Purpose
Cone‐beam computed tomography (CBCT) scanning is used daily or weekly (i.e., on‐treatment CBCT) for accurate patient setup in image‐guided radiotherapy. However, inaccuracy of CT numbers ...prevents CBCT from performing advanced tasks such as dose calculation and treatment planning. Motivated by the promising performance of deep learning in medical imaging, we propose a deep U‐net‐based approach that synthesizes CT‐like images with accurate numbers from planning CT, while keeping the same anatomical structure as on‐treatment CBCT.
Methods
We formulated the CT synthesis problem under a deep learning framework, where a deep U‐net architecture was used to take advantage of the anatomical structure of on‐treatment CBCT and image intensity information of planning CT. U‐net was chosen because it exploits both global and local features in the image spatial domain, matching our task to suppress global scattering artifacts and local artifacts such as noise in CBCT. To train the synthetic CT generation U‐net (sCTU‐net), we include on‐treatment CBCT and initial planning CT of 37 patients (30 for training, seven for validation) as the input. Additional replanning CT images acquired on the same day as CBCT after deformable registration are utilized as the corresponding reference. To demonstrate the effectiveness of the proposed sCTU‐net, we use another seven independent patient cases (560 slices) for testing.
Results
We quantitatively compared the resulting synthetic CT (sCT) with the original CBCT image using deformed same‐day pCT images as reference. The averaged accuracy measured by mean absolute error (MAE) between sCT and reference CT (rCT) on testing data is 18.98 HU, while MAE between CBCT and rCT is 44.38 HU.
Conclusions
The proposed sCTU‐net can synthesize CT‐quality images with accurate CT numbers from on‐treatment CBCT and planning CT. This potentially enables advanced CBCT applications for adaptive treatment planning.
In this work, CO2 hydrogenation over In2O3-supported rhenium (Re) catalysts was found to be highly size-dependent. When the Re loading was less than 1 wt %, the strong interaction between Re and ...In2O3 caused atomically dispersed Re species with a positive charge, resulting in high activity for CO2 hydrogenation to methanol with enhanced stability at elevated temperatures. The space–time yield of methanol over the 1 wt % Re/In2O3 catalyst reached 0.54 gMeOH gcat –1 h–1 with a methanol selectivity of 72.1% at 5 MPa and 573 K. With increasing Re loading, the In2O3 supported Re catalysts become more favored for CO2 methanation. Under the same experimental conditions, the methane selectivity is close to 100.0% over the 10 wt % Re/In2O3 catalyst. Catalyst characterizations and density functional theoretical (DFT) calculations further confirm that the size of the Re/In2O3 catalyst has a significant effect on hydrogen activation and the selectivity of the CO2 hydrogenation reaction. Due to the strong Re–In2O3 interaction, the atomically dispersed Re in the In2O3 surface lattice not only stabilizes oxygen vacancies but also results in Hδ+ formation upon hydrogen adsorption. This significantly promotes methanol synthesis from CO2 hydrogenation. Meanwhile, the 10 wt % Re/In2O3 catalyst with supported Re nanoclusters induces H δ‑ formation, which eventually leads to more methane production. The present study demonstrates the atomically dispersed Re/In2O3 catalyst is promising for CO2 hydrogenation to methanol.
Ni/In2O3 was confirmed to be active for CO2 hydrogenation to methanol. Herein, the In2O3-ZrO2 solid solution was prepared to support the highly dispersed nickel catalyst by chemical reduction. A CO2 ...conversion of 17.9% with a space-time yield (STY) of methanol of 0.63 gMeOH gcat−1 h−1 was achieved at 300 °C and 5 MPa on Ni/In2O3-ZrO2 of 5 wt% Ni loading. The STY of methanol has a 43.2% increase, compared to Ni/In2O3. The use of ZrO2 optimizes the oxygen vacancies for CO2 activation. The highly dispersed Ni catalyst facilitates hydrogen spillover, which improves hydrogenation ability and the formation of oxygen vacancies.
Display omitted
•The chemical reduction leads to highly dispersed Ni catalyst on In2O3-ZrO2.•The highly dispersed Ni catalyst causes an excellent hydrogen spillover.•The use of ZrO2 optimizes and stabilizes the oxygen vacancies for CO2 activation.•Ni/In2O3-ZrO2 is a highly active catalyst for CO2 hydrogenation to methanol.•High methanol selectivity is achieved over Ni/In2O3-ZrO2.
Road dust from different sources directly contacts the human body and has potential effects on public health. In this study, a total number of 87 road dust samples were collected at 29 sampling sites ...from five different functional areas (commercial area (CA), residential area (RA), educational area (EA), industrial area (IA), and park area (PA)) in Zhengzhou to study the contamination status, distribution, source identification, ecological risk assessment, and spatial distribution of human health risks due to eight heavy elements. The geo-accumulation index (
I
geo
) and pollution index (PI) revealed that there was very high contamination with Cd and Hg caused by atmospheric deposition, which should be paid special attention. Additionally, the source identification indicated that Cr, Ni, Cu, Zn, Cd, and Pb originate from anthropogenic activities related to traffic, and Hg can originate from medical equipment and agricultural chemicals, while the extremely low level of pollution with As could be explained by geographic sources. Moreover, the calculated ecological risk index values were increased in the order of CA > RA > EA > IA > PA in different functional areas. According to the human health risks of the whole city, children exposed to Pb have the highest health risk, especially for CA and IA, as calculated by the noncarcinogenic hazard index (HI). For adults and children, health risks caused by Cu, Zn, and Pb were higher in the CA, RA, and PA of the downtown area, whereas Cr and Ni had the highest noncarcinogenic exposure risk in northwestern Zhengzhou due to point source pollution. Calculations of the carcinogenic risk (CR) values for Cr, Ni, As, and Cd indicate that the value of Cr is highest (1.17 × 10
−7
), especially inside the industrial area (8.55 × 10
−7
), which is close to the lower limit of the threshold values (10
−6
to 10
−4
). These results can provide a theoretical basis and data support for air treatment, pollution control, and the implementation of public prevention in different functional areas of Zhengzhou.
Heavy metals in road dust pose a significant threat to human health. This study investigated the concentrations, patterns, and sources of eight hazardous heavy metals (Cr, Ni, Cu, Zn, As, Cd, Pb, and ...Hg) in the street dust of Zhengzhou city of PR China. Fifty-eight samples of road dust were analyzed based on three methods of risk assessment, i.e., Geo-Accumulation Index (Igeo), Potential Ecological Risk Assessment (RI), and Nemerow Synthetic Pollution Index (PIN). The results exhibited higher concentrations of Hg and Cd 14 and 7 times higher than their background values, respectively. Igeo showed the risks of contamination in a range of unpolluted (Cr, Ni) to strongly polluted (Hg and Cd) categories. RI came up with the contamination ranges from low (Cr, Ni, Cu, Zn, As, and Pb) to extreme (Cd and Hg) risk of contamination. The risk of contamination based on PIN was from safe (Cu, As, and Pb) to seriously high (Cd and Hg). The results yielded by PIN indicated the extreme risk of Cd and Hg in the city. Positive Matrix Factorization was used to identify the sources of contamination. Factor 1 (vehicular exhaust), Factor 2 (coal combustion), Factor 3 (metal industry), and Factor 4 (anthropogenic activities), respectively, contributed 14.63%, 35.34%, 36.14%, and 13.87% of total heavy metal pollution. Metal’s presence in the dust is a direct health risk for humans and warrants immediate and effective pollution control and prevention measures in the city.
Purpose
Diagnosis of lung cancer requires radiologists to review every lung nodule in CT images. Such a process can be very time-consuming, and the accuracy is affected by many factors, such as ...experience of radiologists and available diagnosis time. To address this problem, we proposed to develop a deep learning-based system to automatically classify benign and malignant lung nodules.
Methods
The proposed method automatically determines benignity or malignancy given the 3D CT image patch of a lung nodule to assist diagnosis process. Motivated by the fact that real structure among data is often embedded on a low-dimensional manifold, we developed a novel manifold regularized classification deep neural network (MRC-DNN) to perform classification directly based on the manifold representation of lung nodule images. The concise manifold representation revealing important data structure is expected to benefit the classification, while the manifold regularization enforces strong, but natural constraints on network training, preventing over-fitting.
Results
The proposed method achieves accurate manifold learning with reconstruction error of ~ 30 HU on real lung nodule CT image data. In addition, the classification accuracy on testing data is 0.90 with sensitivity of 0.81 and specificity of 0.95, which outperforms state-of-the-art deep learning methods.
Conclusion
The proposed MRC-DNN facilitates an accurate manifold learning approach for lung nodule classification based on 3D CT images. More importantly, MRC-DNN suggests a new and effective idea of enforcing regularization for network training, possessing the potential impact to a board range of applications.
Online adaptive radiation is a new and exciting modality of treatment for gynecologic cancers. Traditional radiation treatments deliver the same radiation plan to cancers with large margins. ...Improvements in imaging, technology, and artificial intelligence have made it possible to account for changes between treatments and improve the delivery of radiation. These advances can potentially lead to significant benefits in tumor coverage and normal tissue sparing. Gynecologic cancers can uniquely benefit from this technology due to the significant changes in bladder, bowel, and rectum between treatments as well as the changes in tumors commonly seen between treatments. Preliminary studies have shown that online adaptive radiation can maintain coverage of the tumor while sparing nearby organs. Given these potential benefits, numerous clinical trials are ongoing to investigate the clinical benefits of online adaptive radiotherapy. Despite the benefits, implementation of online adaptive radiotherapy requires significant clinical resources. Additionally, the timing and workflow for online adaptive radiotherapy is being optimized. In this review, we discuss the history and evolution of radiation techniques, the logistics and implementation of online adaptive radiation, and the potential benefits of online adaptive radiotherapy for gynecologic cancers.
Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, ...existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods.
Display omitted
Tetrahydrofuran (THF) extract of coal tar pitch (CTP) was used instead of blending CTP with pretreated pyrolysis fuel oil to prepare an isotropic pitch precursor with excellent ...spinnability for general-purpose carbon fibre through bromination–dehydrobromination. The feasibility and effectiveness of synthesising an isotropic pitch precursor derived from THF-soluble (CTP-THFs) is demonstrated in this study. The results show that CTP-THFs contains more light components than CTP; CTP-THFs and CTP monomer proportions were 62.52% and 45.32%, respectively. However, based on comparisons of CTP-THFsBr0 and CTPBr0 characterisations, CTP-THFs exhibits better polycondensation than CTP. Bromination–dehydrobromination promotes polycondensation of pitch precursors, leading to greater carbon aromaticity in CTP-THFsBr5, CTP-THFsBr10, and CTP-THFsBr15 than that in CTP-THFsBr0 and CTPBr0. CTP-THFsBr5 and CTP-THFsBr10 have excellent spinnability even with softening points as high as 230 °C. The peri-condensed carbon and carbon aromaticity of CTP-THFsBr5 and CTP-THFsBr10 are high owing to the higher degree of polycondensation; however, they still possess a more linear molecular structure. The as-prepared carbon fibre exhibits homogeneity and uniformity, and the mechanical performance is comparable with that of commercial general-purpose carbon fibre products.
•Efficient removal of N-heterocyclic pollutants, HSs and salts by a novel integrated process.•Utilization of different electrochemical principles on the removal procedure.•High level quality of final ...effluent for industrial water reuse.
In this work, a novel electrochemical process of electrocatalysis-electrodialysis-electro-microfiltration was developed for high level standard reuse of chemical industrial tailwater. The performance and mechanisms for each technique were investigated by multi-analyze methods, individually. The target species including N-heterocyclic pollutants (pyrrole, pyrimidine and pyridine), Humic Substances and salt of sodium sulfate were removed from the simulated wastewater by this process. Within electrocatalysis, pyrrole and pyrimidine were degraded prior to pyridine due to their lower Gibbs energy barriers as 6.79kcaland 16.89kcal, respectively, and thus were easier attacked by hydroxyl radical generated on the electrode surface. Then the pyridine together with the salt was removed efficiently during electrodialysis. The residue salt and pyridine molecules as well as the HSs were furtherly rejected by the synergistic effect of electric field and membrane by the electro-microfiltration process. Final effluent revealed a very low level of pyridine content of 0.103mg/L, TOC of 3mg/L, UV254 of 0.025 and a low conductivity of 33μs/cm, consistent with an excellent removal of the target species of ∼100% pyrrole, ∼100% pyrimidine, >99% pyridine, >95% HSs and >99% salt.