Roles of red mud in remediation of contaminated soil in mining areas: Mechanisms, advances and perspectives.

Red mud (RM) is a kind of strong alkaline solid waste produced from the aluminum industry, which contributes significantly to environmental pollution and can cause severe health issues.Currently, RM is widely recognized as a potential material for soil remediation because of its rich metal oxide content, such as Fe/Al oxides. However, there is no comprehensive description on the roles of RM in passivation remediation of contaminated soil in mining areas. This review summarizes the mechanisms of passivation of heavy metals (HMs) in contaminated soil by RM, including precipitation, adsorption and ion exchange. Besides the effects of adding RM on soil physicochemical properties, heavy metal forms and ecological environment are further elaborated. Moreover, using the co-hydrothermal carbonization of RM and biomass for enhancing the efficiency of contaminated soil remediation is proposed as the main prospective research. This paper provides technical references for the resource utilization of RM and the treatment of heavy metal-contaminated soil.

MR-guided stereotactic radiation therapy for head and neck cancers.

Purpose: MR-guided radiotherapy (MRgRT) has the advantage of utilizing high soft tissue contrast imaging to track daily changes in target and critical organs throughout the entire radiation treatment course. Head and neck (HN) stereotactic body radiation therapy (SBRT) has been increasingly used to treat localized lesions within a shorter timeframe. The purpose of this study is to examine the dosimetric difference between the step-and-shot intensity modulated radiation therapy (IMRT) plans on Elekta Unity and our clinical volumetric modulated arc therapy (VMAT) plans on Varian TrueBeam for HN SBRT. Method: Fourteen patients treated on TrueBeam sTx with VMAT treatment plans were re-planned in the Monaco treatment planning system for Elekta Unity MR-Linac (MRL). The plan qualities, including target coverage, conformity, homogeneity, nearby critical organ doses, gradient index and low dose bath volume, were compared between VMAT and Monaco IMRT plans. Additionally, we evaluated the Unity adaptive plans of adapt-to-position (ATP) and adapt-to-shape (ATS) workflows using simulated setup errors for five patients and assessed the outcomes of our treated patients. Results: Monaco IMRT plans achieved comparable results to VMAT plans in terms of target coverage, uniformity and homogeneity, with slightly higher target maximum and mean doses. The critical organ doses in Monaco IMRT plans all met clinical goals; however, the mean doses and low dose bath volumes were higher than in VMAT plans. The adaptive plans demonstrated that the ATP workflow may result in degraded target coverage and OAR doses for HN SBRT, while the ATS workflow can maintain the plan quality. Conclusion: The use of Monaco treatment planning and online adaptation can achieve dosimetric results comparable to VMAT plans, with the additional benefits of real-time tracking of target volume and nearby critical structures. This offers the potential to treat aggressive and variable tumors in HN SBRT and improve local control and treatment toxicity.

SC-GAN: Structure-completion generative adversarial network for synthetic CT generation from MR images with truncated anatomy.

Creating synthetic CT (sCT) from magnetic resonance (MR) images enables MR-based treatment planning in radiation therapy. However, the MR images used for MR-guided adaptive planning are often truncated in the boundary regions due to the limited field of view and the need for sequence optimization. Consequently, the sCT generated from these truncated MR images lacks complete anatomic information, leading to dose calculation error for MR-based adaptive planning. We propose a novel structure-completion generative adversarial network (SC-GAN) to generate sCT with full anatomic details from the truncated MR images. To enable anatomy compensation, we expand input channels of the CT generator by including a body mask and introduce a truncation loss between sCT and real CT. The body mask for each patient was automatically created from the simulation CT scans and transformed to daily MR images by rigid registration as another input for our SC-GAN in addition to the MR images. The truncation loss was constructed by implementing either an auto-segmentor or an edge detector to penalize the difference in body outlines between sCT and real CT. The experimental results show that our SC-GAN achieved much improved accuracy of sCT generation in both truncated and untruncated regions compared to the original cycleGAN and conditional GAN methods.

Thermal utilization techniques and strategies for secondary aluminum dross: A review.

Secondary aluminum ash (SAD) disposal is challenging, particularly in developing countries, and presents severe eco-environmental risks. This paper presents the treatment techniques, mechanisms, and effects of SAD at the current technical-economic level based on aluminum ash's resource utilization and environmental properties. Five recovery techniques were summarized based on aluminum's recoverability in SAD. Four traditional utilization methods were outlined as per the utilization of alumina in SAD. Three new utilization methods of SAD were summarized based on the removability (or convertibility) of aluminum nitride in SAD. The R-U-R (recoverability, utilizability, and removability) theory of SAD was formed based on several studies that helped identify the fingerprint of SAD. Furthermore, the utilization strategies of SAD, which supported the recycling of aluminum ash, were proposed. To form a perfect fingerprint database and develop various relevant techniques, future research must focus on an extensive examination of the characteristics of aluminum ash. This research will be advantageous for addressing the resource and environmental challenges of aluminum ash.

A look-up-table development to facilitate CT simulation of MR-Linac treatment.

While current MR-Linac (MRL) treatment workflows utilize a large table overlay during CT simulation to convert indexing between the two machines, we developed a look-up-table (LUT) as an alternative approach. After populating the LUT, index conversion factors were verified at three separate table locations. The resultant root-mean-square isocenter shifts on the MRL were 0.04/0.08 cm, 0.08/0.07 cm, and 0.09/0.08 cm with/without using the table overlay during simulation in the lateral, longitudinal, and vertical directions, respectively, which is within registration tolerance. Clinical implementation of the LUT has resulted in a more efficient MRL treatment workflow while maintaining accurate patient setup.

Severe Lymphopenia During Chemoradiation Therapy for Esophageal Cancer: Comprehensive Analysis of Randomized Phase 2B Trial of Proton Beam Therapy Versus Intensity Modulated Radiation Therapy.

PURPOSE: Lymphocytes play an important role in antitumor immunity; however, they are also especially vulnerable to depletion during chemoradiation therapy (CRT). The purpose of this study was to compare the incidence of grade 4 lymphopenia (G4L) between proton beam therapy (PBT) and intensity modulated photon radiation therapy (IMRT) in patients with esophageal cancer treated with CRT in a completed randomized trial and to ascertain patient heterogeneity to G4L risk based on treatment and established prognostic factors. METHODS AND MATERIALS: Between April 2012 and March 2019, a single-institution, open-label, nonblinded, phase 2 randomized trial (NCT01512589) was conducted at the University of Texas MD Anderson Cancer Center. Patients were randomly assigned to IMRT or PBT, either definitively or preoperatively. This secondary analysis of the randomized trial was G4L during concurrent CRT according to Common Terminology Criteria for Adverse Events version 5.0. RESULTS: Among 105 patients evaluable for analysis, 44 patients (42%) experienced G4L at a median of 28 days after the start date of concurrent CRT. Induction chemotherapy (P = .003), baseline absolute lymphocyte count (P < .001), radiation therapy modality (P = .002), and planning treatment volume (P = .033) were found to be significantly associated with G4L. Multivariate classification analysis partitioned patients into 5 subgroups for whom the incidence of G4L was observed in 0%, 14%, 35%, 70%, and 100% of patients. The benefit of PBT over IMRT was most pronounced in patients with an intermediate baseline absolute lymphocyte count and large planning treatment volume (P = .011). CONCLUSIONS: This is the first prospective evidence that limiting dose scatter by PBT significantly reduced the incidence of G4L, especially in the intermediate-risk patients. The implication of this immune-sparing effect of PBT, especially in the context of standard adjuvant immunotherapy, needs further examination in the current phase 3 randomized trials.

Deep learning-based automatic segmentation of cardiac substructures for lung cancers.

PURPOSE: Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning-based auto-segmentation models for cardiac substructures. MATERIALS AND METHODS: Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. The auto-segmented contours were evaluated by comparing them with manually drawn contours in terms of Dice similarity coefficient (DSC) and dose metrics extracted from clinical plans. An independent dataset of 42 patients was used for subjective evaluation of the auto-segmentation model by 4 physicians. RESULTS: The average DSCs were 0.95 (+/- 0.01) for the whole heart, 0.91 (+/- 0.02) for 4 chambers, 0.86 (+/- 0.09) for 6 great vessels, 0.81 (+/- 0.09) for 4 valves, and 0.60 (+/- 0.14) for 4 coronary arteries. The average absolute errors in mean/max doses to all substructures were 1.04 (+/- 1.99) Gy and 2.20 (+/- 4.37) Gy. The subjective evaluation revealed that 94% of the auto-segmented contours were clinically acceptable. CONCLUSION: We demonstrated the effectiveness of our nnU-Net model for delineating cardiac substructures, including coronary arteries. Our results indicate that this model has promise for studies regarding radiation dose to cardiac substructures.

Fully-automated, CT-only GTV contouring for palliative head and neck radiotherapy.

Planning for palliative radiotherapy is performed without the advantage of MR or PET imaging in many clinics. Here, we investigated CT-only GTV delineation for palliative treatment of head and neck cancer. Two multi-institutional datasets of palliative-intent treatment plans were retrospectively acquired: a set of 102 non-contrast-enhanced CTs and a set of 96 contrast-enhanced CTs. The nnU-Net auto-segmentation network was chosen for its strength in medical image segmentation, and five approaches separately trained: (1) heuristic-cropped, non-contrast images with a single GTV channel, (2) cropping around a manually-placed point in the tumor center for non-contrast images with a single GTV channel, (3) contrast-enhanced images with a single GTV channel, (4) contrast-enhanced images with separate primary and nodal GTV channels, and (5) contrast-enhanced images along with synthetic MR images with separate primary and nodal GTV channels. Median Dice similarity coefficient ranged from 0.6 to 0.7, surface Dice from 0.30 to 0.56, and 95th Hausdorff distance from 14.7 to 19.7 mm across the five approaches. Only surface Dice exhibited statistically-significant difference across these five approaches using a two-tailed Wilcoxon Rank-Sum test (p ≤ 0.05). Our CT-only results met or exceeded published values for head and neck GTV autocontouring using multi-modality images. However, significant edits would be necessary before clinical use in palliative radiotherapy.

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources.

Access to radiotherapy worldwide is limited. The Radiation Planning Assistant (RPA) is a fully automated, web-based tool that is being developed to offer fully automated radiotherapy treatment planning tools to clinics with limited resources. The goal is to help clinical teams scale their efforts, thus reaching more patients with cancer. The user connects to the RPA via a webpage, completes a Service Request (prescription and information about the radiotherapy targets), and uploads the patient's CT image set. The RPA offers two approaches to automated planning. In one-step planning, the system uses the Service Request and CT scan to automatically generate the necessary contours and treatment plan. In two-step planning, the user reviews and edits the automatically generated contours before the RPA continues to generate a volume-modulated arc therapy plan. The final plan is downloaded from the RPA website and imported into the user's local treatment planning system, where the dose is recalculated for the locally commissioned linac; if necessary, the plan is edited prior to approval for clinical use.

Characteristics of solid waste from common generation source in nonferrous smelting industry reveal a new classification method.

Solid waste produced by the nonferrous smelting industry has a significant number of notable differences. The lack of recognition of solid waste characteristics is the main factor restricting its disposal and utilization. In this study, we analyzed the main production processes of the nonferrous smelting industry; identified the key production nodes of solid waste; and clarified the characteristics, including the physical, chemical, and pollution characteristics of solid wastes, through a large sample statistical analysis. We found similarities among solid wastes from a common generation source as well as notable differences among the different generation sources: slags and sludges from waste acid treatment and wastewater treatment units had a water content of 27.43-52.71% and 51.14-68.27%, respectively, which were significantly higher than those of other metallurgy and dust collection units; the pH of slags from an electrorefining unit was strongly alkaline; the mineral phase of sludges from wastewater treatment was only calcite; slags from a waste acid treatment unit were mainly in phase of gypsum, claudetite, and anglesite; the chemical composition of slags from pyrometallurgy and hydrometallurgy units was mainly SiO2 and Fe2O3. In this paper, we discuss a new classification method based on a common generation source for the first time. These results are beneficial to guide the disposal, utilization, and management of solid waste.

A real-time contouring feedback tool for consensus-based contour training.

Purpose: Variability in contouring structures of interest for radiotherapy continues to be challenging. Although training can reduce such variability, having radiation oncologists provide feedback can be impractical. We developed a contour training tool to provide real-time feedback to trainees, thereby reducing variability in contouring. Methods: We developed a novel metric termed localized signed square distance (LSSD) to provide feedback to the trainee on how their contour compares with a reference contour, which is generated real-time by combining trainee contour and multiple expert radiation oncologist contours. Nine trainees performed contour training by using six randomly assigned training cases that included one test case of the heart and left ventricle (LV). The test case was repeated 30 days later to assess retention. The distribution of LSSD maps of the initial contour for the training cases was combined and compared with the distribution of LSSD maps of the final contours for all training cases. The difference in standard deviations from the initial to final LSSD maps, ΔLSSD, was computed both on a per-case basis and for the entire group. Results: For every training case, statistically significant ΔLSSD were observed for both the heart and LV. When all initial and final LSSD maps were aggregated for the training cases, before training, the mean LSSD ([range], standard deviation) was -0.8 mm ([-37.9, 34.9], 4.2) and 0.3 mm ([-25.1, 32.7], 4.8) for heart and LV, respectively. These were reduced to -0.1 mm ([-16.2, 7.3], 0.8) and 0.1 mm ([-6.6, 8.3], 0.7) for the final LSSD maps during the contour training sessions. For the retention case, the initial and final LSSD maps of the retention case were aggregated and were -1.5 mm ([-22.9, 19.9], 3.4) and -0.2 mm ([-4.5, 1.5], 0.7) for the heart and 1.8 mm ([-16.7, 34.5], 5.1) and 0.2 mm ([-3.9, 1.6],0.7) for the LV. Conclusions: A tool that uses real-time contouring feedback was developed and successfully used for contour training of nine trainees. In all cases, the utility was able to guide the trainee and ultimately reduce the variability of the trainee's contouring.

Identifying the optimal deep learning architecture and parameters for automatic beam aperture definition in 3D radiotherapy.

PURPOSE: Two-dimensional radiotherapy is often used to treat cervical cancer in low- and middle-income countries, but treatment planning can be challenging and time-consuming. Neural networks offer the potential to greatly decrease planning time through automation, but the impact of the wide range of hyperparameters to be set during training on model accuracy has not been exhaustively investigated. In the current study, we evaluated the effect of several convolutional neural network architectures and hyperparameters on 2D radiotherapy treatment field delineation. METHODS: Six commonly used deep learning architectures were trained to delineate four-field box apertures on digitally reconstructed radiographs for cervical cancer radiotherapy. A comprehensive search of optimal hyperparameters for all models was conducted by varying the initial learning rate, image normalization methods, and (when appropriate) convolutional kernel size, the number of learnable parameters via network depth and the number of feature maps per convolution, and nonlinear activation functions. This yielded over 1700 unique models, which were all trained until performance converged and then tested on a separate dataset. RESULTS: Of all hyperparameters, the choice of initial learning rate was most consistently significant for improved performance on the test set, with all top-performing models using learning rates of 0.0001. The optimal image normalization was not consistent across architectures. High overlap (mean Dice similarity coefficient = 0.98) and surface distance agreement (mean surface distance < 2 mm) were achieved between the treatment field apertures for all architectures using the identified best hyperparameters. Overlap Dice similarity coefficient (DSC) and distance metrics (mean surface distance and Hausdorff distance) indicated that DeepLabv3+ and D-LinkNet architectures were least sensitive to initial hyperparameter selection. CONCLUSION: DeepLabv3+ and D-LinkNet are most robust to initial hyperparameter selection. Learning rate, nonlinear activation function, and kernel size are also important hyperparameters for improving performance.

Multi-constraint point set registration with redundant point removal for the registration of coronary arteries.

BACKGROUND: Coronary artery disease (CAD) is the leading cause of death worldwide. The registration of the coronary artery at different phases can help radiologists explore the motion patterns of the coronary artery and assist in the diagnosis of CAD. However, there is no automatic and easy-to-execute method to solve the missing data problem that occurs at the endpoints of the coronary artery tree. This paper proposed a non-rigid multi-constraint point set registration with redundant point removal (MPSR-RPR) algorithm to tackle this challenge. METHODS: Firstly, the MPSR-RPR algorithm roughly registered two coronary artery point sets with the pre-set smoothness regularization parameter and Gaussian filter width value. The moving coherent, local feature, and the corresponding relationship between bifurcation point pairs were exploited as the constraints. Next, the spatial geometry information of the coronary artery was utilized to automatically recognize the vessel endpoints and to delete the redundant points of the coronary artery. Finally, the algorithm continued carrying out the multi-constraint registration with another group of the pre-set parameters to improve the alignment performance. RESULTS: The experimental results demonstrated that the MPSR-RPR algorithm achieved a significantly lower mean value of the modified Hausdorff distance (MHD) compared to the other state-of-the-art methods for addressing the serious missing data in the left and right coronary arteries. CONCLUSION: This study demonstrated the effectiveness of the proposed algorithm in aligning coronary arteries, providing significant value in assisting in the diagnosis of coronary artery and myocardial lesions.

Free radical formation via BDE-209 thermolysis in the precalciner of a cement kiln: Simulation and DFT study.

To deeply understand the formation mechanism of polybrominated dibenzo-p-dioxins/furans (PBDD/Fs) in the thermal disposal process of polybrominated diphenyl ether (PBDE)-containing waste, this paper studied the formation pathways of key intermediates (free radicals, FRs) in the formation process of PBDD/Fs. BDE-209, the most common PBDE in the environment, was selected as the object of study to analyze FR formation by simulating the key conditions such as temperature (850 °C) and Fe-based materials when PBDE-containing waste entering cement kiln precalciner. Electron paramagnetic resonance (EPR) spectroscopy and density functional theory (DFT) calculations were used to study the reaction. The result of simulation experiments revealed carbon-centered radicals, and DMPO-OH analysis further confirmed the generation of FRs. The findings confirmed previous calculations predicting the existence of radical intermediates during the formation of PBDD/Fs from BDE-209. DFT calculations revealed the existence of an inner ortho-position CBr bond in BDE-209. The priority order of the bond breaking of BDE-209 was ether bond, inner ortho-position CBr bond, and outside ortho-position CBr bond. BDE-209 can further form three kinds of FRs, namely, oxygen-centered radicals of single benzene rings, carbon-centered radicals of single benzene rings, and carbon-centered radicals of double benzene rings. The specific processes of FR formation were inferred: high-temperature homogeneous cleavage of chemical bonds, electron transfer, and chemisorption, where electron transfer and chemisorption may be more important pathways. The proposed inner ortho-position cleavage within BDE-209 provides new insights into the degradation of PBDEs and the formation of PBDD/Fs; the results regarding BDE-209 generation radicals further elucidate the synthesis mechanism of dioxins, which is important for controlling dioxin generation and emission during the treatment and disposal of waste containing PBDEs.

A transformer-based hierarchical registration framework for multimodality deformable image registration.

Deformable image registration (DIR) between daily and reference images is fundamentally important for adaptive radiotherapy. In the last decade, deep learning-based image registration methods have been developed with faster computation time and improved robustness compared to traditional methods. However, the registration performance is often degraded in extra-cranial sites with large volume containing multiple anatomic regions, such as Computed Tomography (CT)/Magnetic Resonance (MR) images used in head and neck (HN) radiotherapy. In this study, we developed a hierarchical deformable image registration (DIR) framework, Patch-based Registration Network (Patch-RegNet), to improve the accuracy and speed of CT-MR and MR-MR registration for head-and-neck MR-Linac treatments. Patch-RegNet includes three steps: a whole volume global registration, a patch-based local registration, and a patch-based deformable registration. Following a whole-volume rigid registration, the input images were divided into overlapping patches. Then a patch-based rigid registration was applied to achieve accurate local alignment for subsequent DIR. We developed a ViT-Morph model, a combination of a convolutional neural network (CNN) and the Vision Transformer (ViT), for the patch-based DIR. A modality independent neighborhood descriptor was adopted in our model as the similarity metric to account for both inter-modality and intra-modality registration. The CT-MR and MR-MR DIR models were trained with 242 CT-MR and 213 MR-MR image pairs from 36 patients, respectively, and both tested with 24 image pairs (CT-MR and MR-MR) from 6 other patients. The registration performance was evaluated with 7 manually contoured organs (brainstem, spinal cord, mandible, left/right parotids, left/right submandibular glands) by comparing with the traditional registration methods in Monaco treatment planning system and the popular deep learning-based DIR framework, Voxelmorph. Evaluation results show that our method outperformed VoxelMorph by 6 % for CT-MR registration, and 4 % for MR-MR registration based on DSC measurements. Our hierarchical registration framework has been demonstrated achieving significantly improved DIR accuracy of both CT-MR and MR-MR registration for head-and-neck MR-guided adaptive radiotherapy.

Addressing the Global Expertise Gap in Radiation Oncology: The Radiation Planning Assistant.

PURPOSE: Automation, including the use of artificial intelligence, has been identified as a possible opportunity to help reduce the gap in access and quality for radiotherapy and other aspects of cancer care. The Radiation Planning Assistant (RPA) project was conceived in 2015 (and funded in 2016) to use automated contouring and treatment planning algorithms to support the efforts of oncologists in low- and middle-income countries, allowing them to scale their efforts and treat more patients safely and efficiently (to increase access). DESIGN: In this review, we discuss the development of the RPA, with a particular focus on clinical acceptability and safety/risk across jurisdictions as these are important indicators for the successful future deployment of the RPA to increase radiotherapy availability and ameliorate global disparities in access to radiation oncology. RESULTS: RPA tools will be offered through a webpage, where users can upload computed tomography data sets and download automatically generated contours and treatment plans. All interfaces have been designed to maximize ease of use and minimize risk. The current version of the RPA includes automated contouring and planning for head and neck cancer, cervical cancer, breast cancer, and metastases to the brain. CONCLUSION: The RPA has been designed to bring high-quality treatment planning to more patients across the world, and it may encourage greater investment in treatment devices and other aspects of cancer treatment.

Longitudinal diffusion and volumetric kinetics of head and neck cancer magnetic resonance on a 1.5T MR-Linear accelerator hybrid system: A prospective R-IDEAL Stage 2a imaging biomarker characterization/ pre-qualification study.

Objectives: We aim to characterize the serial quantitative apparent diffusion coefficient (ADC) changes of the target disease volume using diffusion-weighted imaging (DWI) acquired weekly during radiation therapy (RT) on a 1.5T MR-Linac and correlate these changes with tumor response and oncologic outcomes for head and neck squamous cell carcinoma (HNSCC) patients as part of a programmatic R-IDEAL biomarker characterization effort. Methods: Thirty patients with pathologically confirmed HNSCC who received curative-intent RT at the University of Texas MD Anderson Cancer Center, were included in this prospective study. Baseline and weekly Magnetic resonance imaging (MRI) (weeks 1-6) were obtained, and various ADC parameters (mean, 5 th , 10 th , 20 th , 30 th , 40 th , 50 th , 60 th , 70 th , 80 th , 90 th and 95 th percentile) were extracted from the target regions of interest (ROIs). Baseline and weekly ADC parameters were correlated with response during RT, loco-regional control, and the development of recurrence using the Mann-Whitney U test. The Wilcoxon signed-rank test was used to compare the weekly ADC versus baseline values. Weekly volumetric changes (Δvolume) for each ROI were correlated with ΔADC using Spearman's Rho test. Recursive partitioning analysis (RPA) was performed to identify the optimal ΔADC threshold associated with different oncologic outcomes. Results: There was an overall significant rise in all ADC parameters during different time points of RT compared to baseline values for both gross primary disease volume (GTV-P) and gross nodal disease volumes (GTV-N). The increased ADC values for GTV-P were statistically significant only for primary tumors achieving complete remission (CR) during RT. RPA identified GTV-P ΔADC 5 th percentile >13% at the 3 rd week of RT as the most significant parameter associated with CR for primary tumor during RT (p <0.001). Baseline ADC parameters for GTV-P and GTV-N didn't significantly correlate with response to RT or other oncologic outcomes. There was a significant decrease in residual volume of both GTV-P & GTV-N throughout the course of RT. Additionally, a significant negative correlation between mean ΔADC and Δvolume for GTV-P at the 3 rd and 4 th week of RT was detected (r = -0.39, p = 0.044 & r = -0.45, p = 0.019, respectively). Conclusion: Assessment of ADC kinetics at regular intervals throughout RT seems to be correlated with RT response. Further studies with larger cohorts and multi-institutional data are needed for validation of ΔADC as a model for prediction of response to RT.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Pulmonary arteries segmentation from CT images using PA-Net with attention module and contour loss.

BACKGROUND: Pulmonary embolism is a kind of cardiovascular disease that threatens human life and health. Since pulmonary embolism exists in the pulmonary artery, improving the segmentation accuracy of pulmonary artery is the key to the diagnosis of pulmonary embolism. Traditional medical image segmentation methods have limited effectiveness in pulmonary artery segmentation. In recent years, deep learning methods have been gradually adopted to solve complex problems in the field of medical image segmentation. PURPOSE: Due to the irregular shape of the pulmonary artery and the adjacent-complex tissues, the accuracy of the existing pulmonary artery segmentation methods based on deep learning needs to be improved. Therefore, the purpose of this paper is to develop a segmentation network, which can obtain higher segmentation accuracy and further improve the diagnosis effect. METHODS: In this study, the pulmonary artery segmentation performance from the network model and loss function is improved, proposing a pulmonary artery segmentation network (PA-Net) to segment the pulmonary artery region from 2D CT images. Reverse Attention and edge attention are used to enhance the expression ability of the boundary. In addition, to better use feature information, the channel attention module is introduced in the decoder to highlight the important channel features and suppress the unimportant channels. Due to blurred boundaries, pixels near the boundaries of the pulmonary artery may be difficult to segment. Therefore, a new contour loss function based on the active contour model is proposed in this study to segment the target region by assigning dynamic weights to false positive and false negative regions and accurately predict the boundary structure. RESULTS: The experimental results show that the segmentation accuracy of this proposed method is significantly improved in comparison with state-of-the-art segmentation methods, and the Dice coefficient is 0.938 ± 0.035, which is also confirmed from the 3D reconstruction results. CONCLUSIONS: Our proposed method can accurately segment pulmonary artery structure. This new development will provide the possibility for further rapid diagnosis of pulmonary artery diseases such as pulmonary embolism. Code is available at https://github.com/Yuanyan19/PA-Net.

Compensation cycle consistent generative adversarial networks (Comp-GAN) for synthetic CT generation from MR scans with truncated anatomy.

BACKGROUND: MR scans used in radiotherapy can be partially truncated due to the limited field of view (FOV), affecting dose calculation accuracy in MR-based radiation treatment planning. PURPOSE: We proposed a novel Compensation-cycleGAN (Comp-cycleGAN) by modifying the cycle-consistent generative adversarial network (cycleGAN), to simultaneously create synthetic CT (sCT) images and compensate the missing anatomy from the truncated MR images. METHODS: Computed tomography (CT) and T1 MR images with complete anatomy of 79 head-and-neck patients were used for this study. The original MR images were manually cropped 10-25 mm off at the posterior head to simulate clinically truncated MR images. Fifteen patients were randomly chosen for testing and the rest of the patients were used for model training and validation. Both the truncated and original MR images were used in the Comp-cycleGAN training stage, which enables the model to compensate for the missing anatomy by learning the relationship between the truncation and known structures. After the model was trained, sCT images with complete anatomy can be generated by feeding only the truncated MR images into the model. In addition, the external body contours acquired from the CT images with full anatomy could be an optional input for the proposed method to leverage the additional information of the actual body shape for each test patient. The mean absolute error (MAE) of Hounsfield units (HU), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) were calculated between sCT and real CT images to quantify the overall sCT performance. To further evaluate the shape accuracy, we generated the external body contours for sCT and original MR images with full anatomy. The Dice similarity coefficient (DSC) and mean surface distance (MSD) were calculated between the body contours of sCT and original MR images for the truncation region to assess the anatomy compensation accuracy. RESULTS: The average MAE, PSNR, and SSIM calculated over test patients were 93.1 HU/91.3 HU, 26.5 dB/27.4 dB, and 0.94/0.94 for the proposed Comp-cycleGAN models trained without/with body-contour information, respectively. These results were comparable with those obtained from the cycleGAN model which is trained and tested on full-anatomy MR images, indicating the high quality of the sCT generated from truncated MR images by the proposed method. Within the truncated region, the mean DSC and MSD were 0.85/0.89 and 1.3/0.7 mm for the proposed Comp-cycleGAN models trained without/with body contour information, demonstrating good performance in compensating the truncated anatomy. CONCLUSIONS: We developed a novel Comp-cycleGAN model that can effectively create sCT with complete anatomy compensation from truncated MR images, which could potentially benefit the MRI-based treatment planning.