Deep learning has achieved great success in many medical imaging tasks without explicit solutions. In this work, learning method was applied to dual-energy cone-beam CT imaging. We proposed a Residual W-shape Network (ResWnet). ResWnet consists of three modules: scatter correction module 𝒮, material decomposition module ℳ, decomposition denoising module 𝒟 . Both 𝒮 and 𝒟 use ResWnet architecture, and this lightweight model fuses multi-level features, achieving satisfied performance with a small number of parameters. 𝒮 acts on dual-energy attenuation projections to reduce the scatter contaminations, and 𝒟 acts on material composition projections to suppress the noise. ℳ links the modules 𝒮 and 𝒟, and is used for domain transform from attenuation projections to material projections. This process could be approximated by polynomials with pre-calibrated parameters, that is, ℳ is a known operator in proposed network with no trainable parameters. This helps to reduce model parameters and improve the performance with small training dataset. Using public head CT dataset, we simulated dual-energy cone-beam CT projections and material projections. Proposed ResWnet was trained, validated and tested on this simulated dataset, verifying its effectiveness in projection-domain scatter correction and low-noise decomposition.
Cone-beam CT (CBCT) based cervical brachytherapy (CBCT-BT) is promising to simplify treatment workflow and improve the accuracy of dose delivery. However, severe artifacts in CBCT and its impact on dose calculation should be carefully investigated. In this work, we developed a novel female pelvis phantom dedicated to the cervical brachytherapy, which could be used to evaluate the CBCT-BT performance on imaging accuracy and dose calculation. The phantom dimension and organ position were determined based on Asian female patients. The phantom mainly simulates four parts: adipose, bone, muscle, organs. The first three parts are fixed, and peanut oil, PMMA, POM and PTFE are used to mimic adipose, muscle, cortical bone and cancellous bone respectively. In the muscle, there are four cavities for the insertion of 3D-printed deformable and moveable organs, i.e., vagina and uterus, bladder, intestine, rectum. The vagina and uterus were connected, with a 2 mm diameter elastic channel in it to enable applicator movement. To evaluate the CBCT-BT performance, a standard planning CT (pCT) scan and a CBCT scan were conducted on this phantom, scatter removal algorithm using pCT prior was implemented on the CBCT images. The HU error of muscle, adipose, and organs-at-risk (OARs) in corrected CBCT images were less than 15 HU. Referred to pCT-based plan as baseline, the CBCT-based plan achieved a γ pass rate of >97%. In conclusion, this created phantom successfully simulate both the anatomy structure and the HU numbers of female pelvis, thus provides an effective tool for CBCT-BT evaluation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.