Zheng Chang

Overview:

Dr. Chang's research interests include radiation therapy treatment assessment using MR quantitative imaging, image guided radiation therapy (IGRT), fast MR imaging using parallel imaging and strategic phase encoding, and motion management for IGRT.

Positions:

Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

Ph.D. 2006

University of British Columbia

Grants:

Publications:

An investigation of machine learning methods in delta-radiomics feature analysis.

PURPOSE: This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS: The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS: For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS: The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Authors
MLA Citation
Chang, Yushi, et al. “An investigation of machine learning methods in delta-radiomics feature analysis.Plos One, vol. 14, no. 12, 2019, p. e0226348. Pubmed, doi:10.1371/journal.pone.0226348.
URI
https://scholars.duke.edu/individual/pub1423241
PMID
31834910
Source
pubmed
Published In
Plos One
Volume
14
Published Date
Start Page
e0226348
DOI
10.1371/journal.pone.0226348

TH-EF-BRA-08: A Novel Technique for Estimating Volumetric Cine MRI (VC-MRI) From Multi-Slice Sparsely Sampled Cine Images Using Motion Modeling and Free Form Deformation.

PURPOSE: To develop a technique to estimate on-board VC-MRI using multi-slice sparsely-sampled cine images, patient prior 4D-MRI, motion-modeling and free-form deformation for real-time 3D target verification of lung radiotherapy. METHODS: A previous method has been developed to generate on-board VC-MRI by deforming prior MRI images based on a motion model(MM) extracted from prior 4D-MRI and a single-slice on-board 2D-cine image. In this study, free-form deformation(FD) was introduced to correct for errors in the MM when large anatomical changes exist. Multiple-slice sparsely-sampled on-board 2D-cine images located within the target are used to improve both the estimation accuracy and temporal resolution of VC-MRI. The on-board 2D-cine MRIs are acquired at 20-30frames/s by sampling only 10% of the k-space on Cartesian grid, with 85% of that taken at the central k-space. The method was evaluated using XCAT(computerized patient model) simulation of lung cancer patients with various anatomical and respirational changes from prior 4D-MRI to onboard volume. The accuracy was evaluated using Volume-Percent-Difference(VPD) and Center-of-Mass-Shift(COMS) of the estimated tumor volume. Effects of region-of-interest(ROI) selection, 2D-cine slice orientation, slice number and slice location on the estimation accuracy were evaluated. RESULTS: VCMRI estimated using 10 sparsely-sampled sagittal 2D-cine MRIs achieved VPD/COMS of 9.07±3.54%/0.45±0.53mm among all scenarios based on estimation with ROI_MM-ROI_FD. The FD optimization improved estimation significantly for scenarios with anatomical changes. Using ROI-FD achieved better estimation than global-FD. Changing the multi-slice orientation to axial, coronal, and axial/sagittal orthogonal reduced the accuracy of VCMRI to VPD/COMS of 19.47±15.74%/1.57±2.54mm, 20.70±9.97%/2.34±0.92mm, and 16.02±13.79%/0.60±0.82mm, respectively. Reducing the number of cines to 8 enhanced temporal resolution of VC-MRI by 25% while maintaining the estimation accuracy. Estimation using slices sampled uniformly through the tumor achieved better accuracy than slices sampled non-uniformly. CONCLUSIONS: Preliminary studies showed that it is feasible to generate VC-MRI from multi-slice sparsely-sampled 2D-cine images for real-time 3D-target verification. This work was supported by the National Institutes of Health under Grant No. R01-CA184173 and a research grant from Varian Medical Systems.
Authors
Harris, W; Yin, F; Wang, C; Chang, Z; Cai, J; Zhang, Y; Ren, L
MLA Citation
URI
https://scholars.duke.edu/individual/pub1168167
PMID
28048297
Source
pubmed
Published In
Med Phys
Volume
43
Published Date
Start Page
3898
End Page
3899
DOI
10.1118/1.4958265

SU-E-J-223: A BOLD Contrast Imaging Sequence to Evaluate Oxygenation Changes Due to Breath Holding for Breast Radiotherapy: A Pilot Study.

PURPOSE: To develop a robust MRI sequence to measure BOLD breath hold induced contrast in context of breast radiotherapy. METHODS: Two sequences were selected from prior studies as candidates to measure BOLD contrast attributable to breath holding within the breast: (1) T2* based Gradient Echo EPI (TR/TE = 500/41ms, flip angle = 60°), and (2) T2 based Single Shot Fast Spin Echo (SSFSE) (TR/TE = 3000/60ms). We enrolled ten women post-lumpectomy for breast cancer who were undergoing treatment planning for whole breast radiotherapy. Each session utilized a 1.5T GE MRI and 4 channel breast coil with the subject immobilized prone on a custom board. For each sequence, 1-3 planes of the lumpectomy breast were imaged continuously during a background measurement (1min) and intermittent breath holds (20-40s per breath hold, 3-5 holds per sequence). BOLD contrast was quantified as correlation of changes in per-pixel intensity with the breath hold schedule convolved with a hemodynamic response function. Subtle motion was corrected using a deformable registration algorithm. Correlation with breath-holding was considered significant if p<0.001. RESULTS: The percentage of the breast ROI with positive BOLD contrast measured by the two sequences were in agreement with a correlation coefficient of R=0.72 (p=0.02). While both sequences demonstrated areas with strong BOLD response, the response was more systematic throughout the breast for the SSFSE (T2) sequence (% breast with response in the same direction: 51.2%±0.7% for T2* vs. 68.1%±16% for T2). In addition, the T2 sequence was less prone to magnetic susceptibility artifacts, especially in presence of seroma, and provided a more robust image with little distortion or artifacts. CONCLUSION: A T2 SSFSE sequence shows promise for measuring BOLD contrast in the context of breast radiotherapy utilizing a breath hold technique. Further study in a larger patient cohort is warranted to better refine this novel technique.
Authors
MLA Citation
Adamson, J., et al. “SU-E-J-223: A BOLD Contrast Imaging Sequence to Evaluate Oxygenation Changes Due to Breath Holding for Breast Radiotherapy: A Pilot Study.Medical Physics, vol. 42, no. 6, June 2015, p. 3317. Epmc, doi:10.1118/1.4924309.
URI
https://scholars.duke.edu/individual/pub1075504
PMID
26127614
Source
epmc
Published In
Medical Physics
Volume
42
Published Date
Start Page
3317
DOI
10.1118/1.4924309

SU-E-J-182: A Feasibility Study Evaluating Automatic Identification of Gross Tumor Volume for Breast Cancer Radiotherapy Using Dynamic Contrast-Enhanced MR Imaging.

PURPOSE: To develop a computerized pharmacokinetic model-free Gross Tumor Volume (GTV) segmentation method based on dynamic contrastenhanced MRI (DCE-MRI) data that can improve physician GTV contouring efficiency. METHODS: 12 patients with biopsy-proven early stage breast cancer with post-contrast enhanced DCE-MRI images were analyzed in this study. A fuzzy c-means (FCM) clustering-based method was applied to segment 3D GTV from pre-operative DCE-MRI data. A region of interest (ROI) is selected by a clinician/physicist, and the normalized signal evolution curves were calculated by dividing the signal intensity enhancement value at each voxel by the pre-contrast signal intensity value at the corresponding voxel. Three semi-quantitative metrics were analyzed based on normalized signal evolution curves: initial Area Under signal evolution Curve (iAUC), Immediate Enhancement Ratio (IER), and Variance of Enhancement Slope (VES). The FCM algorithm wass applied to partition ROI voxels into GTV voxels and non-GTV voxels by using three analyzed metrics. The partition map for the smaller cluster is then generated and binarized with an automatically calculated threshold. To reduce spurious structures resulting from background, a labeling operation was performed to keep the largest three-dimensional connected component as the identified target. Basic morphological operations including hole-filling and spur removal were useutilized to improve the target smoothness. Each segmented GTV was compared to that drawn by experienced radiation oncologists. An agreement index was proposed to quantify the overlap between the GTVs identified using two approaches and a thershold value of 0.4 is regarded as acceptable. RESULTS: The GTVs identified by the proposed method were overlapped with the ones drawn by radiation oncologists in all cases, and in 10 out of 12 cases, the agreement indices were above the threshold of 0.4. CONCLUSION: The proposed automatic segmentation method was shown to be promising and might be used to improve physician contouring efficiency. J Horton receives grant from NIH and Varian Medical Systems; F-F Yin receives grant from Varian Medical Systems.
Authors
MLA Citation
URI
https://scholars.duke.edu/individual/pub1168189
PMID
28037170
Source
pubmed
Published In
Medical Physics
Volume
41
Published Date
Start Page
198
End Page
199
DOI
10.1118/1.4888235

Improving Tumor-to-Tissue CNR of 4D-MRI Using Deformable Image Registration.

Authors
MLA Citation
Cai, J., et al. “Improving Tumor-to-Tissue CNR of 4D-MRI Using Deformable Image Registration.Pract Radiat Oncol, vol. 3, no. 2 Suppl 1, Apr. 2013, pp. S8–9. Pubmed, doi:10.1016/j.prro.2013.01.027.
URI
https://scholars.duke.edu/individual/pub1025955
PMID
24674569
Source
pubmed
Published In
Pract Radiat Oncol
Volume
3
Published Date
Start Page
S8
End Page
S9
DOI
10.1016/j.prro.2013.01.027