Automatic IMRT treatment planning through fluence prediction and plan fine-tuning for nasopharyngeal carcinoma.

BACKGROUND: At present, the implementation of intensity-modulated radiation therapy (IMRT) treatment planning for geometrically complex nasopharyngeal carcinoma (NPC) through manual trial-and-error fashion presents challenges to the improvement of planning efficiency and the obtaining of high-consistency plan quality. This paper aims to propose an automatic IMRT plan generation method through fluence prediction and further plan fine-tuning for patients with NPC and evaluates the planning efficiency and plan quality. METHODS: A total of 38 patients with NPC treated with nine-beam IMRT were enrolled in this study and automatically re-planned with the proposed method. A trained deep learning model was employed to generate static field fluence maps for each patient with 3D computed tomography images and structure contours as input. Automatic IMRT treatment planning was achieved by using its generated dose with slight tightening for further plan fine-tuning. Lastly, the plan quality was compared between automatic plans and clinical plans. RESULTS: The average time for automatic plan generation was less than 4 min, including fluence maps prediction with a python script and automated plan tuning with a C# script. Compared with clinical plans, automatic plans showed better conformity and homogeneity for planning target volumes (PTVs) except for the conformity of PTV-1. Meanwhile, the dosimetric metrics for most organs at risk (OARs) were ameliorated in the automatic plan, especially Dmax of the brainstem and spinal cord, and Dmean of the left and right parotid glands significantly decreased (P < 0.05). CONCLUSION: We have successfully implemented an automatic IMRT plan generation method for patients with NPC. This method shows high planning efficiency and comparable or superior plan quality than clinical plans. The qualitative results before and after the plan fine-tuning indicates that further optimization using dose objectives generated by predicted fluence maps is crucial to obtain high-quality automatic plans.

Anti-GM-CSF autoantibodies predict outcome of cryptococcal meningitis in patients not infected with HIV: A cohort study.

OBJECTIVES: To explore the seroprevalence of anti-granulocyte-macrophage colony-stimulating factor (GM-CSF) autoantibodies in non-HIV cryptococcal meningitis (CM) and assess its predictive value for survival. METHODS: This is a retrospective study of 12 years of non-HIV CM. We detected serum anti-GM-CSF autoantibodies, and evaluated the clinical features and outcomes, together with the exploration of prognostic factors for 2-week and 1-year survival. RESULTS: A total of 584 non-HIV CM cases were included. 301 of 584 patients (51.5%) were phenotypically healthy. 264 Cryptococcus isolates were obtained from cerebrospinal fluid (CSF) culture, of which 251 were identified as C. neoformans species complex and 13 as C. gattii species complex. Thirty-seven of 455 patients (8.1%) tested positive for serum anti-GM-CSF autoantibodies. Patients with anti-GM-CSF autoantibodies were more susceptible to C. gattii species complex infection (66.7% vs. 6.3%; p < 0.001) and more likely to develop pulmonary mass lesions with a diameter >3 centimetres (42.9% vs. 6.5%; p 0.001). Of 584 patients 16 (2.7%) died within 2 weeks, 77 of 563 patients (13.7%) died at 1 year, and 93 of 486 patients (19.1%) lived with disabilities at 1 year. Univariant Cox regression analysis found that anti-GM-CSF autoantibodies were associated with lower 1-year survival (HR, 2.66; 95% CI, 1.34-5.27; p 0.005). Multivariable Cox proportional hazards modelling revealed that CSF cryptococcal antigen titres ≥1:1280 were associated with both, reduced 2-week and 1-year survival rates (HR, 5.44; 95% CI, 1.23-24.10; p 0.026 and HR, 5.09; 95% CI, 1.95-13.26; p 0.001). DISCUSSION: Presence of serum anti-GM-CSF autoantibodies is predictive of poor outcomes, regardless of host immune status and the causative Cryptococcus species complex.

Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study.

BACKGROUND: Ovarian cancer is the most lethal gynecological malignancy. Timely diagnosis of ovarian cancer is difficult due to the lack of effective biomarkers. Laboratory tests are widely applied in clinical practice, and some have shown diagnostic and prognostic relevance to ovarian cancer. We aimed to systematically evaluate the value of routine laboratory tests on the prediction of ovarian cancer, and develop a robust and generalisable ensemble artificial intelligence (AI) model to assist in identifying patients with ovarian cancer. METHODS: In this multicentre, retrospective cohort study, we collected 98 laboratory tests and clinical features of women with or without ovarian cancer admitted to three hospitals in China during Jan 1, 2012 and April 4, 2021. A multi-criteria decision making-based classification fusion (MCF) risk prediction framework was used to make a model that combined estimations from 20 AI classification models to reach an integrated prediction tool developed for ovarian cancer diagnosis. It was evaluated on an internal validation set (3007 individuals) and two external validation sets (5641 and 2344 individuals). The primary outcome was the prediction accuracy of the model in identifying ovarian cancer. FINDINGS: Based on 52 features (51 laboratory tests and age), the MCF achieved an area under the receiver-operating characteristic curve (AUC) of 0·949 (95% CI 0·948-0·950) in the internal validation set, and AUCs of 0·882 (0·880-0·885) and 0·884 (0·882-0·887) in the two external validation sets. The model showed higher AUC and sensitivity compared with CA125 and HE4 in identifying ovarian cancer, especially in patients with early-stage ovarian cancer. The MCF also yielded acceptable prediction accuracy with the exclusion of highly ranked laboratory tests that indicate ovarian cancer, such as CA125 and other tumour markers, and outperformed state-of-the-art models in ovarian cancer prediction. The MCF was wrapped as an ovarian cancer prediction tool, and made publicly available to provide estimated probability of ovarian cancer with input laboratory test values. INTERPRETATION: The MCF model consistently achieved satisfactory performance in ovarian cancer prediction when using laboratory tests from the three validation sets. This model offers a low-cost, easily accessible, and accurate diagnostic tool for ovarian cancer. The included laboratory tests, not only CA125 which was the highest ranked laboratory test in importance of diagnostic assistance, contributed to the characterisation of patients with ovarian cancer. FUNDING: Ministry of Science and Technology of China; National Natural Science Foundation of China; Natural Science Foundation of Guangdong Province, China; and Science and Technology Project of Guangzhou, China. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

PND-Net: Physics-Inspired Non-Local Dual-Domain Network for Metal Artifact Reduction.

Metal artifacts caused by the presence of metallic implants tremendously degrade the quality of reconstructed computed tomography (CT) images and therefore affect the clinical diagnosis or reduce the accuracy of organ delineation and dose calculation in radiotherapy. Although various deep learning methods have been proposed for metal artifact reduction (MAR), most of them aim to restore the corrupted sinogram within the metal trace, which removes beam hardening artifacts but ignores other components of metal artifacts. In this paper, based on the physical property of metal artifacts which is verified via Monte Carlo (MC) simulation, we propose a novel physics-inspired non-local dual-domain network (PND-Net) for MAR in CT imaging. Specifically, we design a novel non-local sinogram decomposition network (NSD-Net) to acquire the weighted artifact component and develop an image restoration network (IR-Net) to reduce the residual and secondary artifacts in the image domain. To facilitate the generalization and robustness of our method on clinical CT images, we employ a trainable fusion network (F-Net) in the artifact synthesis path to achieve unpaired learning. Furthermore, we design an internal consistency loss to ensure the data fidelity of anatomical structures in the image domain and introduce the linear interpolation sinogram as prior knowledge to guide sinogram decomposition. NSD-Net, IR-Net, and F-Net are jointly trained so that they can benefit from one another. Extensive experiments on simulation and clinical data demonstrate that our method outperforms state-of-the-art MAR methods.

A predicted three-dimensional dose sequence based treatment planning optimization method for gynecologic IMRT.

In knowledge-based treatment planning (KBTP) for intensity-modulated radiation therapy (IMRT), the quality of the plan is dependent on the sophistication of the predicted dosimetric information and its application. In this paper, we propose a KBTP method that based on the effective and reasonable utilization of a three-dimensional (3D) dose prediction on planning optimization. We used an organs-at-risk (OARs) dose distribution prediction model to create a voxel-based dose sequence based optimization objective for OARs doses. This objective was used to reformulate a traditional fluence map optimization model, which involves a tolerable spatial re-assignment of the predicted dose distribution to the OAR voxels based on their current doses' positions at a sorted dose sequencing. The feasibility of this method was evaluated with ten gynecology (GYN) cancer IMRT cases by comparing its generated plan quality with the original clinical plan. Results showed feasible plan by proposed method, with comparable planning target volume (PTV) dose coverage and greater dose sparing of the OARs. Among ten GYN cases, the average V30 and V45 of rectum were decreased by 4%±4% (p = 0.02) and 4%±3% (p<0.01), respectively. V30 and V45 of bladder were decreased by 8%±2% (p<0.01) and 3%±2% (p<0.01), respectively. Our predicted dose sequence-based planning optimization method for GYN IMRT offered a flexible use of predicted 3D doses while ensuring the output plan consistency.

Simultaneous dose distribution and fluence prediction for nasopharyngeal carcinoma IMRT.

BACKGROUND: Current intensity-modulated radiation therapy (IMRT) treatment planning is still a manual and time/resource consuming task, knowledge-based planning methods with appropriate predictions have been shown to enhance the plan quality consistency and improve planning efficiency. This study aims to develop a novel prediction framework to simultaneously predict dose distribution and fluence for nasopharyngeal carcinoma treated with IMRT, the predicted dose information and fluence can be used as the dose objectives and initial solution for an automatic IMRT plan optimization scheme, respectively. METHODS: We proposed a shared encoder network to simultaneously generate dose distribution and fluence maps. The same inputs (three-dimensional contours and CT images) were used for both dose distribution and fluence prediction. The model was trained with datasets of 340 nasopharyngeal carcinoma patients (260 cases for training, 40 cases for validation, 40 cases for testing) treated with nine-beam IMRT. The predicted fluence was then imported back to treatment planning system to generate the final deliverable plan. Predicted fluence accuracy was quantitatively evaluated within projected planning target volumes in beams-eye-view with 5 mm margin. The comparison between predicted doses, predicted fluence generated doses and ground truth doses were also conducted inside patient body. RESULTS: The proposed network successfully predicted similar dose distribution and fluence maps compared with ground truth. The quantitative evaluation showed that the pixel-based mean absolute error between predicted fluence and ground truth fluence was 0.53% ± 0.13%. The structural similarity index also showed high fluence similarity with values of 0.96 ± 0.02. Meanwhile, the difference in the clinical dose indices for most structures between predicted dose, predicted fluence generated dose and ground truth dose were less than 1 Gy. As a comparison, the predicted dose achieved better target dose coverage and dose hot spot than predicted fluence generated dose compared with ground truth dose. CONCLUSION: We proposed an approach to predict 3D dose distribution and fluence maps simultaneously for nasopharyngeal carcinoma patients. Hence, the proposed method can be potentially integrated in a fast automatic plan generation scheme by using predicted dose as dose objectives and predicted fluence as a warm start.

A transmission measurement-based spectrum estimation method incorporating X-ray tube voltage fluctuation.

Background: The energy spectrum is the property of the X-ray tube that describes the energy fluence per unit interval of photon energy. The existing indirect methods for estimating the spectrum ignore the influence caused by the voltage fluctuation of the X-ray tube. Methods: In this work, we propose a method for estimating the X-ray energy spectrum more accurately by including the voltage fluctuation of the X-ray tube. It expresses the spectrum as the weighted summation of a set of model spectra within a certain voltage fluctuation range. The difference between the raw projection and the estimated projection is considered as the objective function for obtaining the corresponding weight of each model spectrum. The equilibrium optimizer (EO) algorithm is used to find the weight combination that minimizes the objective function. Finally, the estimated spectrum is obtained. We refer to the proposed method as the poly-voltage method. The method is mainly aimed at the cone-beam computed tomography (CBCT) system. Results: The model spectra mixture evaluation and projection evaluation showed that the reference spectrum can be combined by multiple model spectra. They also showed that it is appropriate to choose about 10% of the preset voltage as the voltage range of the model spectra, which can match the reference spectrum and projection quite well. The phantom evaluation showed that the beam-hardening artifact can be corrected using the estimated spectrum via the poly-voltage method, and the poly-voltage method provides not only the accurate reprojection but also an accurate spectrum. The normalized root mean square error (NRMSE) index between the spectrum generated via the poly-voltage method and the reference spectrum could be kept within 3% according to above evaluations. There existed a 1.77% percentage error between the estimated scatter of polymethyl methacrylate (PMMA) phantom using the two spectra generated via the poly-voltage method and the single-voltage method, and it could be considered for scatter simulation. Conclusions: Our proposed poly-voltage method could estimate the spectrum more accurately for both ideal and more realistic voltage spectra, and it is robust to the different modes of voltage pulse.

Multimodality MRI synchronous construction based deep learning framework for MRI-guided radiotherapy synthetic CT generation.

Synthesizing computed tomography (CT) images from magnetic resonance imaging (MRI) data can provide the necessary electron density information for accurate dose calculation in the treatment planning of MRI-guided radiation therapy (MRIgRT). Inputting multimodality MRI data can provide sufficient information for accurate CT synthesis: however, obtaining the necessary number of MRI modalities is clinically expensive and time-consuming. In this study, we propose a multimodality MRI synchronous construction based deep learning framework from a single T1-weight (T1) image for MRIgRT synthetic CT (sCT) image generation. The network is mainly based on a generative adversarial network with sequential subtasks of intermediately generating synthetic MRIs and jointly generating the sCT image from the single T1 MRI. It contains a multitask generator and a multibranch discriminator, where the generator consists of a shared encoder and a splitted multibranch decoder. Specific attention modules are designed within the generator for feasible high-dimensional feature representation and fusion. Fifty patients with nasopharyngeal carcinoma who had undergone radiotherapy and had CT and sufficient MRI modalities scanned (5550 image slices for each modality) were used in the experiment. Results showed that our proposed network outperforms state-of-the-art sCT generation methods well with the least MAE, NRMSE, and comparable PSNR and SSIM index measure. Our proposed network exhibits comparable or even superior performance than the multimodality MRI-based generation method although it only takes a single T1 MRI image as input, thereby providing a more effective and economic solution for the laborious and high-cost generation of sCT images in clinical applications.

Diagnostic Laboratory Features and Performance of an Aspergillus IgG Lateral Flow Assay in a Chronic Pulmonary Aspergillosis Cohort.

Chronic pulmonary aspergillosis (CPA) is a chronic and progressive fungal disease with high morbidity and mortality. Avoiding diagnostic delay and misdiagnosis are concerns for CPA patients. However, diagnostic practice is poorly evaluated, especially in resource-constrained areas where Aspergillus antibody testing tools are lacking. This study aimed to investigate the diagnostic laboratory findings in a retrospective CPA cohort and to evaluate the performance of a novel Aspergillus IgG lateral flow assay (LFA; Era Biology, Tianjin, China). During January 2016 and December 2021, suspected CPA patients were screened at the Center for Infectious Diseases at Huashan Hospital. A total of 126 CPA patients were enrolled. Aspergillus IgG was positive in 72.1% with chronic cavitary pulmonary aspergillosis, 75.0% with chronic necrotizing pulmonary aspergillosis, 41.7% with simple aspergilloma, and 30.3% with Aspergillus nodule(s). The cavitary CPA subtypes had significantly higher levels of Aspergillus IgG. Aspergillus IgG was negative in 52 patients, who were finally diagnosed by histopathology, respiratory culture, and metagenomic next-generation sequencing (mNGS). Sputum culture was positive in 39.3% (42/107) of patients and Aspergillus fumigatus was the most common species (69.0%, 29/42). For CPA cohort versus controls, the sensitivity and specificity of the LFA were 55.6% and 92.7%, respectively. In a subgroup analysis, the LFA was highly sensitive for A. fumigatus-associated chronic cavitary pulmonary aspergillosis (CCPA; 96.2%, 26/27). Given the complexity of the disease, a combination of serological and non-serological tests should be considered to avoid misdiagnosis of CPA. The novel LFA has a satisfactory performance and allows earlier screening and diagnosis of CPA patients. IMPORTANCE There are concerns on avoiding diagnostic delay and misdiagnosis for chronic pulmonary aspergillosis due to its high morbidity and mortality. A proportion of CPA patients test negative for Aspergillus IgG. An optimal diagnostic strategy for CPA requires in-depth investigation based on real-world diagnostic practice, which has been rarely discussed. We summarized the clinical and diagnostic laboratory findings of 126 CPA patients with various CPA subtypes. Aspergillus IgG was the most sensitive test for diagnosing CPA. However, it was negative in 52 patients, who were finally diagnosed by non-serological tests, including biopsy, respiratory culture, and metagenomic next-generation sequencing. We also evaluated a novel Aspergillus IgG lateral flow assay, which showed a satisfactory performance in cavitary CPA patients and was highly specific to Aspergillus fumigatus. This study gives a full picture of the diagnostic practice for CPA patients in Chinese context and calls for early diagnosis of CPA with combined approaches.

Diagnostic performance of noncultural methods for central nervous system aspergillosis.

BACKGROUND: Central nervous system (CNS) aspergillosis is an uncommon but fatal disease, the diagnosis of which is still difficult. OBJECTIVES: We aim to explore the diagnositic performance of noncultural methods for CNS aspergillosis. METHODS: In this retrospective study, all pathologically confirmed rhinosinusitis patients in whom cerebrospinal fluid (CSF) galactomannan (GM) test and metagenomic next-generation sequencing (mNGS) had been performed were included. We evaluated the diagnostic performances of CSF GM optical density indexes (ODI) at different cut-off values and compared performance with mNGS in patients with and without CNS aspergillosis, as well as in patients with different manifestations of CNS aspergillosis. RESULTS: Of the 21 proven and probable cases, one had positive culture result, five had positive mNGS results and 10 had a CSF GM ODI of >0.7. Sample concordance between mNGS and GM test was poor, but best diagnostic performance was achieved by combination of GM test (ODI of >0.7) and mNGS, which generated a sensitivity of 61.9% and specificity of 82.6%. Further investigation of combination diagnostic performances in different kind of CNS aspergillosis was also conducted. Lowest sensitivity (42.9%) was identified in abscess group, while increased sensitivity (60.0%) was achieved in abscess with encephalitis groups. Combination test exhibited the best performance for encephalitis patients who had only CSF abnormalities, in whom the sensitivity and specificity were 77.8% and 82.6%, respectively. CONCLUSIONS: In conclusion, combination of these two tests might be useful for diagnosis of CNS aspergillosis associated with fungal rhinosinusitis, especially in encephalitis patients.

Induction therapy with high-dose fluconazole plus flucytosine for human immunodeficiency virus-uninfected cryptococcal meningitis patients: Feasible or not?

BACKGROUND: Cryptococcal meningitis (CM) is increasingly recognised in human immunodeficiency virus (HIV)-uninfected patients with high mortality. The efficacy and safety profiles of induction therapy with high-dose fluconazole plus flucytosine remain unclear. METHODS: HIV-uninfected CM patients who received high-dose fluconazole (800 mg/d) for initial therapy in Huashan Hospital were included in this retrospective study from January 2013 to December 2018. Efficacy and safety of initial therapy, clinical outcomes and risk factors were evaluated. RESULTS: Twenty-seven (71.1%) patients who received high-dose fluconazole with flucytosine combination therapy and 11 (28.9%) having fluconazole alone for induction therapy were included. With a median duration of 42 days (IQR, 28-86), the successful response rate of initial therapy was 76.3% (29/38), while adverse drug reactions occurred in 14 patients (36.8%). The rate of persistently positive cerebrospinal fluid (CSF) culture results was 30.6% at 2 weeks, which was significantly associated with CSF CrAg titre >1:1280 (OR 9.56; 95% CI 1.40-103.65; p = .010) and CSF culture of Cryptococcus >3.9 log10 CFU/ml (OR 19.20; 95% CI 1.60-920.54; p = .011), and decreased to 8.6% at 4 weeks. One-year mortality was 15.8% (6/38), and low serum albumin (35 g/L) was found as an independent risk factor for 1-year mortality (HR 6.31; 95% CI 1.150-34.632; p = .034). CONCLUSIONS: Induction therapy with high-dose fluconazole (800 mg/d), combined with flucytosine, effectively treated HIV-uninfected CM and was well tolerated. Long-term fluconazole treatment with continued monitoring is beneficial for patients with persistent infection.

Cross-engine transformation-based fast dose calculation for MRI-Linac online treatment planning.

PURPOSE: To propose a novel magnetic field dose calculation method based on transformation from pencil beam (PB) to Monte Carlo (MC) distribution for MRI-Linac online treatment planning. METHODS: The novel magnetic field dose calculation algorithm was established by a PB dose engine and a magnetic field with tissue inhomogeneity influence correction network. The correction network was constructed with a Res-UNet framework, including residual modules and an encoding-decoding path, by inputting three-dimensional PB dose and patient electron density map, and outputting transformed dose distribution. The influences of magnetic fields and tissue heterogeneity were considered and corrected simultaneously in the correction model. A total of 110 clinically treated static beam IMRT plans were collected, including plans for brain, head-and-neck, lung, and rectum cases. A total of 90 cases were used and enhanced to train and validate the model, and the other 20 cases were for test. By comparing the proposed pipeline-generated dose distribution with original input PB dose and corresponding MC dose, the feasibility and effectiveness of the method was evaluated. RESULTS: Results on both beam dose and plan dose accuracy comparisons on all investigated four tumor sites show great consistency between the cross-dose-engine transformation generations and the MC results, with averaged plan mean absolute error of 0.90% ± 0.13% for the voxel-wise dose difference and 98.33% ± 1.07% gamma passing rate at the 2%/2 mm criteria. The whole PB calculation and transformation process can be completed within second. CONCLUSIONS: We have successfully developed a fast novel magnetic field dose calculation pipeline based on transformation from PB distribution to MC distribution for MRI-Linac online treatment planning.

Cerebrospinal fluid cytokine and chemokine patterns correlate with prognosis of HIV-uninfected cryptococcal meningitis: A prospective observational study.

The cerebrospinal fluid (CSF) immune responses in HIV-uninfected cryptococcal meningitis (CM) have not been well studied. In this study, we aimed to explore the phenotype of CSF immune response during the course of disease and to examine relationships between phenotypes and disease severity. We profiled the CSF immune response in 128 HIV-uninfected CM and 30 pulmonary cryptococcosis patients using a 27-plex Luminex cytokine kit. Principal component analyses (PCA) and logistic regression model were performed. Concentrations of 23 out of 27 cytokines and chemokines in baseline CSF were significantly elevated in CM patients compared with pulmonary cryptococcosis cases. In CM patients with Cryptococcus neoformans infection, IL-1ra, IL-9, and VEGF were significantly elevated in immunocompetent cases. Cytokine levels usually reached peaks within the first 2 weeks of antifungal treatment and gradually decreased over time. PCA demonstrated a co-correlated CSF cytokine and chemokine response consisting of Th1, Th2, and Th17 type cytokines. Prognostic analysis showed that higher scores for the PCs loading pro-inflammatory cytokines, IFN-γ, TNF-α, and IL-12; and anti-inflammatory cytokine, IL-4; and chemokines, Eotaxin, FGF-basis, and PDGF-bb; as well as lower scores for the PCs loading RANTES were associated with disease severity, as defined by a Glasgow Coma Scale of <15 or death. In conclusion, combined inflammatory responses in CSF involving both pro- and anti-inflammatory cytokines and chemokines are upregulated in HIV-uninfected CM, and associated with disease severity.

TransDose: a transformer-based UNet model for fast and accurate dose calculation for MR-LINACs.

Objective. To present a transformer-based UNet model (TransDose) for fast and accurate dose calculation for magnetic resonance-linear accelerators (MR-LINACs).Approach. A 2D fluence map from each beam was first projected into a 3D fluence volume and then fed into the TransDose model together with patient density volume and output predicted beam dose. The proposed TransDose model combined a 3D residual UNet with a transformer encoder, where convolutional layers extracted the volumetric spatial features, and the transformer encoder processed the long-range dependencies in a global space. Ninety-eight cases with four tumor sites (brain, nasopharynx, lung, and rectum) treated with fixed-beam intensity-modulated radiotherapy were included in the dataset; 78 cases were used for model training and validation; and 20 cases were used for testing. The ground-truth beam doses were calculated with Monte Carlo (MC) simulations within 1% statistical uncertainty and magnetic field strengthB = 1.5 T in the superior and inferior direction. Beam angles from the training and validation datasets were rotated 2-5 times, and doses were recalculated to augment the datasets.Results. The dose-volume histograms and indices between the predicted and MC doses showed good consistency. The average 3Dγ-passing rates (3%/2 mm, for dose regions above 10% of maximum dose) were 99.13 ± 0.89% (brain), 98.31 ± 1.92% (nasopharynx), 98.74 ± 0.70% (lung), and 99.28 ± 0.25% (rectum). The average dose calculation time, which included the fluence projection and model prediction, was less than 310 ms for each beam.Significance. We successfully developed a transformer-based UNet dose calculation model-TransDose in magnetic fields. Its accuracy and efficiency indicated its potential for use in online adaptive plan optimization for MR-LINACs.

Multisequence MR-generated sCT is promising for HNC MR-only RT: A comprehensive evaluation of previously developed sCT generation networks.

PURPOSE: To verify the feasibility of our in-house developed multisequence magnetic resonance (MR)-generated synthetic computed tomography (sCT) for accurate dose calculation and fractional positioning for head and neck MR-only radiation therapy (RT). METHODS: Forty-five patients with nasopharyngeal carcinoma were retrospectively studied. By applying our previously in-house developed network, a patient's sCT can rapidly be generated with respect to feeding the sole T1 image, T1C image, T1DixonC image, T2 image, and their combination (five pipelines in total). A k(5)-fold strategy was implemented during model establishment. Dose recalculation was performed for each pipeline generation to attain a dosimetric feasibility evaluation. Fractional positioning evaluation was performed by calculating the digitally reconstructed radiograph (DRR) of the sCT and planning CT and their offset to the portal image. RESULTS: The dose mean absolute error values were (0.47±0.16)%, (0.48±0.15)% (p < 0.05), (0.50±0.16)% (p < 0.05), (0.50±0.15)% (p < 0.05), and (0.45±0.16)% (p < 0.05) for the T1, T1C, T1Dixon C, T2, and 4-channel generated sCT to the prescription dose, respectively. The 4-channel-generated sCT outperforms any other single-sequence pipeline. Among the single-sequence MR imaging-generated sCTs, the T1-generated sCT shows the most accurate HU image quality and provides a reliable dose result. Quantified positioning errors with calculation of the difference to the planning CT offsets are (-0.26±0.50) mm, (-0.58±0.52) mm (p < 0.05), (-0.27±0.57) mm (p > 0.05), (-0.31±0.44) mm (p > 0.05), and (-0.19±0.37) mm (p > 0.05) at LNG and (0.34±0.53) mm, (0.48±0.56) mm (p > 0.05), (0.55±0.56) mm (p > 0.05), (0.37±0.61) mm (p > 0.05), and (0.24±0.43) mm (p > 0.05) at LAT of the anterior-posterior direction for the five pipelines. CONCLUSION: Multisequence MR-generated sCT allows for accurate dose calculation and fractional positioning for head and neck MR-only RT.

Deep learning-based 3Din vivodose reconstruction with an electronic portal imaging device for magnetic resonance-linear accelerators: a proof of concept study.

Objective.To develop a novel deep learning-based 3Din vivodose reconstruction framework with an electronic portal imaging device (EPID) for magnetic resonance-linear accelerators (MR-LINACs).Approach.The proposed method directly back-projected 2D portal dose into 3D patient coarse dose, which bypassed the complicated patient-to-EPID scatter estimation step used in conventional methods. A pre-trained convolutional neural network (CNN) was then employed to map the coarse dose to the final accurate dose. The electron return effect caused by the magnetic field was captured with the CNN model. Patient dose and portal dose datasets were synchronously generated with Monte Carlo simulation for 96 patients (78 cases for training and validation and 18 cases for testing) treated with fixed-beam intensity-modulated radiotherapy in four different tumor sites, including the brain, nasopharynx, lung, and rectum. Beam angles from the training dataset were further rotated 2-3 times, and doses were recalculated to augment the datasets.Results.The comparison between reconstructed doses and MC ground truth doses showed mean absolute errors <0.88% for all tumor sites. The averaged 3Dγ-passing rates (3%, 2 mm) were 97.42%±2.66% (brain), 98.53%±0.95% (nasopharynx), 99.41%±0.46% (lung), and 98.63%±1.01% (rectum). The dose volume histograms and indices also showed good consistency. The average dose reconstruction time, including back projection and CNN dose mapping, was less than 3 s for each individual beam.Significance.The proposed method can be potentially used for accurate and fast 3D dosimetric verification for online adaptive radiotherapy using MR-LINACs.

A prior image constraint robust principal component analysis reconstruction method for sparse segmental multi-energy computed tomography.

BACKGROUND: Multi-energy computed tomography (MECT) is a promising technique in medical imaging, especially for quantitative imaging. However, high technical requirements and system costs barrier its step into clinical practice. METHODS: We propose a novel sparse segmental MECT (SSMECT) scheme and corresponding reconstruction method, which is a cost-efficient way to realize MECT on a conventional single-source CT. For the data acquisition, the X-ray source is controlled to maintain an energy within a segmental arc, and then switch alternately to another energy level. This scan only needs to switch tube voltage a few times to acquire multi-energy data, but leads to sparse-view and limited-angle issues in image reconstruction. To solve this problem, we propose a prior image constraint robust principal component analysis (PIC-RPCA) reconstruction method, which introduces structural similarity and spectral correlation into the reconstruction. RESULTS: A numerical simulation and a real phantom experiment were conducted to demonstrate the efficacy and robustness of the scan scheme and reconstruction method. The results showed that our proposed reconstruction method could have achieved better multi-energy images than other competing methods both quantitatively and qualitatively. CONCLUSIONS: Our proposed SSMECT scan with PIC-RPCA reconstruction method could lower kVp switching frequency while achieving satisfactory reconstruction accuracy and image quality.

Immune reconstitution inflammatory syndrome in non-HIV cryptococcal meningitis: Cross-talk between pathogen and host.

BACKGROUND: Cryptococcal meningitis (CM)-associated immune reconstitution inflammatory syndrome (IRIS) is associated with high mortality, the epidemiology and pathophysiology of which is poorly understood, especially in non-HIV populations. OBJECTIVES: We aim to explore the incidence, clinical risk factors, immunological profiles and potential influence of leukotriene A4 hydroxylase (LTA4H) on non-HIV CM IRIS populations. METHODS: In this observational cohort study, 101 previously untreated non-HIV CM patients were included. We obtained data for clinical variables, 27 cerebrospinal fluid (CSF) cytokines levels and LTA4H genotype frequencies. Changes of CSF cytokines levels before and at IRIS occurrence were compared. RESULTS: Immune reconstitution inflammatory syndrome was identified in 11 immunocompetent males, generating an incidence of 10.9% in non-HIV CM patients. Patients with higher CrAg titres (> 1:160) were more likely to develop IRIS, and titre of 1:1280 is the optimum level to predict IRIS occurrence. Baseline CSF cytokines were significantly higher in IRIS group, which indicated a severe host immune inflammation response. Four LTA4H SNPs (rs17525488, rs6538697, rs17525495 and rs1978331) exhibited significant genetic susceptibility to IRIS in overall non-HIV CM, while five cytokines were found to be associated with rs1978331, and baseline monocyte chemotactic protein 1 (MCP-1) became the only cytokine correlated with both IRIS and LTA4H SNPs. CONCLUSIONS: Our study suggested that non-HIV CM patients with high fungal burden and severe immune inflammation response were more likely to developed IRIS. LTA4H polymorphisms may affect the pathogenesis of IRIS by regulating the level of baseline CSF MCP-1.

A feasibility study on deep learning-based individualized 3D dose distribution prediction.

PURPOSE: Radiation therapy treatment planning is a trial-and-error, often time-consuming process. An approximately optimal dose distribution corresponding to a specific patient's anatomy can be predicted by using pre-trained deep learning (DL) models. However, dose distributions are often optimized based not only on patient-specific anatomy but also on physicians' preferred trade-offs between planning target volume (PTV) coverage and organ at risk (OAR) sparing or among different OARs. Therefore, it is desirable to allow physicians to fine-tune the dose distribution predicted based on patient anatomy. In this work, we developed a DL model to predict the individualized 3D dose distributions by using not only the patient's anatomy but also the desired PTV/OAR trade-offs, as represented by a dose volume histogram (DVH), as inputs. METHODS: In this work, we developed a modified U-Net network to predict the 3D dose distribution by using patient PTV/OAR masks and the desired DVH as inputs. The desired DVH, fine-tuned by physicians from the initially predicted DVH, is first projected onto the Pareto surface, then converted into a vector, and then concatenated with feature maps encoded from the PTV/OAR masks. The network output for training is the dose distribution corresponding to the Pareto optimal DVH. The training/validation datasets contain 77 prostate cancer patients, and the testing dataset has 20 patients. RESULTS: The trained model can predict a 3D dose distribution that is approximately Pareto optimal while having the DVH closest to the input desired DVH. We calculated the difference between the predicted dose distribution and the optimized dose distribution that has a DVH closest to the desired one for the PTV and for all OARs as a quantitative evaluation. The largest absolute error in mean dose was about 3.6% of the prescription dose, and the largest absolute error in the maximum dose was about 2.0% of the prescription dose. CONCLUSIONS: In this feasibility study, we have developed a 3D U-Net model with the patient's anatomy and the desired DVH curves as inputs to predict an individualized 3D dose distribution that is approximately Pareto optimal while having the DVH closest to the desired one. The predicted dose distributions can be used as references for dosimetrists and physicians to rapidly develop a clinically acceptable treatment plan.