KLKe Lu

Ke Lu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ke Lu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Knowledge‐based deep residual U‐Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery

    by Xiwen Shu, Ke Lu, Jingtong Zhao, John Ginn, Yongbok Kim, Zhenyu Yang, Justus Adamson, Trey Mullikin, Chunhao Wang

    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 for training and 19 for testing. A Deep Residual U‐Net(DRU) was developed to generate sCT from patient‐specific high‐resolution T1 + Contrast MR volume, complemented by a healthy brain CT volume from the Visible Human Project that provides CT‐specific anatomical knowledge. To simulate treatment conditions, a template immobilization mask was deformed to align with the patient‐specific sCT anatomy, thereby creating a full sCT F volume. Four metrics, including PSNR, SSIM, RMSE, and MAE were derived to evaluate Hounsfield units(HU) accuracy of sCT compared to the ground‐truth CT without immobilization masks. Single isocenter multi‐target SRS plans developed with volumetric modulated arc therapy (VMAT) technique were recalculated within sCT F volumes to produce simulated dose distributions, which were compared with clinical plan dose distributions using the mean dose difference in the planning target volume(PTV) and gamma index evaluation. Results: In the test set, the generated sCT (statistics are reported as mean ± standard deviation) achieved a PSNR(Peak Signal‐to‐Noise Ratio) of 75 ± 4 dB, Structural Similarity Index (SSIM) of 0.99 ± 0.01, root mean square error (RMSE) of 11.9 ± 5.8 HU, and mean average error (MAE) of 1.4 ± 0.8 HU for brain tissues. When comparing sCT F dose calculation results against the original plans, gamma index passing rates were 95.8 ± 4.2% for the entire volume and 84.4 ± 15.0% within PTVs, using 3%/1 mm/15% threshold criteria. The median/ interquartile range of PTV dose differences were –2.0% and 2.3%, with all discrepancies below –5.0%. Conclusion: This study successfully demonstrated the generation and validation of sCT images from single‐modality MRI using a knowledge‐based deep model. The results confirm that single‐modality MRI without simulation CT scan effectively supports frameless SRS planning and integrates seamlessly into current clinical workflows.

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

    by Ke Lu, Lei Ren, Fang-Fang Yin

    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 substantial computation power, potentially exceeding the computation memory limit. Our previous work proposed a geometry-guided-deep-learning (GDL) technique for CBCT reconstruction that reduces model size and GPU memory consumption. This study further develops the technique and proposes a novel multi-beamlet deep learning (GMDL) technique of improved performance. The study compares the proposed technique with the FC layer-based deep learning (FCDL) method and the GDL technique through low-dose real-patient CT image reconstruction. Methods . Instead of using a large FC layer, the GMDL technique learns the projection-to-image domain transformation by constructing many small FC layers. In addition to connecting each pixel in the projection domain to beamlet points along the central beamlet in the image domain as GDL does, these smaller FC layers in GMDL connect each pixel to beamlets peripheral to the central beamlet based on the CT projection geometry. We compare ground truth images with low-dose images reconstructed with the GMDL, the FCDL, the GDL, and the conventional FBP methods. The images are quantitatively analyzed in terms of peak-signal-to-noise-ratio (PSNR), structural-similarity-index-measure (SSIM), and root-mean-square-error (RMSE). Results . Compared to other methods, the GMDL reconstructed low-dose CT images show improved image quality in terms of PSNR, SSIM, and RMSE. The optimal number of peripheral beamlets for the GMDL technique is two beamlets on each side of the central beamlet. The model size and memory consumption of the GMDL model is less than 1/100 of the FCDL model. Conclusion . Compared to the FCDL method, the GMDL technique is demonstrated to be able to reconstruct real patient low-dose CT images of improved image quality with significantly reduced model size and GPU memory requirement.


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

    by Zeyu Zhang, Mi Huang, Zhuoran Jiang, Yushi Chang, Ke Lu, Fang-Fang Yin, Phuoc Tran, Dapeng Wu, Chris Beltran, Lei Ren

    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 features. Previously we developed group-patient-trained deep learning methods to enhance the 4D-CBCT quality for radiomics analysis, which was not optimized for individual patients. In this study, a patient-specific model was developed to further improve the accuracy of 4D-CBCT based radiomics analysis for individual patients. Approach. This patient-specific model was trained with intra-patient data. Specifically, patient planning 4D-CT was augmented through image translation, rotation, and deformation to generate 305 CT volumes from 10 volumes to simulate possible patient positions during the onboard image acquisition. 72 projections were simulated from 4D-CT for each phase and were used to reconstruct 4D-CBCT using FDK back-projection algorithm. The patient-specific model was trained using these 305 paired sets of patient-specific 4D-CT and 4D-CBCT data to enhance the 4D-CBCT image to match with 4D-CT images as ground truth. For model testing, 4D-CBCT were simulated from a separate set of 4D-CT scan images acquired from the same patient and were then enhanced by this patient-specific model. Radiomics features were then extracted from the testing 4D-CT, 4D-CBCT, and enhanced 4D-CBCT image sets for comparison. The patient-specific model was tested using 4 lung-SBRT patients’ data and compared with the performance of the group-based model. The impact of model dimensionality, region of interest (ROI) selection, and loss function on the model accuracy was also investigated. Main results. Compared with a group-based model, the patient-specific training model further improved the accuracy of radiomic features, especially for features with large errors in the group-based model. For example, the 3D whole-body and ROI loss-based patient-specific model reduces the errors of the first-order median feature by 83.67%, the wavelet LLL feature maximum by 91.98%, and the wavelet HLL skewness feature by 15.0% on average for the four patients tested. In addition, the patient-specific models with different dimensionality (2D versus 3D) or loss functions (L1 versus L1 + VGG + GAN) achieved comparable results for improving the radiomics accuracy. Using whole-body or whole-body+ROI L1 loss for the model achieved better results than using the ROI L1 loss alone as the loss function. Significance. This study demonstrated that the patient-specific model is more effective than the group-based model on improving the accuracy of the 4D-CBCT radiomic features analysis, which could potentially improve the precision for outcome prediction in radiotherapy.


  • A geometry-guided deep learning technique for CBCT reconstruction

    by Ke Lu, Lei Ren, Fang-Fang Yin

    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 technique is developed to resolve the memory issue, and its feasibility is demonstrated for CBCT reconstruction from sparsely sampled projection data. Methods. The novel geometry-guided deep learning (GDL) technique is composed of a GDL reconstruction module and a post-processing module. The GDL reconstruction module learns and performs projection-to-image domain transformation by replacing the traditional single fully connected layer with an array of small fully connected layers in the network architecture based on the projection geometry. The DL post-processing module further improves image quality after reconstruction. We demonstrated the feasibility and advantage of the model by comparing ground truth CBCT with CBCT images reconstructed using (1) GDL reconstruction module only, (2) GDL reconstruction module with DL post-processing module, (3) Feldkamp, Davis, and Kress (FDK) only, (4) FDK with DL post-processing module, (5) ray-tracing only, and (6) ray-tracing with DL post-processing module. The differences are quantified by peak-signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and root-mean-square error (RMSE). Results. CBCT images reconstructed with GDL show improvements in quantitative scores of PSNR, SSIM, and RMSE. Reconstruction time per image for all reconstruction methods are comparable. Compared to current DL methods using large fully connected layers, the estimated memory requirement using GDL is four orders of magnitude less, making DL CBCT reconstruction feasible. Conclusion. With much lower memory requirement compared to other existing networks, the GDL technique is demonstrated to be the first DL technique that can rapidly and accurately reconstruct CBCT images from sparsely sampled data.