A deep unsupervised learning framework for the 4D CBCT artifact correction

Adaptive scatter kernel deconvolution modeling for cone-beam CT scatter correction via deep reinforcement learning

BACKGROUND

Scattering photons can seriously contaminate cone-beam CT (CBCT) image quality with severe artifacts and substantial degradation of CT value accuracy, which is a major concern limiting the widespread application of CBCT in the medical field. The scatter kernel deconvolution (SKD) method commonly used in clinic requires a Monte Carlo (MC) simulation to determine numerous quality-related kernel parameters, and it cannot realize intelligent scatter kernel parameter optimization, causing limited accuracy of scatter estimation.

PURPOSE

Aiming at improving the scatter estimation accuracy of the SKD algorithm, an intelligent scatter correction framework integrating the SKD with deep reinforcement learning (DRL) scheme is proposed.

METHODS

Our method firstly builds a scatter kernel model to iteratively convolve with raw projections, and then the deep Q-network of the DRL scheme is introduced to intelligently interact with the scatter kernel to achieve a projection adaptive parameter optimization. The potential of the proposed framework is demonstrated on CBCT head and pelvis simulation data and experimental CBCT measurement data. Furthermore, we have implemented the U-net based scatter estimation approach for comparison.

RESULTS

The simulation study demonstrates that the mean absolute percentage error (MAPE) of the proposed method is less than 9.72% and the peak signal-to-noise ratio (PSNR) is higher than 23.90 dB, while for the conventional SKD algorithm, the minimum MAPE is 17.92% and the maximum PSNR is 19.32 dB. In the measurement study, we adopt a hardware-based beam stop array algorithm to obtain the scatter-free projections as a comparison baseline, and our method can achieve superior performance with MAPE < 17.79% and PSNR > 16.34 dB.

CONCLUSIONS

In this paper, we propose an intelligent scatter correction framework that integrates the physical scatter kernel model with DRL algorithm, which has the potential to improve the accuracy of the clinical scatter correction method to obtain better CBCT imaging quality.

An unsupervised dual contrastive learning framework for scatter correction in cone-beam CT image

PURPOSE

Cone-beam computed tomography (CBCT) is widely utilized in modern radiotherapy; however, CBCT images exhibit increased scatter artifacts compared to planning CT (pCT), compromising image quality and limiting further applications. Scatter correction is thus crucial for improving CBCT image quality.

METHODS

In this study, we proposed an unsupervised contrastive learning method for CBCT scatter correction. Initially, we transformed low-quality CBCT into high-quality synthetic pCT (spCT) and generated forward projections of CBCT and spCT. By computing the difference between these projections, we obtained a residual image containing image details and scatter artifacts. Image details primarily comprise high-frequency signals, while scatter artifacts consist mainly of low-frequency signals. We extracted the scatter projection signal by applying a low-pass filter to remove image details. The corrected CBCT (cCBCT) projection signal was obtained by subtracting the scatter artifacts projection signal from the original CBCT projection. Finally, we employed the FDK reconstruction algorithm to generate the cCBCT image.

RESULTS

To evaluate cCBCT image quality, we aligned the CBCT and pCT of six patients. In comparison to CBCT, cCBCT maintains anatomical consistency and significantly enhances CT number, spatial homogeneity, and artifact suppression. The mean absolute error (MAE) of the test data decreased from 88.0623 ± 26.6700 HU to 17.5086 ± 3.1785 HU. The MAE of fat regions of interest (ROIs) declined from 370.2980 ± 64.9730 HU to 8.5149 ± 1.8265 HU, and the error between their maximum and minimum CT numbers decreased from 572.7528 HU to 132.4648 HU. The MAE of muscle ROIs reduced from 354.7689 ± 25.0139 HU to 16.4475 ± 3.6812 HU. We also compared our proposed method with several conventional unsupervised synthetic image generation techniques, demonstrating superior performance.

CONCLUSIONS

Our approach effectively enhances CBCT image quality and shows promising potential for future clinical adoption.

Scatter correction of 4D cone beam computed tomography to detect dosimetric effects due to anatomical changes in proton therapy for lung cancer

BACKGROUND

The treatment of moving tumor entities is expected to have superior clinical outcomes, using image-guided adaptive intensity-modulated proton therapy (IMPT).

PURPOSE

For 21 lung cancer patients, IMPT dose calculations were performed on scatter-corrected 4D cone beam CTs (4DCBCTcor ) to evaluate their potential for triggering treatment adaptation. Additional dose calculations were performed on corresponding planning 4DCTs and day-of-treatment 4D virtual CTs (4DvCTs).

METHODS

A 4DCBCT correction workflow, previously validated on a phantom, generates 4DvCT (CT-to-CBCT deformable registration) and 4DCBCTcor images (projection-based correction using 4DvCT as a prior) with 10 phase bins, using day-of-treatment free-breathing CBCT projections and planning 4DCT images as input. Using a research planning system, robust IMPT plans administering eight fractions of 7.5 Gy were created on a free-breathing planning CT (pCT) contoured by a physician. The internal target volume (ITV) was overridden with muscle tissue. Robustness settings for range and setup uncertainties were 3% and 6 mm, and a Monte Carlo dose engine was used. On every phase of planning 4DCT, day-of-treatment 4DvCT, and 4DCBCTcor , the dose was recalculated. For evaluation, image analysis as well as dose analysis were performed using mean error (ME) and mean absolute error (MAE) analysis, dose-volume histogram (DVH) parameters, and 2%/2-mm gamma pass rate analysis. Action levels (1.6% ITV D98 and 90% gamma pass rate) based on our previous phantom validation study were set to determine which patients had a loss of dosimetric coverage.

RESULTS

Quality enhancements of 4DvCT and 4DCBCTcor over 4DCBCT were observed. ITV D98% and bronchi D2% had its largest agreement for 4DCBCTcor -4DvCT, and the largest gamma pass rates (>94%, median 98%) were found for 4DCBCTcor -4DvCT. Deviations were larger and gamma pass rates were smaller for 4DvCT-4DCT and 4DCBCTcor -4DCT. For five patients, deviations were larger than the action levels, suggesting substantial anatomical changes between pCT and CBCT projections acquisition.

CONCLUSIONS

This retrospective study shows the feasibility of daily proton dose calculation on 4DCBCTcor for lung tumor patients. The applied method is of clinical interest as it generates up-to-date in-room images, accounting for breathing motion and anatomical changes. This information could be used to trigger replanning.

ScatterNet for projection-based 4D cone-beam computed tomography intensity correction of lung cancer patients

Background and purpose: In radiotherapy, dose calculations based on 4D cone beam CTs (4DCBCTs) require image intensity corrections. This retrospective study compared the dose calculation accuracy of a deep learning, projection-based scatter correction workflow (ScatterNet), to slower workflows: conventional 4D projection-based scatter correction (CBCTcor) and a deformable image registration (DIR)-based method (4DvCT). Materials and methods: For 26 lung cancer patients, planning CTs (pCTs), 4DCTs and CBCT projections were available. ScatterNet was trained with pairs of raw and corrected CBCT projections. Corrected projections from ScatterNet and the conventional workflow were reconstructed using MA-ROOSTER, yielding 4DCBCTSN and 4DCBCTcor. The 4DvCT was generated by 4DCT to 4DCBCT DIR, as part of the 4DCBCTcor workflow. Robust intensity modulated proton therapy treatment plans were created on free-breathing pCTs. 4DCBCTSN was compared to 4DCBCTcor and the 4DvCT in terms of image quality and dose calculation accuracy (dose-volume-histogram parameters and 3 % /3 mm gamma analysis). Results: 4DCBCTSN resulted in an average mean absolute error of 87 HU and 102 HU when compared to 4DCBCTcor and 4DvCT respectively. High agreement was observed in targets with median dose differences of 0.4 Gy (4DCBCTSN-4DCBCTcor) and 0.3 Gy (4DCBCTSN-4DvCT). The gamma analysis showed high average 3 % /3 mm pass rates of 96 % for both 4DCBCTSN vs. 4DCBCTcor and 4DCBCTSN vs. 4DvCT. Conclusions: Accurate 4D dose calculations are feasible for lung cancer patients using ScatterNet for 4DCBCT correction. Average scatter correction times could be reduced from 10 min (4DCBCTcor) to 3.9 s , showing the clinical suitability of the proposed deep learning-based method.

Four-Dimensional Cone Beam CT Imaging Using a Single Routine Scan via Deep Learning

A novel method is proposed to obtain four-dimensional (4D) cone-beam computed tomography (CBCT) images from a routine scan in patients with upper abdominal cancer. The projections are sorted according to the location of the lung diaphragm before being reconstructed to phase-sorted data. A multiscale-discriminator generative adversarial network (MSD-GAN) is proposed to alleviate the severe streaking artifacts in the original images. The MSD-GAN is trained using simulated CBCT datasets from patient planning CT images. The enhanced images are further used to estimate the deformable vector field (DVF) among breathing phases using a deformable image registration method. The estimated DVF is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction approach to generate 4D CBCT images. The proposed MSD-GAN is compared with U-Net on the performance of image enhancement. Results show that the proposed method significantly outperforms the total variation regularization-based iterative reconstruction approach and the method using only MSD-GAN to enhance original phase-sorted images in simulation and patient studies on 4D reconstruction quality. The MSD-GAN also shows higher accuracy than the U-Net. The proposed method enables a practical way for 4D-CBCT imaging from a single routine scan in upper abdominal cancer treatment including liver and pancreatic tumors.

Learning low-dose CT degradation from unpaired data with flow-based model

BACKGROUND

There has been growing interest in low-dose computed tomography (LDCT) for reducing the X-ray radiation to patients. However, LDCT always suffers from complex noise in reconstructed images. Although deep learning-based methods have shown their strong performance in LDCT denoising, most of them require a large number of paired training data of normal-dose CT (NDCT) images and LDCT images, which are hard to acquire in the clinic. Lack of paired training data significantly undermines the practicability of supervised deep learning-based methods. To alleviate this problem, unsupervised or weakly supervised deep learning-based methods are required.

PURPOSE

We aimed to propose a method that achieves LDCT denoising without training pairs. Specifically, we first trained a neural network in a weakly supervised manner to simulate LDCT images from NDCT images. Then, simulated training pairs could be used for supervised deep denoising networks.

METHODS

We proposed a weakly supervised method to learn the degradation of LDCT from unpaired LDCT and NDCT images. Concretely, LDCT and normal-dose images were fed into one shared flow-based model and projected to the latent space. Then, the degradation between low-dose and normal-dose images was modeled in the latent space. Finally, the model was trained by minimizing the negative log-likelihood loss with no requirement of paired training data. After training, an NDCT image can be input to the trained flow-based model to generate the corresponding LDCT image. The simulated image pairs of NDCT and LDCT can be further used to train supervised denoising neural networks for test.

RESULTS

Our method achieved much better performance on LDCT image simulation compared with the most widely used image-to-image translation method, CycleGAN, according to the radial noise power spectrum. The simulated image pairs could be used for any supervised LDCT denoising neural networks. We validated the effectiveness of our generated image pairs on a classic convolutional neural network, REDCNN, and a novel transformer-based model, TransCT. Our method achieved mean peak signal-to-noise ratio (PSNR) of 24.43dB, mean structural similarity (SSIM) of 0.785 on an abdomen CT dataset, mean PSNR of 33.88dB, mean SSIM of 0.797 on a chest CT dataset, which outperformed several traditional CT denoising methods, the same network trained by CycleGAN-generated data, and a novel transfer learning method. Besides, our method was on par with the supervised networks in terms of visual effects.

CONCLUSION

We proposed a flow-based method to learn LDCT degradation from only unpaired training data. It achieved impressive performance on LDCT synthesis. Next, we could train neural networks with the generated paired data for LDCT denoising. The denoising results are better than traditional and weakly supervised methods, comparable to supervised deep learning methods.