Scatter correction of cone-beam CT using a deep residual convolution neural network (DRCNN)

Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools

Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm's ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

Diagnostic capability of artificial intelligence tools for detecting and classifying odontogenic cysts and tumors: a systematic review and meta-analysis

OBJECTIVE

To evaluate the diagnostic capability of artificial intelligence (AI) for detecting and classifying odontogenic cysts and tumors, with special emphasis on odontogenic keratocyst (OKC) and ameloblastoma.

STUDY DESIGN

Nine electronic databases and the gray literature were examined. Human-based studies using AI algorithms to detect or classify odontogenic cysts and tumors by using panoramic radiographs or CBCT were included. Diagnostic tests were evaluated, and a meta-analysis was performed for classifying OKCs and ameloblastomas. Heterogeneity, risk of bias, and certainty of evidence were evaluated.

RESULTS

Twelve studies concluded that AI is a promising tool for the detection and/or classification of lesions, producing high diagnostic test values. Three articles assessed the sensitivity of convolutional neural networks in classifying similar lesions using panoramic radiographs, specifically OKC and ameloblastoma. The accuracy was 0.893 (95% CI 0.832-0.954). AI applied to cone beam computed tomography produced superior accuracy based on only 4 studies. The results revealed heterogeneity in the models used, variations in imaging examinations, and discrepancies in the presentation of metrics.

CONCLUSION

AI tools exhibited a relatively high level of accuracy in detecting and classifying OKC and ameloblastoma. Panoramic radiography appears to be an accurate method for AI-based classification of these lesions, albeit with a low level of certainty. The accuracy of CBCT model data appears to be high and promising, although with limited available data.

Scatter estimation and correction using time-of-flight and deconvolution in x-ray medical imaging

Objective.Time-of-flight (TOF) scatter rejection requires a total timing jitter, including the detector timing jitter and the x-ray source's pulses width, of 50 ps or less to mitigate most of the effects of scattered photons in radiography and CT imaging. However, since the total contribution of the source and detector to the timing jitter can be retrieved during an acquisition with nothing between the source and detector, it can be demonstrated that this contribution may be partially removed to improve the image quality.Approach.A scatter correction method using iterative deconvolution of the measured time point-spread function estimates the number of scattered photons detected in each pixel. To evaluate the quality of the estimation, GATE was used to simulate the radiography of a water cylinder with bone inserts, and a head and torso in a system with total timing jitters from 100 ps up to 500 ps full-width-at-half-maximum (FWHM).Main results.With a total timing jitter of 200 ps FWHM, 89% of the contrast degradation caused by scattered photons was recovered in a head and torso radiography, compared to 28% with a simple time threshold method. Corrected images using the estimation have a percent root-mean square error between 2% and 14% in both phantoms with timing jitters from 100 to 500 ps FWHM which is lower than the error achieved with scatter rejection alone at 100 ps FWHM.Significance.TOF x-ray imaging has the potential to mitigate the effects of the scattering contribution and offers an alternative to anti-scatter grids that avoids loss of primary photons. Compare to simple TOF scatter rejection using only a threshold, the deconvolution estimation approach has lower requirements on both the source and detector. These requirements are now within reach of state-of-the-art systems.

A joint learning framework for multisite CBCT-to-CT translation using a hybrid CNN-transformer synthesizer and a registration network

Background

Cone-beam computed tomography (CBCT) is a convenient method for adaptive radiation therapy (ART), but its application is often hindered by its image quality. We aim to develop a unified deep learning model that can consistently enhance the quality of CBCT images across various anatomical sites by generating synthetic CT (sCT) images.

Methods

A dataset of paired CBCT and planning CT images from 135 cancer patients, including head and neck, chest and abdominal tumors, was collected. This dataset, with its rich anatomical diversity and scanning parameters, was carefully selected to ensure comprehensive model training. Due to the imperfect registration, the inherent challenge of local structural misalignment of paired dataset may lead to suboptimal model performance. To address this limitation, we propose SynREG, a supervised learning framework. SynREG integrates a hybrid CNN-transformer architecture designed for generating high-fidelity sCT images and a registration network designed to correct local structural misalignment dynamically during training. An independent test set of 23 additional patients was used to evaluate the image quality, and the results were compared with those of several benchmark models (pix2pix, cycleGAN and SwinIR). Furthermore, the performance of an autosegmentation application was also assessed.

Results

The proposed model disentangled sCT generation from anatomical correction, leading to a more rational optimization process. As a result, the model effectively suppressed noise and artifacts in multisite applications, significantly enhancing CBCT image quality. Specifically, the mean absolute error (MAE) of SynREG was reduced to 16.81 ± 8.42 HU, whereas the structural similarity index (SSIM) increased to 94.34 ± 2.85%, representing improvements over the raw CBCT data, which had the MAE of 26.74 ± 10.11 HU and the SSIM of 89.73 ± 3.46%. The enhanced image quality was particularly beneficial for organs with low contrast resolution, significantly increasing the accuracy of automatic segmentation in these regions. Notably, for the brainstem, the mean Dice similarity coefficient (DSC) increased from 0.61 to 0.89, and the MDA decreased from 3.72 mm to 0.98 mm, indicating a substantial improvement in segmentation accuracy and precision.

Conclusions

SynREG can effectively alleviate the differences in residual anatomy between paired datasets and enhance the quality of CBCT images.

Correction of scatter in CBCT with a new grid design

Objective.This study aims at developing a simple and rapid Compton scatter correction approach for cone-beam CT (CBCT) imaging.Approach.In this work, a new Compton scatter estimation model is established based on two distinct CBCT scans: one measures the full primary and scatter signals without anti-scatter grid (ASG), and the other measures a portion of primary and scatter signals with ASG. To accelerate the entire data acquisition speed, a half anti-scatter grid (h-ASG) that covers half of the full detector surface is proposed. As a result, the distribution of scattered x-ray photons could be estimated from a single CBCT scan. Physical phantom experiments are conducted to validate the performance of the newly proposed scatter correction approach.Main results.Results demonstrate that the proposed half grid approach can quickly and precisely estimate the distribution of scattered x-ray photons from only one single CBCT scan, resulting in a significant reduction of shading artifacts. In addition, it is found that the h-ASG approach is less sensitive to the grid transmission fractions, grid ratio and object size, indicating a robust performance of the new method.Significance.In the future, the Compton scatter artifacts can be quickly corrected using a half grid in CBCT imaging.

A deep-learning-based scatter correction with water equivalent path length map for digital radiography

We proposed a new deep learning (DL) model for accurate scatter correction in digital radiography. The proposed network featured a pixel-wise water equivalent path length (WEPL) map of subjects with diverse sizes and 3D inner structures. The proposed U-Net model comprises two concatenated modules: one for generating a WEPL map and the other for predicting scatter using the WEPL map as auxiliary information. First, 3D CT images were used as numerical phantoms for training and validation, generating observed and scattered images by Monte Carlo simulation, and WEPL maps using Siddon's algorithm. Then, we optimised the model without overfitting. Next, we validated the proposed model's performance by comparing it with other DL models. The proposed model obtained scatter-corrected images with a peak signal-to-noise ratio of 44.24 ± 2.89 dB and a structural similarity index measure of 0.9987 ± 0.0004, which were higher than other DL models. Finally, scatter fractions (SFs) were compared with other DL models using an actual phantom to confirm practicality. Among DL models, the proposed model showed the smallest deviation from measured SF values. Furthermore, using an actual radiograph containing an acrylic object, the contrast-to-noise ratio (CNR) of the proposed model and the anti-scatter grid were compared. The CNR of the images corrected using the proposed model are 16% and 82% higher than those of the raw and grid-applied images, respectively. The advantage of the proposed method is that no actual radiography system is required for collecting training dataset, as the dataset is created from CT images using Monte Carlo simulation.

Convolutional LSTM model for cine image prediction of abdominal motion

Objective.In this study, we tackle the challenge of latency in magnetic resonance linear accelerator (MR-Linac) systems, which compromises target coverage accuracy in gated real-time radiotherapy. Our focus is on enhancing motion prediction precision in abdominal organs to address this issue. We developed a convolutional long short-term memory (convLSTM) model, utilizing 2D cine magnetic resonance (cine-MR) imaging for this purpose.Approach.Our model, featuring a sequence-to-one architecture with six input frames and one output frame, employs structural similarity index measure (SSIM) as loss function. Data was gathered from 17 cine-MRI datasets using the Philips Ingenia MR-sim system and an Elekta Unity MR-Linac equivalent sequence, focusing on regions of interest (ROIs) like the stomach, liver, pancreas, and kidney. The datasets varied in duration from 1 to 10 min.Main results.The study comprised three main phases: hyperparameter optimization, individual training, and transfer learning with or without fine-tuning. Hyperparameters were initially optimized to construct the most effective model. Then, the model was individually applied to each dataset to predict images four frames ahead (1.24-3.28 s). We evaluated the model's performance using metrics such as SSIM, normalized mean square error, normalized correlation coefficient, and peak signal-to-noise ratio, specifically for ROIs with target motion. The average SSIM values achieved were 0.54, 0.64, 0.77, and 0.66 for the stomach, liver, kidney, and pancreas, respectively. In the transfer learning phase with fine-tuning, the model showed improved SSIM values of 0.69 for the liver and 0.78 for the kidney, compared to 0.64 and 0.37 without fine-tuning.Significance. The study's significant contribution is demonstrating the convLSTM model's ability to accurately predict motion for multiple abdominal organs using a Unity-equivalent MR sequence. This advancement is key in mitigating latency issues in MR-Linac radiotherapy, potentially improving the precision and effectiveness of real-time treatment for abdominal cancers.

UBES: Unified scatter correction using ultrafast Boltzmann equation solver for conebeam CT

A semi-analytical solution to the unified Boltzmann equation is constructed to exactly describe the scatter distribution on a flat-panel detector for high-quality conebeam CT (CBCT) imaging. The solver consists of three parts, including the phase space distribution estimator, the effective source constructor and the detector signal extractor. Instead of the tedious Monte Carlo solution, the derived Boltzmann equation solver achieves ultrafast computational capability for scatter signal estimation by combining direct analytical derivation and time-efficient one-dimensional numerical integration over the trajectory along each momentum of the photon phase space distribution. The execution of scatter estimation using the proposed ultrafast Boltzmann equation solver (UBES) for a single projection is finalized in around 0.4 seconds. We compare the performance of the proposed method with the state-of-the-art schemes, including a time-expensive Monte Carlo (MC) method and a conventional kernel-based algorithm using the same dataset, which is acquired from the CBCT scans of a head phantom and an abdominal patient. The evaluation results demonstrate that the proposed UBES method achieves comparable correction accuracy compared with the MC method, while exhibits significant improvements in image quality over learning and kernel-based methods. With the advantages of MC equivalent quality and superfast computational efficiency, the UBES method has the potential to become a standard solution to scatter correction in high-quality CBCT reconstruction.

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.

An efficient quasi-Monte Carlo method with forced fixed detection for photon scatter simulation in CT

Detected scattered photons can cause cupping and streak artifacts, significantly degrading the quality of CT images. For fast and accurate estimation of scatter intensities resulting from photon interactions with a phantom, we first transform the path probability of photons interacting with the phantom into a high-dimensional integral. Secondly, we develope a new efficient algorithm called gQMCFFD, which combines graphics processing unit(GPU)-based quasi-Monte Carlo (QMC) with forced fixed detection to approximate this integral. QMC uses low discrepancy sequences for simulation and is deterministic versions of Monte Carlo. Numerical experiments show that the results are in excellent agreement and the efficiency improvement factors are 4 ∼ 46 times in all simulations by gQMCFFD with comparison to GPU-based Monte Carlo methods. And by combining gQMCFFD with sparse matrix method, the simulation time is reduced to 2 seconds in a single projection angle and the relative difference is 3.53%.

Image-based scatter correction for cone-beam CT using flip swin transformer U-shape network

BACKGROUND

Cone beam computed tomography (CBCT) plays an increasingly important role in image-guided radiation therapy. However, the image quality of CBCT is severely degraded by excessive scatter contamination, especially in the abdominal region, hindering its further applications in radiation therapy.

PURPOSE

To restore low-quality CBCT images contaminated by scatter signals, a scatter correction algorithm combining the advantages of convolutional neural networks (CNN) and Swin Transformer is proposed.

METHODS

In this paper a scatter correction model for CBCT image, the Flip Swin Transformer U-shape network (FSTUNet) model, is proposed. In this model, the advantages of CNN in texture detail and Swin Transformer in global correlation are used to accurately extract shallow and deep features, respectively. Instead of using the original Swin Transformer tandem structure, we build the Flip Swin Transformer Block to achieve a more powerful inter-window association extraction. The validity and clinical relevance of the method is demonstrated through extensive experiments on a Monte Carlo (MC) simulation dataset and frequency split dataset generated by a validated method, respectively.

RESULT

Experimental results on the MC simulated dataset show that the root mean square error of images corrected by the method is reduced from over 100 HU to about 7 HU. Both the structural similarity index measure (SSIM) and the universal quality index (UQI) are close to 1. Experimental results on the frequency split dataset demonstrate that the method not only corrects shading artifacts but also exhibits a high degree of structural consistency. In addition, comparison experiments show that FSTUNet outperforms UNet, Deep Residual Convolutional Neural Network (DRCNN), DSENet, Pix2pixGAN, and 3DUnet methods in both qualitative and quantitative metrics.

CONCLUSIONS

Accurately capturing the features at different levels is greatly beneficial for reconstructing high-quality scatter-free images. The proposed FSTUNet method is an effective solution to CBCT scatter correction and has the potential to improve the accuracy of CBCT image-guided radiation therapy.

A novel beam stopper-based approach for scatter correction in digital planar radiography

X-ray scatter in planar radiography degrades the contrast resolution of the image, thus reducing its diagnostic utility. Antiscatter grids partially block scattered photons at the cost of increasing the dose delivered by two- to four-fold and posing geometrical restrictions that hinder their use for other acquisition settings, such as portable radiography. The few software-based approaches investigated for planar radiography mainly estimate the scatter map from a low-frequency version of the image. We present a novel method for scatter correction in planar imaging based on direct patient measurements. Samples from the shadowed regions of an additional partially obstructed projection acquired with a beam stopper placed between the X-ray source and the patient are used to estimate the scatter map. Evaluation with simulated and real data showed an increase in contrast resolution for both lung and spine and recovery of ground truth values superior to those of three recently proposed methods. Our method avoids the biases of post-processing methods and yields results similar to those for an antiscatter grid while removing geometrical restrictions at around half the radiation dose. It can be used in unconventional imaging techniques, such as portable radiography, where training datasets needed for deep-learning approaches would be very difficult to obtain.

A correlated sampling-based Monte Carlo simulation for fast CBCT iterative scatter correction

BACKGROUND

In recent years, cone-beam computed tomography (CBCT) has played an important role in medical imaging. However, the applications of CBCT are limited due to the severe scatter contamination. Conventional Monte Carlo (MC) simulation can provide accurate scatter estimation for scatter correction, but the expensive computational cost has always been the bottleneck of MC method in clinical application.

PURPOSE

In this work, an MC simulation method combined with a variance reduction technique called correlated sampling is proposed for fast iterative scatter correction.

METHODS

Correlated sampling exploits correlation between similar simulation systems to reduce the variance of interest quantities. Specifically, conventional MC simulation is first performed on the scatter-contaminated CBCT to generate the initial scatter signal. In the subsequent correction iterations, scatter estimation is then updated by applying correlated MC sampling to the latest corrected CBCT images by reusing the random number sequences of the task-related photons in conventional MC. Afterward, the corrected projections obtained by subtracting the scatter estimation from raw projections are utilized for FDK reconstruction. These steps are repeated until an adequate scatter correction is obtained. The performance of the proposed framework is evaluated by the accuracy of the scatter estimation, the quality of corrected CBCT images and efficiency.

RESULTS

Overall, the difference in mean absolute percentage error between scatter estimation with and without correlated sampling is 0.25% for full-fan case and 0.34% for half-fan case, respectively. In simulation studies, scatter artifacts are substantially eliminated, where the mean absolute error value is reduced from 15 to 2 HU in full-fan case and from 53 to 13 HU in half-fan case. Scatter-to-primary ratio is reduced to 0.02 for full-fan and 0.04 for half-fan, respectively. In phantom study, the contrast-to-noise ratio (CNR) is increased by a factor of 1.63, and the contrast is increased by a factor of 1.77. As for clinical studies, the CNR is improved by 11% and 14% for half-fan and full-fan, respectively. The contrast after correction is increased by 19% for half-fan and 44% for full-fan. Furthermore, root mean square error is also effectively reduced, especially from 78 to 4 HU for full-fan. Experimental results demonstrate that the figure of merit is improved between 23 and 43 folds when using correlated sampling. The proposed method takes less than 25 s for the whole iterative scatter correction process.

CONCLUSIONS

The proposed correlated sampling-based MC simulation method can achieve fast and accurate scatter correction for CBCT, making it suitable for real-time clinical use.

Dosimetric benefits of adaptive radiation therapy for patients with stage III non-small cell lung cancer

BACKGROUND

Daily adaptive radiation therapy (ART) of patients with non-small cell lung cancer (NSCLC) lowers organs at risk exposure while maintaining the planning target volume (PTV) coverage. Thus, ART allows an isotoxic approach with increased doses to the PTV that could improve local tumor control. Herein we evaluate daily online ART strategies regarding their impact on relevant dose-volume metrics.

METHODS

Daily cone-beam CTs (1 × n = 28, 1 × n = 29, 11 × n = 30) of 13 stage III NSCLC patients were converted into synthetic CTs (sCTs). Treatment plans (TPs) were created retrospectively on the first-fraction sCTs (sCT₁) and subsequently transferred unaltered to the sCTs of the remaining fractions of each patient (sCT_2-n) (IGRT scenario). Two additional TPs were generated on sCT_2-n: one minimizing the lung-dose while preserving the D_95%(PTV) (isoeffective scenario), the other escalating the D_95%(PTV) with a constant V_20Gy(lung_ipsilateral) (isotoxic scenario).

RESULTS

Compared to the original TPs predicted dose, the median D_95%(PTV) in the IGRT scenario decreased by 1.6 Gy ± 4.2 Gy while the V_20Gy(lung_ipsilateral) increased in median by 1.1% ± 4.4%. The isoeffective scenario preserved the PTV coverage and reduced the median V_20Gy(lung_ipsilateral) by 3.1% ± 3.6%. Furthermore, the median V_5%(heart) decreased by 2.9% ± 6.4%. With an isotoxic prescription, a median dose-escalation to the gross target volume of 10.0 Gy ± 8.1 Gy without increasing the V_20Gy(lung_ipsilateral) and V_5%(heart) was feasible.

CONCLUSIONS

We demonstrated that even without reducing safety margins, ART can reduce lung-doses, while still reaching adequate target coverage or escalate target doses without increasing ipsilateral lung exposure. Clinical benefits by means of toxicity and local control of both strategies should be evaluated in prospective clinical trials.

A practical and robust method for beam blocker-based cone beam CT scatter correction

Objective. In the traditional beam-blocker based cone beam CT (CBCT) scatter correction, the scatter measured in the region shaded by lead strips was multiplied by a correction factor to directly represent the scatter in the unblocked region. The correction factor optimization is a tedious process and lacks an objective stop criterion. To skip the optimization process, an indirect scatter estimation method was developed and validated in phantom imaging.Approach.A beam-blocker made of lead strips was mounted between the x-ray source and object for scatter estimation. The primary signal between lead strips in the blocked region was first calculated by subtracting the measured scatter, and then used to calculate the scatter signal in the unblocked region corresponding to the same attenuation path. The calculated scatter signal was smoothed via local filtration and used to correct the measured projection in the unblocked region. Finally, the CBCT was reconstructed via Feldkamp-Davis-Kress algorithm. A Catphan and a head phantom were used to verify the performance of the proposed method in both full- and half-blocker scenarios, and with and without a bow-tie filter.Main Results. For scans without the bow-tie filter, the CT number error was reduced to 3.97±2.27 and 5.51±3.90 HU in the full- and half-blocker scenarios, respectively, for the Catphan, and to 4.01±2.18 and 7.97 ± 4.05 HU for the head phantom. When the bow-tie filter was applied, the CT number error was reduced to 2.29±1.42 and 6.72±0.77 HU in the full- and half-blocker scenarios, respectively, for the Catphan, and 2.35±1.25 and 4.96 ± 1.89 HU for the head phantom.Significance. The proposed method effectively avoids the influence of the inserted beam blocker itself on the scatter intensity estimation, and proves a more practical and robust way for the beam-blocker based scatter correction in CBCT scanning.

A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy

Purpose

The challenge of cone-beam computed tomography (CBCT) is its low image quality, which limits its application for adaptive radiotherapy (ART). Despite recent substantial improvement in CBCT imaging using the deep learning method, the image quality still needs to be improved for effective ART application. Spurred by the advantages of transformers, which employs multi-head attention mechanisms to capture long-range contextual relations between image pixels, we proposed a novel transformer-based network (called TransCBCT) to generate synthetic CT (sCT) from CBCT. This study aimed to further improve the accuracy and efficiency of ART.

Materials and methods

In this study, 91 patients diagnosed with prostate cancer were enrolled. We constructed a transformer-based hierarchical encoder–decoder structure with skip connection, called TransCBCT. The network also employed several convolutional layers to capture local context. The proposed TransCBCT was trained and validated on 6,144 paired CBCT/deformed CT images from 76 patients and tested on 1,026 paired images from 15 patients. The performance of the proposed TransCBCT was compared with a widely recognized style transferring deep learning method, the cycle-consistent adversarial network (CycleGAN). We evaluated the image quality and clinical value (application in auto-segmentation and dose calculation) for ART need.

Results

TransCBCT had superior performance in generating sCT from CBCT. The mean absolute error of TransCBCT was 28.8 ± 16.7 HU, compared to 66.5 ± 13.2 for raw CBCT, and 34.3 ± 17.3 for CycleGAN. It can preserve the structure of raw CBCT and reduce artifacts. When applied in auto-segmentation, the Dice similarity coefficients of bladder and rectum between auto-segmentation and oncologist manual contours were 0.92 and 0.84 for TransCBCT, respectively, compared to 0.90 and 0.83 for CycleGAN. When applied in dose calculation, the gamma passing rate (1%/1 mm criterion) was 97.5% ± 1.1% for TransCBCT, compared to 96.9% ± 1.8% for CycleGAN.

Conclusions

The proposed TransCBCT can effectively generate sCT for CBCT. It has the potential to improve radiotherapy accuracy.

Deep learning methods for enhancing cone-beam CT image quality towards adaptive radiation therapy: A systematic review

The use of deep learning (DL) to improve cone-beam CT (CBCT) image quality has gained popularity as computational resources and algorithmic sophistication have advanced in tandem. CBCT imaging has the potential to facilitate online adaptive radiation therapy (ART) by utilizing up-to-date patient anatomy to modify treatment parameters before irradiation. Poor CBCT image quality has been an impediment to realizing ART due to the increased scatter conditions inherent to cone-beam acquisitions. Given the recent interest in DL applications in radiation oncology, and specifically DL for CBCT correction, we provide a systematic theoretical and literature review for future stakeholders. The review encompasses DL approaches for synthetic CT generation, as well as projection domain methods employed in the CBCT correction literature. We review trends pertaining to publications from January 2018 to April 2022 and condense their major findings - with emphasis on study design and deep learning techniques. Clinically relevant endpoints relating to image quality and dosimetric accuracy are summarised, highlighting gaps in the literature. Finally, we make recommendations for both clinicians and DL practitioners based on literature trends and the current DL state of the art methods utilized in radiation oncology. This article is protected by copyright. All rights reserved.

Correction of Bowtie filter induced scatter signals based on air scan data and object scan data

In a cone beam CT system, a bowtie filter brings in additional scatter signals with respect to object induced scatter signals, which can degrade image quality and sometimes result in artifacts. This work aims to improve the image quality of CT scans by analyzing the contribution of bowtie filter induced scatter signals and removing them from projection data. Air calibration is a very useful preprocessing step to eliminate the response variations of detector pixels. Bowtie filter induced scattered x-ray signals of air scans are recorded in air calibration tables and therefore considered as a part of primary signals. However, scattered X-rays behave differently in scanned objects compared to primary x-rays. The difference should be corrected to eliminate the impact of bowtie filter induced scatter signals. A kernel based correction algorithm based on air scan data, named bowtie filter scatter correction algorithm, is applied to estimate and to eliminate the bowtie filter induced scatter signals in object scans. The scatter signals of air scans can be measured with air scans or retrieved from air calibration tables of a CT system, and can be used as input of the correction algorithm to estimate the change of scatter signals caused by the scanned objects in the scan field. Based on the assumption that the scatter signals in the projection data scanned with narrow collimation can be neglected, the difference signals between narrow and broad collimations can be used to estimate bowtie filter induced scatter signals for air scans with the correction of extra-focal radiations (EFRs). The calculated bowtie filter induced scatter signals have been compared with the results of Monte Carlo simulations, and the parameters of correction algorithm have been determined by fitting the measured scatter signal curves of phantom scans with calculated curves. Projection data have been reconstructed using Filtered BackProjection (FBP) method with and without bowtie filter correction to check whether the image quality is improved. Scatter signals can be well approximated with the bowtie filter scatter correction algorithm together with an existing object scatter correction algorithm. After removing the bowtie filter induced scatter signals, the dark bands in reconstructed images in the regions near the edges of scanned objects can be mostly eliminated. The difference signals of air scan data between narrow and broad collimations can be used to estimate the bowtie filter induced scatter for air scans. The proposed bowtie filter scatter correction algorithm using air scan data can be applied to estimate and to remove most of the bowtie filter induced scatter signals in object scans.

A generalized image quality improvement strategy of cone-beam CT using multiple spectral CT labels in Pix2pix GAN

Objective. The quantitative and routine imaging capabilities of cone-beam CT (CBCT) are hindered from clinical applications due to the severe shading artifacts of scatter contamination. The scatter correction methods proposed in the literature only consider the anatomy of the scanned objects while disregarding the impact of incident x-ray energy spectra. The multiple-spectral model is in urgent need for CBCT scatter estimation. Approach. In this work, we incorporate the multiple spectral diagnostic multidetector CT labels into the pixel-to-pixel (Pix2pix) GAN to estimate accurate scatter distributions from CBCT projections acquired at various imaging volume sizes and x-ray energy spectra. The Pix2pix GAN combines the residual network as the generator and the PatchGAN as the discriminator to construct the correspondence between the scatter-contaminated projection and scatter distribution. The network architectures and loss function of Pix2pix GAN are optimized to achieve the best performance on projection-to-scatter transition. Results. The CBCT data of a head phantom and abdominal patients are applied to test the performance of the proposed method. The error of the corrected CBCT image using the proposed method is reduced from over 200 HU to be around 20 HU in both phantom and patient studies. The mean structural similarity index of the CT image is improved from 0.2 to around 0.9 after scatter correction using the proposed method compared with the MC-simulation method, which indicates a high similarity of the anatomy in the images before and after the proposed correction. The proposed method achieves higher accuracy of scatter estimation than using the Pix2pix GAN with the U-net generator. Significance. The proposed scheme is an effective solution to the multiple spectral CBCT scatter correction. The scatter-correction software using the proposed model will be available at: https://github.com/YangkangJiang/Cone-beam-CT-scatter-correction-tool.

A dose-neutral image quality comparison of different CBCT and CT systems using paranasal sinus imaging protocols and phantoms

Purpose

To compare the image quality produced by equivalent low-dose and default sinus imaging protocols of a conventional dental cone-beam computed tomography (CBCT) scanner, an extremity CBCT scanner and a clinical multidetector computed tomography (MDCT) scanner.

Methods

Three different phantoms were scanned using dose–neutral ultra-low-dose and low-dose sinus imaging protocols, as well as default sinus protocols of each device. Quantified parameters of image quality included modulation transfer function (MTF) to characterize the spatial response of the imaging system, contrast-to-noise ratio, low contrast visibility, image uniformity and Hounsfield unit accuracy. MTF was calculated using the line spread and edge spread functions (LSF and ESF).

Results

The dental CBCT had superior performance over the extremity CBCT in each studied parameter at similar dose levels. The MDCT had better contrast-to-noise ratio, low contrast visibility and image uniformity than the CBCT scanners. However, the CBCT scanners had better resolution compared to the MDCT. Accuracy of HU values for different materials was on the same level between the dental CBCT and MDCT, but substantially poorer performance was observed with the extremity CBCT.

Conclusions

The studied dental CBCT scanner showed superior performance over the studied extremity CBCT scanner when using dose–neutral imaging protocols. In case a dental CBCT is not available, the given extremity CBCT is still a viable option as it provides the benefit of high resolution over a conventional MDCT.

CBCT-based synthetic CT generation using generative adversarial networks with disentangled representation

Background

Cone-beam computed tomography (CBCT) plays a key role in image-guided radiotherapy (IGRT), however its poor image quality limited its clinical application. In this study, we developed a deep-learning based approach to translate CBCT image to synthetic CT (sCT) image that preserves both CT image quality and CBCT anatomical structures.

Methods

A novel synthetic CT generative adversarial network (sCTGAN) was proposed for CBCT-to-CT translation via disentangled representation. The approach of disentangled representation was employed to extract the anatomical information shared by CBCT and CT image domains. Both on-board CBCT and planning CT of 40 patients were used for network learning and those of another 12 patients were used for testing. Accuracy of our network was quantitatively evaluated using a series of statistical metrics, including the peak signal-to-noise ratio (PSNR), mean structural similarity index (SSIM), mean absolute error (MAE), and root-mean-square error (RMSE). Effectiveness of our network was compared against three state-of-the-art CycleGAN-based methods.

Results

The PSNR, SSIM, MAE, and RMSE between sCT generated by sCTGAN and deformed planning CT (dpCT) were 34.12 dB, 0.86, 32.70 HU, and 60.53 HU, while the corresponding values between original CBCT and dpCT were 28.67 dB, 0.64, 70.56 HU, and 112.13 HU. The RMSE (60.53±14.38 HU) of sCT generated by sCTGAN was less than that of sCT generated by all the three comparing methods (72.40±16.03 HU by CycleGAN, 71.60±15.09 HU by CycleGAN-Unet512, 64.93±14.33 HU by CycleGAN-AG).

Conclusions

The sCT generated by our sCTGAN network was closer to the ground truth (dpCT), in comparison to all the three comparing CycleGAN-based methods. It provides an effective way to generate high-quality sCT which has a wide application in IGRT and adaptive radiotherapy.

A deep-learning method for generating synthetic kV-CT and improving tumor segmentation for helical tomotherapy of nasopharyngeal carcinoma

Objective:Megavoltage computed tomography (MV-CT) is used for setup verification and adaptive radiotherapy in tomotherapy. However, its low contrast and high noise lead to poor image quality. This study aimed to develop a deep-learning-based method to generate synthetic kilovoltage CT (skV-CT) and then evaluate its ability to improve image quality and tumor segmentation.Approach:The planning kV-CT and MV-CT images of 270 patients with nasopharyngeal carcinoma (NPC) treated on an Accuray TomoHD system were used. An improved cycle-consistent adversarial network which used residual blocks as its generator was adopted to learn the mapping between MV-CT and kV-CT and then generate skV-CT from MV-CT. A Catphan 700 phantom and 30 patients with NPC were used to evaluate image quality. The quantitative indices included contrast-to-noise ratio (CNR), uniformity and signal-to-noise ratio (SNR) for the phantom and the structural similarity index measure (SSIM), mean absolute error (MAE), and peak signal-to-noise ratio (PSNR) for patients. Next, we trained three models for segmentation of the clinical target volume (CTV): MV-CT, skV-CT, and MV-CT combined with skV-CT. The segmentation accuracy was compared with indices of the dice similarity coefficient (DSC) and mean distance agreement (MDA).Mainresults:Compared with MV-CT, skV-CT showed significant improvement in CNR (184.0%), image uniformity (34.7%), and SNR (199.0%) in the phantom study and improved SSIM (1.7%), MAE (24.7%), and PSNR (7.5%) in the patient study. For CTV segmentation with only MV-CT, only skV-CT, and MV-CT combined with skV-CT, the DSCs were 0.75 ± 0.04, 0.78 ± 0.04, and 0.79 ± 0.03, respectively, and the MDAs (in mm) were 3.69 ± 0.81, 3.14 ± 0.80, and 2.90 ± 0.62, respectively.Significance:The proposed method improved the image quality of MV-CT and thus tumor segmentation in helical tomotherapy. The method potentially can benefit adaptive radiotherapy.

Image-based shading correction for narrow-FOV truncated pelvic CBCT with deep convolutional neural networks and transfer learning

Purpose: Cone beam computed tomography (CBCT) is a standard solution for in‐room image guidance for radiation therapy. It is used to evaluate and compensate for anatomopathological changes between the dose delivery plan and the fraction delivery day. CBCT is a fast and versatile solution, but it suffers from drawbacks like low contrast and requires proper calibration to derive density values. Although these limitations are even more prominent with in‐room customized CBCT systems, strategies based on deep learning have shown potential in improving image quality. As such, this article presents a method based on a convolutional neural network and a novel two‐step supervised training based on the transfer learning paradigm for shading correction in CBCT volumes with narrow field of view (FOV) acquired with an ad hoc in‐room system.

Methods: We designed a U‐Net convolutional neural network, trained on axial slices of corresponding CT/CBCT couples. To improve the generalization capability of the network, we exploited two‐stage learning using two distinct data sets. At first, the network weights were trained using synthetic CBCT scans generated from a public data set, and then only the deepest layers of the network were trained again with real‐world clinical data to fine‐tune the weights. Synthetic data were generated according to real data acquisition parameters. The network takes a single grayscale volume as input and outputs the same volume with corrected shading and improved HU values.

Results: Evaluation was carried out with a leave‐one‐out cross‐validation, computed on 18 unique CT/CBCT pairs from six different patients from a real‐world dataset. Comparing original CBCT to CT and improved CBCT to CT, we obtained an average improvement of 6 dB on peak signal‐to‐noise ratio (PSNR), +2% on structural similarity index measure (SSIM). The median interquartile range (IQR) Hounsfield unit (HU) difference between CBCT and CT improved from 161.37 (162.54) HU to 49.41 (66.70) HU. Region of interest (ROI)‐based HU difference was narrowed by 75% in the spongy bone (femoral head), 89% in the bladder, 85% for fat, and 83% for muscle. The improvement in contrast‐to‐noise ratio for these ROIs was about 67%.

Conclusions: We demonstrated that shading correction obtaining CT‐compatible data from narrow‐FOV CBCTs acquired with a customized in‐room system is possible. Moreover, the transfer learning approach proved particularly beneficial for such a shading correction approach.

Efficient high cone-angle artifact reduction in circular cone-beam CT using deep learning with geometry-aware dimension reduction

High cone-angle artifacts (HCAAs) appear frequently in circular cone-beam computed tomography (CBCT) images and can heavily affect diagnosis and treatment planning. To reduce HCAAs in CBCT scans, we propose a novel deep learning approach that reduces the three-dimensional (3D) nature of HCAAs to two-dimensional (2D) problems in an efficient way. Specifically, we exploit the relationship between HCAAs and the rotational scanning geometry by training a convolutional neural network (CNN) using image slices that were radially sampled from CBCT scans. We evaluated this novel approach using a dataset of input CBCT scans affected by HCAAs and high-quality artifact-free target CBCT scans. Two different CNN architectures were employed, namely U-Net and a mixed-scale dense CNN (MS-D Net). The artifact reduction performance of the proposed approach was compared to that of a Cartesian slice-based artifact reduction deep learning approach in which a CNN was trained to remove the HCAAs from Cartesian slices. In addition, all processed CBCT scans were segmented to investigate the impact of HCAAs reduction on the quality of CBCT image segmentation. We demonstrate that the proposed deep learning approach with geometry-aware dimension reduction greatly reduces HCAAs in CBCT scans and outperforms the Cartesian slice-based deep learning approach. Moreover, the proposed artifact reduction approach markedly improves the accuracy of the subsequent segmentation task compared to the Cartesian slice-based workflow.

Improving CBCT quality to CT level using deep learning with generative adversarial network

PURPOSE

To improve image quality and computed tomography (CT) number accuracy of daily cone beam CT (CBCT) through a deep learning methodology with generative adversarial network.

METHODS

One hundred and fifty paired pelvic CT and CBCT scans were used for model training and validation. An unsupervised deep learning method, 2.5D pixel-to-pixel generative adversarial network (GAN) model with feature mapping was proposed. A total of 12 000 slice pairs of CT and CBCT were used for model training, while ten-fold cross validation was applied to verify model robustness. Paired CT-CBCT scans from an additional 15 pelvic patients and 10 head-and-neck (HN) patients with CBCT images collected at a different machine were used for independent testing purpose. Besides the proposed method above, other network architectures were also tested as: 2D vs 2.5D; GAN model with vs without feature mapping; GAN model with vs without additional perceptual loss; and previously reported models as U-net and cycleGAN with or without identity loss. Image quality of deep-learning generated synthetic CT (sCT) images was quantitatively compared against the reference CT (rCT) image using mean absolute error (MAE) of Hounsfield units (HU) and peak signal-to-noise ratio (PSNR). The dosimetric calculation accuracy was further evaluated with both photon and proton beams.

RESULTS

The deep-learning generated sCTs showed improved image quality with reduced artifact distortion and improved soft tissue contrast. The proposed algorithm of 2.5 Pix2pix GAN with feature matching (FM) was shown to be the best model among all tested methods producing the highest PSNR and the lowest MAE to rCT. The dose distribution demonstrated a high accuracy in the scope of photon-based planning, yet more work is needed for proton-based treatment. Once the model was trained, it took 11-12 ms to process one slice, and could generate a 3D volume of dCBCT (80 slices) in less than a second using a NVIDIA GeForce GTX Titan X GPU (12 GB, Maxwell architecture).

CONCLUSION

The proposed deep learning algorithm is promising to improve CBCT image quality in an efficient way, thus has a potential to support online CBCT-based adaptive radiotherapy.

Synthetic dual-energy CT for MRI-only based proton therapy treatment planning using label-GAN

MRI-only treatment planning is highly desirable in the current proton radiation therapy workflow due to its appealing advantages such as bypassing MR-CT co-registration, avoiding x-ray CT exposure dose and reduced medical cost. However, MRI alone cannot provide stopping power ratio (SPR) information for dose calculations. Given that dual energy CT (DECT) can estimate SPR with higher accuracy than conventional single energy CT, we propose a deep learning-based method in this study to generate synthetic DECT (sDECT) from MRI to calculate SPR. Since the contrast difference between high-energy and low-energy CT (LECT) is important, and in order to accurately model this difference, we propose a novel label generative adversarial network-based model which can not only discriminate the realism of sDECT but also differentiate high-energy CT (HECT) and LECT from DECT. A cohort of 57 head-and-neck cancer patients with DECT and MRI pairs were used to validate the performance of the proposed framework. The results of sDECT and its derived SPR maps were compared with clinical DECT and the corresponding SPR, respectively. The mean absolute error for synthetic LECT and HECT were 79.98 ± 18.11 HU and 80.15 ± 16.27 HU, respectively. The corresponding SPR maps generated from sDECT showed a normalized mean absolute error as 5.22% ± 1.23%. By comparing with the traditional Cycle GANs, our proposed method significantly improves the accuracy of sDECT. The results indicate that on our dataset, the sDECT image form MRI is close to planning DECT, and thus shows promising potential for generating SPR maps for proton therapy.

Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy

PURPOSE

Image-guided radiation therapy could benefit from implementing adaptive radiation therapy (ART) techniques. A cycle-generative adversarial network (cycle-GAN)-based cone-beam computed tomography (CBCT)-to-synthetic CT (sCT) conversion algorithm was evaluated regarding image quality, image segmentation and dosimetric accuracy for head and neck (H&N), thoracic and pelvic body regions.

METHODS

Using a cycle-GAN, three body site-specific models were priorly trained with independent paired CT and CBCT datasets of a kV imaging system (XVI, Elekta). sCT were generated based on first-fraction CBCT for 15 patients of each body region. Mean errors (ME) and mean absolute errors (MAE) were analyzed for the sCT. On the sCT, manually delineated structures were compared to deformed structures from the planning CT (pCT) and evaluated with standard segmentation metrics. Treatment plans were recalculated on sCT. A comparison of clinically relevant dose-volume parameters (D₉₈, D₅₀ and D₂ of the target volume) and 3D-gamma (3%/3mm) analysis were performed.

RESULTS

The mean ME and MAE were 1.4, 29.6, 5.4 Hounsfield units (HU) and 77.2, 94.2, 41.8 HU for H&N, thoracic and pelvic region, respectively. Dice similarity coefficients varied between 66.7 ± 8.3% (seminal vesicles) and 94.9 ± 2.0% (lungs). Maximum mean surface distances were 6.3 mm (heart), followed by 3.5 mm (brainstem). The mean dosimetric differences of the target volumes did not exceed 1.7%. Mean 3D gamma pass rates greater than 97.8% were achieved in all cases.

CONCLUSIONS

The presented method generates sCT images with a quality close to pCT and yielded clinically acceptable dosimetric deviations. Thus, an important prerequisite towards clinical implementation of CBCT-based ART is fulfilled.

Artificial intelligence in radiotherapy: a technological review

Radiation therapy (RT) is widely used to treat cancer. Technological advances in RT have occurred in the past 30 years. These advances, such as three-dimensional image guidance, intensity modulation, and robotics, created challenges and opportunities for the next breakthrough, in which artificial intelligence (AI) will possibly play important roles. AI will replace certain repetitive and labor-intensive tasks and improve the accuracy and consistency of others, particularly those with increased complexity because of technological advances. The improvement in efficiency and consistency is important to manage the increasing cancer patient burden to the society. Furthermore, AI may provide new functionalities that facilitate satisfactory RT. The functionalities include superior images for real-time intervention and adaptive and personalized RT. AI may effectively synthesize and analyze big data for such purposes. This review describes the RT workflow and identifies areas, including imaging, treatment planning, quality assurance, and outcome prediction, that benefit from AI. This review primarily focuses on deep-learning techniques, although conventional machine-learning techniques are also mentioned.

[Use of artificial intelligence for image reconstruction]

CLINICAL/METHODOLOGICAL PROBLEM

In the reconstruction of three-dimensional image data, artifacts that interfere with the appraisal often occur as a result of trying to minimize the dose or due to missing data. Used iterative reconstruction methods are time-consuming and have disadvantages.

STANDARD RADIOLOGICAL METHODS

These problems are known to occur in computed tomography (CT), cone beam CT, interventional imaging, magnetic resonance imaging (MRI) and nuclear medicine imaging (PET and SPECT).

METHODOLOGICAL INNOVATIONS

Using techniques based on the use of artificial intelligence (AI) in data analysis and data supplementation, a number of problems can be solved up to a certain extent.

PERFORMANCE

The performance of the methods varies greatly. Since the generated image data usually look very good using the AI-based methods presented here while their results depend strongly on the study design, reliable comparable quantitative statements on the performance are not yet available in broad terms.

EVALUATION

In principle, the methods of image reconstruction based on AI algorithms offer many possibilities for improving and optimizing three-dimensional image datasets. However, the validity strongly depends on the design of the respective study in the structure of the individual procedure. It is therefore essential to have a suitable test prior to use in clinical practice.

PRACTICAL RECOMMENDATIONS

Before the widespread use of AI-based reconstruction methods can be recommended, it is necessary to establish meaningful test procedures that can characterize the actual performance and applicability in terms of information content and a meaningful study design during the learning phase of the algorithms.

Radiomics and Machine Learning in Oral Healthcare

The increasing storage of information, data, and forms of knowledge has led to the development of new technologies that can help to accomplish complex tasks in different areas, such as in dentistry. In this context, the role of computational methods, such as radiomics and Artificial Intelligence (AI) applications, has been progressing remarkably for dentomaxillofacial radiology (DMFR). These tools bring new perspectives for diagnosis, classification, and prediction of oral diseases, treatment planning, and for the evaluation and prediction of outcomes, minimizing the possibilities of human errors. A comprehensive review of the state-of-the-art of using radiomics and machine learning (ML) for imaging in oral healthcare is presented in this paper. Although the number of published studies is still relatively low, the preliminary results are very promising and in a near future, an augmented dentomaxillofacial radiology (ADMFR) will combine the use of radiomics-based and AI-based analyses with the radiologist's evaluation. In addition to the opportunities and possibilities, some challenges and limitations have also been discussed for further investigations.