimal energy selection, clinically comparable plan quality, and significant reduction in planning time, allowing for near-real-time planning.Item Open Access Clinical Experience With Machine Learning-Based Automated Treatment Planning for Whole Breast Radiation Therapy.(Advances in radiation oncology, 2021-03) Yoo, Sua; Sheng, Yang; Blitzblau, Rachel; McDuff, Susan; Champ, Colin; Morrison, Jay; O'Neill, Leigh; Catalano, Suzanne; Yin, Fang-Fang; Wu, Q JackiePurpose
The machine learning-based automated treatment planning (MLAP) tool has been developed and evaluated for breast radiation therapy planning at our institution. We implemented MLAP for patient treatment and assessed our clinical experience for its performance.Methods and materials
A total of 102 patients of breast or chest wall treatment plans were prospectively evaluated with institutional review board approval. A human planner executed MLAP to create an auto-plan via automation of fluence maps generation. If judged necessary, a planner further fine-tuned the fluence maps to reach a final plan. Planners recorded the time required for auto-planning and manual modification. Target (ie, breast or chest wall and nodes) coverage and dose homogeneity were compared between the auto-plan and final plan.Results
Cases without nodes (n = 71) showed negligible (<1%) differences for target coverage and dose homogeneity between the auto-plan and final plan. Cases with nodes (n = 31) also showed negligible difference for target coverage. However, mean ± standard deviation of volume receiving 105% of the prescribed dose and maximum dose were reduced from 43.0% ± 26.3% to 39.4% ± 23.7% and 119.7% ± 9.5% to 114.4% ± 8.8% from auto-plan to final plan, respectively, all with P ≤ .01 for cases with nodes (n = 31). Mean ± standard deviation time spent for auto-plans and additional fluence modification for final plans were 12.1 ± 9.3 and 13.1 ± 12.9 minutes, respectively, for cases without nodes, and 16.4 ± 9.7 and 26.4 ± 16.4 minutes, respectively, for cases with nodes.Conclusions
The MLAP tool has been successfully implemented for routine clinical practice and has significantly improved planning efficiency. Clinical experience indicates that auto-plans are sufficient for target coverage, but improvement is warranted to reduce high dose volume for cases with nodal irradiation. This study demonstrates the clinical implementation of auto-planning for patient treatment and the significant importance of integrating human experience and feedback to improve MLAP for better clinical translation.Item Embargo Deep-Learning-Based Auto-Segmentation for Cone Beam Computed Tomography (CBCT) in Cervical Cancer Radiation Therapy(2024) Wu, YuduoBackground: Cervical cancer is a common gynecological malignancy among women worldwide. Among the primary modalities for treating cervical cancer, radiation therapy occupies a central role. Using Cone-Beam Computed Tomography (CBCT) scans obtained prior to treatment for target registration and alignment holds critical significance for precision radiation therapy. Accurately contouring targets and critical-organs-at risk (OARs) is the most time-consuming task for radiation oncologists. The OAR contouring in CBCT plays a crucial role in the radiotherapy of cervical cancer. Specifically, the location and volume of the rectum and bladder can significantly impact the precision of cervical cancer treatment, as the patients need to drink certain amount of water to fill the bladder prior to the treatment for target localization. The resulting change in position of rectum and bladder may lead to alterations in the target dose. Further, changes in radiation dose to these two OARs can directly affect the severity of the acute and late radiation induced damage. Therefore, the OAR contouring not only allows for better localization before each radiotherapy session, but also provides valuable reference for clinicians when they need to adjust the treatment plan.Purpose: The objective of this study is to evaluate the capabilities of four deep-learning models for contouring OARs in CBCT images of cervical cancer patients. Materials and Methods: The study dataset comprising 40 sets of CBCT images were collected from the Fujian Provincial Cancer Hospital in China. Two experienced radiation oncologists meticulously delineated 10 groups of OARs (Body, Bladder, Bone Marrow, Bowel Bag, Femoral Head L, Femoral Head R, Femoral Head and Neck L, Femoral Head and Neck R, Rectum, Spinal Canal) on the CBCT images as reference/ground truth. Subsequently, the 24 sets of CBCT reference were used to train the CBCT model, and the unedited CBCT images of the remaining 16 sets were used for comparing with their reference to test the four models. The only difference between these four models is the adoption of different neural network structures. They are classic U-Net, Flex U-Net, Attention U-Net (ATT), and SegResNet respectively. The evaluation of contouring quality for the four models was performed using the metrics such as 95 percentile Hausdorff Distance (HD95), Dice Similarity Coefficient (DICE), Average Symmetric Surface Distance (ASSD), Maximum Symmetric Surface Distance (MSSD), and Relative Absolute Volume Difference (RAVD), respectively. Results: The average DICE was 0.86 for bladder contouring among four models. The average DICE for rectum on CBCT image was 0.84 for four models. Conclusion: According to the quantitative analysis, classic U-Net neural network architecture with minor adjustments can obtain competitive segmentation on CBCT images.
Item Open Access Diode-based transmission detector for IMRT delivery monitoring: a validation study.(Journal of applied clinical medical physics, 2016-09-08) Li, Taoran; Wu, Q Jackie; Matzen, Thomas; Yin, Fang-Fang; O'Daniel, Jennifer CThe purpose of this work was to evaluate the potential of a new transmission detector for real-time quality assurance of dynamic-MLC-based radiotherapy. The accuracy of detecting dose variation and static/dynamic MLC position deviations was measured, as well as the impact of the device on the radiation field (surface dose, transmission). Measured dose variations agreed with the known variations within 0.3%. The measurement of static and dynamic MLC position deviations matched the known deviations with high accuracy (0.7-1.2 mm). The absorption of the device was minimal (~ 1%). The increased surface dose was small (1%-9%) but, when added to existing collimator scatter effects could become significant at large field sizes (≥ 30 × 30 cm2). Overall the accuracy and speed of the device show good potential for real-time quality assurance.Item Open Access Fluence Map Prediction Using Deep Learning Models - Direct Plan Generation for Pancreas Stereotactic Body Radiation Therapy.(Frontiers in artificial intelligence, 2020-01) Wang, Wentao; Sheng, Yang; Wang, Chunhao; Zhang, Jiahan; Li, Xinyi; Palta, Manisha; Czito, Brian; Willett, Christopher G; Wu, Qiuwen; Ge, Yaorong; Yin, Fang-Fang; Wu, Q JackiePurpose: Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a difficult and time-consuming task. In this study, we aim to develop a novel deep learning framework to generate clinical-quality plans by direct prediction of fluence maps from patient anatomy using convolutional neural networks (CNNs). Materials and Methods: Our proposed framework utilizes two CNNs to predict intensity-modulated radiation therapy fluence maps and generate deliverable plans: (1) Field-dose CNN predicts field-dose distributions in the region of interest using planning images and structure contours; (2) a fluence map CNN predicts the final fluence map per beam using the predicted field dose projected onto the beam's eye view. The predicted fluence maps were subsequently imported into the treatment planning system for leaf sequencing and final dose calculation (model-predicted plans). One hundred patients previously treated with pancreas SBRT were included in this retrospective study, and they were split into 85 training cases and 15 test cases. For each network, 10% of training data were randomly selected for model validation. Nine-beam benchmark plans with standardized target prescription and organ-at-risk constraints were planned by experienced clinical physicists and used as the gold standard to train the model. Model-predicted plans were compared with benchmark plans in terms of dosimetric endpoints, fluence map deliverability, and total monitor units. Results: The average time for fluence-map prediction per patient was 7.1 s. Comparing model-predicted plans with benchmark plans, target mean dose, maximum dose (0.1 cc), and D95% absolute differences in percentages of prescription were 0.1, 3.9, and 2.1%, respectively; organ-at-risk mean dose and maximum dose (0.1 cc) absolute differences were 0.2 and 4.4%, respectively. The predicted plans had fluence map gamma indices (97.69 ± 0.96% vs. 98.14 ± 0.74%) and total monitor units (2,122 ± 281 vs. 2,265 ± 373) that were comparable to the benchmark plans. Conclusions: We develop a novel deep learning framework for pancreas SBRT planning, which predicts a fluence map for each beam and can, therefore, bypass the lengthy inverse optimization process. The proposed framework could potentially change the paradigm of treatment planning by harnessing the power of deep learning to generate clinically deliverable plans in seconds.Item Open Access Goal-Driven Beam Setting Optimization for Whole-Breast Radiation Therapy.(Technology in cancer research & treatment, 2019-01) Wang, Wentao; Sheng, Yang; Yoo, Sua; Blitzblau, Rachel C; Yin, Fang-Fang; Wu, Q JackiePURPOSE:To develop an automated optimization program to generate optimal beam settings for whole-breast radiation therapy driven by clinically oriented goals. MATERIALS AND METHODS:Forty patients were retrospectively included in this study. Each patient's planning images, contoured structures of planning target volumes, organs-at-risk, and breast wires were used to optimize for patient-specific-beam settings. Two beam geometries were available tangential beams only and tangential plus supraclavicular beams. Beam parameters included isocenter position, gantry, collimator, couch angles, and multileaf collimator shape. A geometry-based goal function was defined to determine such beam parameters to minimize out-of-field target volume and in-field ipsilateral lung volume. For each geometry, the weighting in the goal function was trained with 10 plans and tested on 10 additional plans. For each query patient, the optimal beam setting was searched for different gantry-isocenter pairs. Optimal fluence maps were generated by an in-house automatic fluence optimization program for target coverage and homogeneous dose distribution, and dose calculation was performed in Eclipse. Automatically generated plans were compared with manually generated plans for target coverage and lung and heart sparing. RESULTS:The program successfully produced a set of beam parameters for every patient. Beam optimization time ranged from 10 to 120 s. The automatic plans had overall comparable plan quality to manually generated plans. For all testing cases, the mean target V95% was 91.0% for the automatic plans and 88.5% for manually generated plans. The mean ipsilateral lung V20Gy was lower for the automatic plans (15.2% vs 17.9%). The heart mean dose, maximum dose of the body, and conformity index were all comparable. CONCLUSION:We developed an automated goal-driven beam setting optimization program for whole-breast radiation therapy. It provides clinically relevant solutions based on previous clinical practice as well as patient specific anatomy on a substantially faster time frame.Item Open Access Impact of collimator leaf width and treatment technique on stereotactic radiosurgery and radiotherapy plans for intra- and extracranial lesions.(Radiation oncology (London, England), 2009-01-21) Wu, Q Jackie; Wang, Zhiheng; Kirkpatrick, John P; Chang, Zheng; Meyer, Jeffrey J; Lu, Mei; Huntzinger, Calvin; Yin, Fang-FangBACKGROUND: This study evaluated the dosimetric impact of various treatment techniques as well as collimator leaf width (2.5 vs 5 mm) for three groups of tumors -- spine tumors, brain tumors abutting the brainstem, and liver tumors. These lesions often present challenges in maximizing dose to target volumes without exceeding critical organ tolerance. Specifically, this study evaluated the dosimetric benefits of various techniques and collimator leaf sizes as a function of lesion size and shape. METHODS: Fifteen cases (5 for each site) were studied retrospectively. All lesions either abutted or were an integral part of critical structures (brainstem, liver or spinal cord). For brain and liver lesions, treatment plans using a 3D-conformal static technique (3D), dynamic conformal arcs (DARC) or intensity modulation (IMRT) were designed with a conventional linear accelerator with standard 5 mm leaf width multi-leaf collimator, and a linear accelerator dedicated for radiosurgery and hypofractionated therapy with a 2.5 mm leaf width collimator. For the concave spine lesions, intensity modulation was required to provide adequate conformality; hence, only IMRT plans were evaluated using either the standard or small leaf-width collimators.A total of 70 treatment plans were generated and each plan was individually optimized according to the technique employed. The Generalized Estimating Equation (GEE) was used to separate the impact of treatment technique from the MLC system on plan outcome, and t-tests were performed to evaluate statistical differences in target coverage and organ sparing between plans. RESULTS: The lesions ranged in size from 2.6 to 12.5 cc, 17.5 to 153 cc, and 20.9 to 87.7 cc for the brain, liver, and spine groups, respectively. As a group, brain lesions were smaller than spine and liver lesions. While brain and liver lesions were primarily ellipsoidal, spine lesions were more complex in shape, as they were all concave. Therefore, the brain and the liver groups were compared for volume effect, and the liver and spine groups were compared for shape. For the brain and liver groups, both the radiosurgery MLC and the IMRT technique contributed to the dose sparing of organs-at-risk(OARs), as dose in the high-dose regions of these OARs was reduced up to 15%, compared to the non-IMRT techniques employing a 5 mm leaf-width collimator. Also, the dose reduction contributed by the fine leaf-width MLC decreased, as dose savings at all levels diminished from 4 - 11% for the brain group to 1 - 5% for the liver group, as the target structures decreased in volume. The fine leaf-width collimator significantly improved spinal cord sparing, with dose reductions of 14 - 19% in high to middle dose regions, compared to the 5 mm leaf width collimator. CONCLUSION: The fine leaf-width MLC in combination with the IMRT technique can yield dosimetric benefits in radiosurgery and hypofractionated radiotherapy. Treatment of small lesions in cases involving complex target/OAR geometry will especially benefit from use of a fine leaf-width MLC and the use of IMRT.Item Open Access Incorporating Case-Based Reasoning for Radiation Therapy Knowledge Modeling: A Pelvic Case Study.(Technology in cancer research & treatment, 2019-01) Sheng, Yang; Zhang, Jiahan; Wang, Chunhao; Yin, Fang-Fang; Wu, Q Jackie; Ge, YaorongKnowledge models in radiotherapy capture the relation between patient anatomy and dosimetry to provide treatment planning guidance. When treatment schemes evolve, existing models struggle to predict accurately. We propose a case-based reasoning framework designed to handle novel anatomies that are of same type but vary beyond original training samples. A total of 105 pelvic intensity-modulated radiotherapy cases were analyzed. Eighty cases were prostate cases while the other 25 were prostate-plus-lymph-node cases. We simulated 4 scenarios: Scarce scenario, Semiscarce scenario, Semiample scenario, and Ample scenario. For the Scarce scenario, a multiple stepwise regression model was trained using 85 cases (80 prostate, 5 prostate-plus-lymph-node). The proposed workflow started with evaluating the feature novelty of new cases against 5 training prostate-plus-lymph-node cases using leverage statistic. The case database was composed of a 5-case dose atlas. Case-based dose prediction was compared against the regression model prediction using sum of squared residual. Mean sum of squared residual of case-based and regression predictions for the bladder of 13 identified outliers were 0.174 ± 0.166 and 0.459 ± 0.508, respectively (P = .0326). For the rectum, the respective mean sum of squared residuals were 0.103 ± 0.120 and 0.150 ± 0.171 for case-based and regression prediction (P = .1972). By retaining novel cases, under the Ample scenario, significant statistical improvement was observed over the Scarce scenario (P = .0398) for the bladder model. We expect that the incorporation of case-based reasoning that judiciously applies appropriate predictive models could improve overall prediction accuracy and robustness in clinical practice.Item Open Access Knowledge-Based Statistical Inference Method for Plan Quality Quantification.(Technology in cancer research & treatment, 2019-01) Zhang, Jiang; Wu, Q Jackie; Ge, Yaorong; Wang, Chunhao; Sheng, Yang; Palta, Jatinder; Salama, Joseph K; Yin, Fang-Fang; Zhang, JiahanAIM:The aim of the study is to develop a geometrically adaptive and statistically robust plan quality inference method. METHODS AND MATERIALS:We propose a knowledge-based plan quality inference method that references to similar plans in the historical database for patient-specific plan quality evaluation. First, a novel plan similarity metric with high-dimension geometrical difference quantification is utilized to retrieve similar plans. Subsequently, dosimetric statistical inferences are obtained from the selected similar plans. Two plan quality metrics-dosimetric result probability and dose deviation index-are proposed to quantify plan quality among prior similar plans. To evaluate the performance of the proposed method, we exported 927 clinically approved head and neck treatment plans. Eight organs at risk, including brain stem, cord, larynx, mandible, pharynx, oral cavity, left parotid and right parotid, were analyzed. Twelve suboptimal plans identified by dosimetric result probability were replanned to validate the capability of the proposed methods in identifying inferior plans. RESULTS:After replanning, left and right parotid median doses are reduced by 31.7% and 18.2%, respectively; 83% of these cases would not be identified as suboptimal without the proposed similarity plan selection. Analysis of population plan quality reveals that average parotid sparing has been improving significantly over time (21.7% dosimetric result probability reduction from year 2006-2007 to year 2016-2017). Notably, the increasing dose sparing over time in retrospective plan quality analysis is strongly correlated with the increasing dose prescription ratios to the 2 planning targets, revealing the collective trend in planning conventions. CONCLUSIONS:The proposed similar plan retrieval and analysis methodology has been proven to be predictive of the current plan quality. Therefore, the proposed workflow can potentially be applied in the clinics as a real-time plan quality assurance tool. The proposed metrics can also serve the purpose of plan quality analytics in finding connections and historical trends in the clinical treatment planning workflow.Item Open Access On-line adaptive radiation therapy: feasibility and clinical study.(Journal of oncology, 2010-01) Li, Taoran; Zhu, Xiaofeng; Thongphiew, Danthai; Lee, W Robert; Vujaskovic, Zeljko; Wu, Qiuwen; Yin, Fang-Fang; Wu, Q JackieThe purpose of this paper is to evaluate the feasibility and clinical dosimetric benefit of an on-line, that is, with the patient in the treatment position, Adaptive Radiation Therapy (ART) system for prostate cancer treatment based on daily cone-beam CT imaging and fast volumetric reoptimization of treatment plans. A fast intensity-modulated radiotherapy (IMRT) plan reoptimization algorithm is implemented and evaluated with clinical cases. The quality of these adapted plans is compared to the corresponding new plans generated by an experienced planner using a commercial treatment planning system and also evaluated by an in-house developed tool estimating achievable dose-volume histograms (DVHs) based on a database of existing treatment plans. In addition, a clinical implementation scheme for ART is designed and evaluated using clinical cases for its dosimetric qualities and efficiency.Item Open Access Quantitative comparison of automatic and manual IMRT optimization for prostate cancer: the benefits of DVH prediction.(Journal of applied clinical medical physics, 2015-03-08) Yang, Yun; Li, Taoran; Yuan, Lunlin; Ge, Yaorong; Yin, Fang-Fang; Lee, W Robert; Wu, Q JackieA recent publication indicated that the patient anatomical feature (PAF) model was capable of predicting optimal objectives based on past experience. In this study, the benefits of IMRT optimization using PAF-predicted objectives as guidance for prostate were evaluated. Three different optimization methods were compared.1) Expert Plan: Ten prostate cases (16 plans) were planned by an expert planner using conventional trial-and-error approach started with institutional modified OAR and PTV constraints. Optimization was stopped at 150 iterations and that plan was saved as Expert Plan. 2) Clinical Plan: The planner would keep working on the Expert Plan till he was satisfied with the dosimetric quality and the final plan was referred to as Clinical Plan. 3) PAF Plan: A third sets of plans for the same ten patients were generated fully automatically using predicted DVHs as guidance. The optimization was based on PAF-based predicted objectives, and was continued to 150 iterations without human interaction. DMAX and D98% for PTV, DMAX for femoral heads, DMAX, D10cc, D25%/D17%, and D40% for bladder/rectum were compared. Clinical Plans are further optimized with more iterations and adjustments, but in general provided limited dosimetric benefits over Expert Plans. PTV D98% agreed within 2.31% among Expert, Clinical, and PAF plans. Between Clinical and PAF Plans, differences for DMAX of PTV, bladder, and rectum were within 2.65%, 2.46%, and 2.20%, respectively. Bladder D10cc was higher for PAF but < 1.54% in general. Bladder D25% and D40% were lower for PAF, by up to 7.71% and 6.81%, respectively. Rectum D10cc, D17%, and D40% were 2.11%, 2.72%, and 0.27% lower for PAF, respectively. DMAX for femoral heads were comparable (< 35 Gy on average). Compared to Clinical Plan (Primary + Boost), the average optimization time for PAF plan was reduced by 5.2 min on average, with a maximum reduction of 7.1min. Total numbers of MUs per plan for PAF Plans were lower than Clinical Plans, indicating better delivery efficiency. The PAF-guided planning process is capable of generating clinical-quality prostate IMRT plans with no human intervention. Compared to manual optimization, this automatic optimization increases planning and delivery efficiency, while maintainingplan quality.