Dr. Deshan Yang Profile

Dr. Deshan Yang

Professor at Duke Univ School of Medicine

SPIE Involvement:

Author

Publications (4)

SPIE Journal Paper | 21 December 2022

Contour interpolation by deep learning approach

Chenxi Zhao, Ye Duan, Deshan Yang

JMI, Vol. 9, Issue 06, 064003, (December 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.6.064003

KEYWORDS: Interpolation, Deep learning, Education and training, Contour modeling, Lung, Stomach, Liver, Image segmentation, Data modeling, Kidney

Read Abstract +

PurposeContour interpolation is an important tool for expediting manual segmentation of anatomical structures. The process allows users to manually contour on discontinuous slices and then automatically fill in the gaps, therefore saving time and efforts. The most used conventional shape-based interpolation (SBI) algorithm, which operates on shape information, often performs suboptimally near the superior and inferior borders of organs and for the gastrointestinal structures. In this study, we present a generic deep learning solution to improve the robustness and accuracy for contour interpolation, especially for these historically difficult cases.ApproachA generic deep contour interpolation model was developed and trained using 16,796 publicly available cases from 5 different data libraries, covering 15 organs. The network inputs were a 128 × 128 × 5 image patch and the two-dimensional contour masks for the top and bottom slices of the patch. The outputs were the organ masks for the three middle slices. The performance was evaluated on both dice scores and distance-to-agreement (DTA) values.ResultsThe deep contour interpolation model achieved a dice score of 0.95 ± 0.05 and a mean DTA value of 1.09 ± 2.30 mm, averaged on 3167 testing cases of all 15 organs. In a comparison, the results by the conventional SBI method were 0.94 ± 0.08 and 1.50 ± 3.63 mm, respectively. For the difficult cases, the dice score and DTA value were 0.91 ± 0.09 and 1.68 ± 2.28 mm by the deep interpolator, compared with 0.86 ± 0.13 and 3.43 ± 5.89 mm by SBI. The t-test results confirmed that the performance improvements were statistically significant (p < 0.05) for all cases in dice scores and for small organs and difficult cases in DTA values. Ablation studies were also performed.ConclusionsA deep learning method was developed to enhance the process of contour interpolation. It could be useful for expediting the tasks of manual segmentation of organs and structures in the medical images.

SPIE Journal Paper | 1 September 2017

Adaptive anatomical preservation optimal denoising for radiation therapy daily MRI

Rapeepan Maitree, Gloria J. Perez-Carrillo, Joshua S. Shimony, H. Michael Gach, Anupama Chundury, Michael Roach, H. Harold Li, Deshan Yang

JMI, Vol. 4, Issue 03, 034004, (September 2017) https://doi.org/10.1117/12.10.1117/1.JMI.4.3.034004

KEYWORDS: Denoising, Tissues, Magnetic resonance imaging, Image filtering, Image quality, Edge detection, Wavelets, Digital filtering, Computed tomography, Radiotherapy

Read Abstract +

Proceedings Article | 3 March 2012 Paper

Onboard cone beam CT with flexible image trajectories to improve image quality and longitudinal coverage: simulation and phantom study

Deshan Yang, Jun Tan, Hua Li, Sreekrishna Goddu, Harold Li

Proceedings Volume 8313, 83132Q (2012) https://doi.org/10.1117/12.910851

KEYWORDS: Image quality, Reconstruction algorithms, Sensors, X-ray sources, MATLAB, X-ray computed tomography, Computer simulations, Image restoration, Image segmentation, Signal detection

Read Abstract +

Proceedings Article | 2 March 2007 Paper

Level set motion assisted non-rigid 3D image registration

Deshan Yang, Joseph Deasy, Daniel Low, Issam El Naqa

Proceedings Volume 6512, 651207 (2007) https://doi.org/10.1117/12.710024

KEYWORDS: Image registration, Image resolution, Motion models, Optical flow, Image processing, Motion estimation, 3D image processing, Medical imaging, Computed tomography, Medical imaging applications

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years