Ke Lu

Journal article J Appl Clin Med Phys · January 2026 PURPOSE: To develop a knowledge-based deep model for sCT generation from a single MR volume in LINAC-based frameless SRS, enabling the MR-only workflow without extra CT simulation. METHODS: A total of 139 patients were included in the study, with 120 used ... Full text Link to item Cite

PhysMorph: A biomechanical and image-guided deep learning framework for real-time multi-modal liver image registration.

Journal article Phys Imaging Radiat Oncol · January 2026 BACKGROUND AND PURPOSE: Accurate registration of pretreatment Magnetic Resonance Imaging (MRI) to onboard Cone Beam Computed Tomography (CBCT) is critical for liver Stereotactic Body Radiation Therapy (SBRT) but is challenged by poor CBCT soft-tissue contr ... Full text Link to item Cite

A Radiogenomic Deep Ensemble Learning Model for Identifying Radionecrosis Following Brain Metastases (BM) Stereotactic Radiosurgery in Patients With Non-small Cell Lung Cancer BM.

Journal article Adv Radiat Oncol · August 2025 PURPOSE: Stereotactic radiosurgery (SRS) is widely used for brain metastases (BM), but the risk of radionecrosis poses a challenge in post-SRS management. Given the lack of noninvasive imaging methods for distinguishing radionecrosis from recurrence, we ai ... Full text Link to item Cite

Deep residual network-based projection interpolation and post-processing techniques for thoracic patient CBCT reconstruction.

Journal article Med Phys · July 2025 BACKGROUND: Projection interpolation can be used to reduce streak artifacts caused by sparse sampling in cone-beam computed tomography (CBCT) image reconstruction. Conventional analytical interpolation methods create additional blur and artifacts at locati ... Full text Link to item Cite

Radiogenomic explainable AI with neural ordinary differential equation for identifying post‐SRS brain metastasis radionecrosis

Journal article Medical Physics · April 2025 AbstractBackgroundStereotactic radiosurgery (SRS) is widely used for managing brain metastases (BMs), but an adverse effect, radionecrosis, complicates post‐SRS management. Differentiating ... Full text Cite

Development of GUI-based simple independent dose calculation software without DICOM data transfer for high-dose-rate brachytherapy.

Journal article J Contemp Brachytherapy · December 2024 PURPOSE: Dose calculation in clinical treatment plans must be verified by an independent dose calculation prior to treatment. This study presented an independent second check dose calculation software developed for clinical use. MATERIAL AND METHODS: A sof ... Full text Link to item Cite

A dual-radiomics model for overall survival prediction in early-stage NSCLC patient using pre-treatment CT images.

Journal article Front Oncol · 2024 INTRODUCTION: Radiation therapy (RT) is one of the primary treatment options for early-stage non-small cell lung cancer (ES-NSCLC). Therefore, accurately predicting the overall survival (OS) rate following radiotherapy is crucial for implementing personali ... Full text Link to item Cite

Improving liver tumor image contrast and synthesizing novel tissue contrasts by adaptive multiparametric MRI fusion.

Journal article Precis Radiat Oncol · September 2022 PURPOSE: Multiparametric MRI contains rich and complementary anatomical and functional information, which is often utilized separately. This study aims to propose an adaptive multiparametric MRI (mpMRI) fusion method and examine its capability in improving ... Full text Link to item Cite

Patient-specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy.

Journal article Precis Radiat Oncol · June 2022 OBJECTIVE: Despite its prevalence, cone beam computed tomography (CBCT) has poor soft-tissue contrast, making it challenging to localize liver tumors. We propose a patient-specific deep learning model to generate synthetic magnetic resonance imaging (MRI) ... Full text Link to item Cite

A geometry-guided multi-beamlet deep learning technique for CT reconstruction.

Journal article Biomed Phys Eng Express · May 13, 2022 Purpose. Previous studies have proposed deep-learning techniques to reconstruct CT images from sinograms. However, these techniques employ large fully-connected (FC) layers for projection-to-image domain transformation, producing large models requiring sub ... Full text Link to item Cite

Patient-specific deep learning model to enhance 4D-CBCT image for radiomics analysis.

Journal article Phys Med Biol · April 1, 2022 Objective.4D-CBCT provides phase-resolved images valuable for radiomics analysis for outcome prediction throughout treatment courses. However, 4D-CBCT suffers from streak artifacts caused by under-sampling, which severely degrades the accuracy of radiomic ... Full text Link to item Cite

An AI-Enabled Virtual Hands-On Teaching Tool for Treatment Planning: A Pancreas SBRT Pilot Study.

Journal article International journal of radiation oncology, biology, physics · November 2021 Purpose/objective(s)To develop a tutoring program to help physician and physics residents to learn pancreas stereotactic body radiation therapy (SBRT) treatment planning via carefully collected cases and a series of specially designed knowledge mo ... Full text Cite

A geometry-guided deep learning technique for CBCT reconstruction.

Journal article Phys Med Biol · July 30, 2021 Purpose.Although deep learning (DL) technique has been successfully used for computed tomography (CT) reconstruction, its implementation on cone-beam CT (CBCT) reconstruction is extremely challenging due to memory limitations. In this study, a novel DL tec ... Full text Link to item Cite