Efficient All-Perovskite Tandem Solar Cells with Low-Optical-Loss Carbazolyl Interconnecting Layers.

Combining wide-band gap (WBG) and narrow-band gap (NBG) perovskites with interconnecting layers (ICLs) to construct monolithic all-perovskite tandem solar cell is an effective way to achieve high power conversion efficiency (PCE). However, optical losses from ICLs need to be further reduced to leverage the full potential of all-perovskite tandem solar cells. Here, metal oxide nanocrystal layers anchored with carbazolyl hole-selective-molecules (CHs), which exhibit much lower optical loss, is employed to replace poly(3,4-ethylenedioxythiophene) polystyrenesulfonate (PEDOT : PSS) as the hole transporting layers (HTLs) in lead-tin (Pb-Sn) perovskite sub-cells and ICLs in all-perovskite tandem solar cells. Optically transparent indium tin oxide nanocrystals (ITO NCs) layers are employed to enhance anchoring of CHs, while a mixture of two CHs is adopted to tune the surface energy-levels of ITO NCs. The optimized mixed Pb-Sn NBG perovskite solar cells demonstrate a high PCE of 23.2 %, with a high short-circuit current density (Jsc ) of 33.5 mA cm-2 . A high PCE of 28.1 % is further obtained in all-perovskite tandem solar cells, with the highest Jsc of 16.7 mA cm-2 to date. Encapsulated tandem solar cells maintain 90 % of their reference point after 500 h of operation at the maximum power point (MPP) under 1-Sun illumination.

Recent Advances in Porphyrin-Based Systems for Electrochemical Oxygen Evolution Reaction.

Oxygen evolution reaction (OER) plays a pivotal role in the development of renewable energy methods, such as water-splitting devices and the use of Zn-air batteries. First-row transition metal complexes are promising catalyst candidates due to their excellent electrocatalytic performance, rich abundance, and cheap price. Metalloporphyrins are a class of representative high-efficiency complex catalysts owing to their structural and functional characteristics. However, OER based on porphyrin systems previously have been paid little attention in comparison to the well-described oxygen reduction reaction (ORR), hydrogen evolution reaction, and CO2 reduction reaction. Recently, porphyrin-based systems, including both small molecules and porous polymers for electrochemical OER, are emerging. Accordingly, this review summarizes the recent advances of porphyrin-based systems for electrochemical OER. Firstly, the electrochemical OER for water oxidation is discussed, which shows various methodologies to achieve catalysis from homogeneous to heterogeneous processes. Subsequently, the porphyrin-based catalytic systems for bifunctional oxygen electrocatalysis including both OER and ORR are demonstrated. Finally, the future development of porphyrin-based catalytic systems for electrochemical OER is briefly prospected.

Recent Advances in the Photoreactions Triggered by Porphyrin-Based Triplet-Triplet Annihilation Upconversion Systems: Molecular Innovations and Nanoarchitectonics.

Triplet-triplet annihilation upconversion (TTA-UC) is a very promising technology that could be used to convert low-energy photons to high-energy ones and has been proven to be of great value in various areas. Porphyrins have the characteristics of high molar absorbance, can form a complex with different metal ions and a high proportion of triplet states as well as tunable structures, and thus they are important sensitizers for TTA-UC. Porphyrin-based TTA-UC plays a pivotal role in the TTA-UC systems and has been widely used in many fields such as solar cells, sensing and circularly polarized luminescence. In recent years, applications of porphyrin-based TTA-UC systems for photoinduced reactions have emerged, but have been paid little attention. As a consequence, this review paid close attention to the recent advances in the photoreactions triggered by porphyrin-based TTA-UC systems. First of all, the photochemistry of porphyrin-based TTA-UC for chemical transformations, such as photoisomerization, photocatalytic synthesis, photopolymerization, photodegradation and photochemical/photoelectrochemical water splitting, was discussed in detail, which revealed the different mechanisms of TTA-UC and methods with which to carry out reasonable molecular innovations and nanoarchitectonics to solve the existing problems in practical application. Subsequently, photoreactions driven by porphyrin-based TTA-UC for biomedical applications were demonstrated. Finally, the future developments of porphyrin-based TTA-UC systems for photoreactions were briefly discussed.

[Metal artifact reduction for dental implants in kilovoltage computed tomography using megavoltage cone-beam computer tomography].

This paper proposes a novel metal artifact reduction (MAR) algorithm for dental implants in kilovoltage computed tomography (kVCT) using megavoltage cone-beam computer tomography (MVCBCT). Firstly, two CT images were derived by scanning patient with dental implants using kVCT and MVCBCT. Metal image was derived by thresholding segmentation in kVCT. MVCBCT and kVCT images were fused to generate prior image which was forward projected to get surrogate sinogram of metal trace. The corrected image was generated by filtered backprojection (FBP) reconstruction in corrected sinogram. The results of proposed algorithm were compared with other frequently-used metal artifact reduction algorithm, such as normalized MAR (NMAR), normalized MAR using MVCBCT prior images (NMAR-MV), and linear interpolation MAR (LIMAR). The normalized root mean square deviation (NRMSD) and mean absolute deviation (MAD) were computed. The experiment showed that the proposed method removed serious metal artifacts without introducing new artifacts. The values of NRMSD and MAD for proposed method were the minimum in all methods. The values of NRMSD for NMAR, NMAR-MV, LIMAR and the proposed method were 21.0%, 22.1%, 41.9% and 17.0% respectively. And MAD values of them were 232, 235, 553, 205 HU, respectively. In conclusion, the proposed metal artifact reduction algorithm can successfully suppress metal artifacts for dental implants, and greatly improve the quality of CT image.

miR-302b suppresses cell invasion and metastasis by directly targeting AKT2 in human hepatocellular carcinoma cells.

MicroRNAs (miRNAs) have been shown to play essential roles in regulating the activity of human hepatocellular carcinoma (HCC) cells, thereby contributing to the suppression of invasion and metastasis. In this study, using gain and loss of function assays, we demonstrated that miR-302b was frequently down-regulated in clinical HCC specimens, as compared with 15 corresponding adjacent normal tissues. Overexpression of miR-302b suppressed HCC cell invasion and metastasis. Regulation of NF-κB and matrix metalloproteinase (MMP)-2 expression by miR-302b was mediated via AKT2 in SMMC-7721 cells. Silencing AKT2 produced effects similar to those of miR-302b overexpression, which included inhibiting SMMC-7721 cell invasion and metastasis and dereasing NF-κB and MMP-2 expression. Furthermore, overexpression of AKT2 attenuated the effects of miR-302b overexpression. Taken together, our findings indicate that miR-302b inhibits SMMC-7721 cell invasion and metastasis by targeting AKT2, suggesting that miR-302b might represent a potential therapeutic target for HCC intervention.

Identification of organic pollutants and heavy metals in natural rubber wastewater and evaluation its phytotoxicity and cytogenotoxicity.

The natural rubber industry consumes large volumes of water and annually releases wastewater with rich organic and inorganic loads. This wastewater is allowed for soil irrigation in developing countries. However, the pollutant composition in wastewater and its environmental effects remain unclear. Therefore, we aimed to assess the wastewater's physicochemical parameters, toxic organic pollutants, heavy metals, and phytotoxic and cytogenotoxic. The result revealed that values of comprehensive wastewater parameters were recorded as chemical oxygen demand (187432.1 mg/L), pH (4.23), total nitrogen (1157.1 mg/L), ammonia nitrogen (1113.0 mg/L), total phosphorus (1181.2 mg/L), Zn (593.3 mg/L), Cr (0.6127 mg/L), and Ni (0.2986 mg/L). The organic compounds detected by LC-MS were salbostatin, sirolimus, Gibberellin A34-catabolite, 1-(sn-glycero-3-phospho)-1D-myo-inositol, and methyldiphenylsilane. The toxicity of the identified toxic chemicals and heavy metals was confirmed by onion and mung bean phytotoxicity characterization tests. The wastewater affected the germination of mung bean seeds, reduced or inhibited the growth of onions, and induced various chromosomal aberrations in root apical meristems. Our study shows that the treatment of natural rubber wastewater needs to be improved, and the feasibility of irrigating soil with wastewater needs to be reconsidered.

Polyimide covalent organic frameworks bearing star-shaped electron-deficient polycyclic aromatic hydrocarbon building blocks: molecular innovations for energy conversion and storage.

Polyimide covalent organic frameworks (PI-COFs) are outstanding functional materials for electrochemical energy conversion and storage owing to their integrated advantages of the high electroactive feature of polyimides and the periodic porous structure of COFs. Nevertheless, only anhydride monomers with C2 symmetry are generally used, and limited selectivity of electron-deficient monomers has become a major obstacle in the development of materials. The introduction of polycyclic aromatic hydrocarbons (PAHs) is a very effective method to regulate the structure-activity relationship of PI-COFs due to their excellent stability and electrical properties. Over the past two years, various star-shaped electron-deficient PAH building blocks possessing different compositions and topologies have been successfully fabricated, greatly improving the monomer selectivity and electrochemical performances of PI-COFs. This paper systematically summarizes the recent highlights in PI-COFs based on these building blocks. Firstly, the preparation of anhydride (or phthalic acid) monomers and PI-COFs related to different star-shaped PAHs is presented. Secondly, the applications of these PI-COFs in energy conversion and storage and the corresponding factors influencing their performance are discussed in detail. Finally, the future development of this meaningful field is briefly proposed.

Pseudo-medical image-guided technology based on 'CBCT-only' mode in esophageal cancer radiotherapy.

Purpose To minimize the various errors introduced by image-guided radiotherapy (IGRT) in the application of esophageal cancer treatment, this study proposes a novel technique based on the 'CBCT-only' mode of pseudo-medical image guidance. Methods The framework of this technology consists of two pseudo-medical image synthesis models in the CBCT→CT and the CT→PET direction. The former utilizes a dual-domain parallel deep learning model called AWM-PNet, which incorporates attention waning mechanisms. This model effectively suppresses artifacts in CBCT images in both the sinogram and spatial domains while efficiently capturing important image features and contextual information. The latter leverages tumor location and shape information provided by clinical experts. It introduces a PRAM-GAN model based on a prior region aware mechanism to establish a non-linear mapping relationship between CT and PET image domains.  As a result, it enables the generation of pseudo-PET images that meet the clinical requirements for radiotherapy. Results The NRMSE and multi-scale SSIM (MS-SSIM) were utilized to evaluate the test set, and the results were presented as median values with lower quartile and upper quartile ranges. For the AWM-PNet model, the NRMSE and MS-SSIM values were 0.0218 (0.0143, 0.0255) and 0.9325 (0.9141, 0.9410), respectively. The PRAM-GAN model produced NRMSE and MS-SSIM values of 0.0404 (0.0356, 0.0476) and 0.9154 (0.8971, 0.9294), respectively. Statistical analysis revealed significant differences (p < 0.05) between these models and others. The numerical results of dose metrics, including D98 %, Dmean, and D2 %, validated the accuracy of HU values in the pseudo-CT images synthesized by the AWM-PNet. Furthermore, the Dice coefficient results confirmed statistically significant differences (p < 0.05) in GTV delineation between the pseudo-PET images synthesized using the PRAM-GAN model and other compared methods. Conclusion The AWM-PNet and PRAM-GAN models have the capability to generate accurate pseudo-CT and pseudo-PET images, respectively. The pseudo-image-guided technique based on the 'CBCT-only' mode shows promising prospects for application in esophageal cancer radiotherapy.

Enhancing Electrocatalytic CO2-to-CO Conversion by Weakening CO Binding through Nitrogen Integration in the Metallic Fe Catalyst.

Metallic iron (Fe) typically demonstrates the unfavorable catalytic activity for the CO2 reduction reaction (CO2RR), mainly attributed to the excessively strong binding of CO products on Fe sites. Toward this end, we employed an effective approach involving electronic structure modulation through nitrogen (N) integration to enhance the performance of the CO2RR. Here, an efficient catalyst has been developed, composed of N-doped metallic iron (Fe) nanoparticles encapsulated in a porous N-doped carbon framework. Notably, this N-integrated Fe catalyst displays significantly enhanced performance in the electrocatalytic reduction of CO2, yielding the highest CO Faradaic efficiency of 97.5% with a current density of 6.68 mA cm-2 at -0.7 V versus the reversible hydrogen electrode. The theoretical calculations, combined with the in situ attenuated total reflection surface-enhanced infrared absorption spectroscopy study, reveal that N integration modulates the electron density around Fe, resulting in the weakening of the binding strength between the Fe active sites and *CO intermediates, consequently promoting the desorption of CO and the overall CO2RR process.

Scalable Solution-Processed Hybrid Electron Transport Layers for Efficient All-Perovskite Tandem Solar Modules.

All-perovskite tandem solar cells offer the potential to surpass the Shockley-Queisser (SQ) limit efficiency of single-junction solar cells while maintaining the advantages of low-cost and high-productivity solution processing. However, scalable solution processing of electron transport layer (ETL) in p-i-n structured perovskite solar subcells remains challenging due to the rough perovskite film surface and energy level mismatch between ETL and perovskites. Here, scalable solution processing of hybrid fullerenes (HF) with blade-coating on both wide-bandgap (≈1.80 eV) and narrow-bandgap (≈1.25 eV) perovskite films in all-perovskite tandem solar modules is developed. The HF, comprising a mixture of fullerene (C60 ), phenyl C61 butyric acid methyl ester, and indene-C60 bisadduct, exhibits improved conductivity, superior energy level alignment with both wide- and narrow-bandgap perovskites, and reduced interfacial nonradiative recombination when compared to the conventional thermal-evaporated C60 . With scalable solution-processed HF as the ETLs, the all-perovskite tandem solar modules achieve a champion power conversion efficiency of 23.3% (aperture area = 20.25 cm2 ). This study paves the way to all-solution processing of low-cost and high-efficiency all-perovskite tandem solar modules in the future.

Homogeneous crystallization and buried interface passivation for perovskite tandem solar modules.

Scalable fabrication of all-perovskite tandem solar cells is challenging because the narrow-bandgap subcells made of mixed lead-tin (Pb-Sn) perovskite films suffer from nonuniform crystallization and inferior buried perovskite interfaces. We used a dopant from Good's list of biochemical buffers, aminoacetamide hydrochloride, to homogenize perovskite crystallization and used it to extend the processing window for blade-coating Pb-Sn perovskite films and to selectively passivate defects at the buried perovskite interface. The resulting all-perovskite tandem solar module exhibited a certified power conversion efficiency of 24.5% with an aperture area of 20.25 square centimeters.

Solvent engineering for scalable fabrication of perovskite/silicon tandem solar cells in air.

Perovskite/silicon tandem solar cells hold great promise for realizing high power conversion efficiency at low cost. However, achieving scalable fabrication of wide-bandgap perovskite (~1.68 eV) in air, without the protective environment of an inert atmosphere, remains challenging due to moisture-induced degradation of perovskite films. Herein, this study reveals that the extent of moisture interference is significantly influenced by the properties of solvent. We further demonstrate that n-Butanol (nBA), with its low polarity and moderate volatilization rate, not only mitigates the detrimental effects of moisture in air during scalable fabrication but also enhances the uniformity of perovskite films. This approach enables us to achieve an impressive efficiency of 29.4% (certified 28.7%) for double-sided textured perovskite/silicon tandem cells featuring large-size pyramids (2-3 µm) and 26.3% over an aperture area of 16 cm2. This advance provides a route for large-scale production of perovskite/silicon tandem solar cells, marking a significant stride toward their commercial viability.

The gap before real clinical application of imaging-based machine-learning and radiomic models for chemoradiation outcome prediction in esophageal cancer: a systematic review and meta-analysis.

BACKGROUND: Due to tumoral heterogeneity and the lack of robust biomarkers, the prediction of chemoradiotherapy response and prognosis in patients with esophageal cancer (EC) is challenging. The goal of this study was to assess the study quality and clinical value of machine learning and radiomic-based quantitative imaging studies for predicting the outcomes of EC patients after chemoradiotherapy. MATERIALS AND METHODS: PubMed, Embase, and Cochrane were searched for eligible articles. The methodological quality and risk of bias were evaluated using the Radiomics Quality Score (RQS), Image Biomarkers Standardization Initiative (IBSI) Guideline, and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement, as well as the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. A meta-analysis of the evidence focusing on predicting chemoradiotherapy response and outcome in EC patients was implemented. RESULTS: Forty-six studies were eligible for qualitative synthesis. The mean RQS score was 9.07, with an adherence rate of 42.52%. The adherence rates of the TRIPOD and IBSI were 61.70 and 43.17%, respectively. Ultimately, 24 studies were included in the meta-analysis, of which 16 studies had a pooled sensitivity, specificity, and area under the curve (AUC) of 0.83 (0.76-0.89), 0.83 (0.79-0.86), and 0.84 (0.81-0.87) in neoadjuvant chemoradiotherapy datasets, as well as 0.84 (0.75-0.93), 0.89 (0.83-0.93), and 0.93 (0.90-0.95) in definitive chemoradiotherapy datasets, respectively. Moreover, radiomics could distinguish patients from the low-risk and high-risk groups with different disease-free survival (DFS) (pooled hazard ratio: 3.43, 95% CI 2.39-4.92) and overall survival (pooled hazard ratio: 2.49, 95% CI 1.91-3.25). The results of subgroup and regression analyses showed that some of the heterogeneity was explained by the combination with clinical factors, sample size, and usage of the deep learning (DL) signature. CONCLUSIONS: Noninvasive radiomics offers promising potential for optimizing treatment decision-making in EC patients. However, it is necessary to make scientific advancements in EC radiomics regarding reproducibility, clinical usefulness analysis, and open science categories. Improved model reporting of study objectives, blind assessment, and image processing steps are required to help promote real clinical applications of radiomics in EC research.

Sediment-water distribution and potential sources of polyhalogenated carbazoles in a coastal river locating at a north metropolis, China.

The fate and transformation of PHCZs in the coastal river environment are not yet comprehensively understood. Paired river water and surface sediment were collected, and 12 PHCZs were analyzed to find out their potential sources and investigate the distribution of PHCZs between river water and sediment. The concentration of ∑PHCZs varied from 8.66 to 42.97 ng/g (mean 22.46 ng/g) in sediment and 17.91 to 81.82 ng/L (mean 39.07 ng/L) in river water. 18-B-36-CCZ was the dominant PHCZ congener in sediment, while 36-CCZ was in water. Meanwhile, the logKoc values for CZ and PHCZs were among the first calculated in the estuary and the mean logKoc varied from 4.12 for 1-B-36-CCZ to 5.63 for 3-CCZ. The logKoc values of CCZs were higher than those of BCZs, this may suggest that sediments have a higher capacity for accumulation and storage of CCZs than highly mobile environmental media.

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification.

Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models. Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. Conclusions: The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification.

Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR). Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features. Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN's attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation. Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes' F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19). Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.

Bioremediation of tetramethyl thiuram disulfide and resource utilization of natural rubber wastewater by WR-2 Bacillus-dominated microbial community.

Tetramethyl thiuram disulfide (TMTD), an emerging pollutant with ecotoxicity and accumulation in rubber wastewater, is directly discharged by factories into the surrounding soil to save costs, and this disrupts the nearby ecosystem. In this study, an efficient bioremediation microbial community (WR-2) dominated by Bacillus was acclimatized and isolated from soil contaminated by rubber wastewater. After passing through the metabolic process of WR-2, the ecotoxic TMTD decomposes within 14 days. In the pot experiment, WR-2 not only completed the bioremediation of contaminated soil but also significantly improved the crop growth conditions and the product quality. These results show that WR-2 has broad application prospects in the bioremediation of soil contaminated by rubber wastewater. It also provides a theoretical framework for the resource utilization of the effluent at the end of the initial rubber processing.

Research on new treatment mode of radiotherapy based on pseudo-medical images.

BACKGROUND AND OBJECTIVE: Multi-modal medical images with multiple feature information are beneficial for radiotherapy. A new radiotherapy treatment mode based on triangle generative adversarial network (TGAN) model was proposed to synthesize pseudo-medical images between multi-modal datasets. METHODS: CBCT, MRI and CT images of 80 patients with nasopharyngeal carcinoma were selected. The TGAN model based on multi-scale discriminant network was used for data training between different image domains. The generator of the TGAN model refers to cGAN and CycleGAN, and only one generation network can establish the non-linear mapping relationship between multiple image domains. The discriminator used multi-scale discrimination network to guide the generator to synthesize pseudo-medical images that are similar to real images from both shallow and deep aspects. The accuracy of pseudo-medical images was verified in anatomy and dosimetry. RESULTS: In the three synthetic directions, namely, CBCT â†’ CT, CBCT â†’ MRI, and MRI â†’ CT, significant differences (p < 0.05) in the three-fold-cross validation results on PSNR and SSIM metrics between the pseudo-medical images obtained based on TGAN and the real images. In the testing stage, for TGAN, the MAE metric results in the three synthesis directions (CBCT â†’ CT, CBCT â†’ MRI, and MRI â†’ CT) were presented as mean (standard deviation), which were 68.67 (5.83), 83.14 (8.48), and 79.96 (7.59), and the NMI metric results were 0.8643 (0.0253), 0.8051 (0.0268), and 0.8146 (0.0267) respectively. In terms of dose verification, the differences in dose distribution between the pseudo-CT obtained by TGAN and the real CT were minimal. The H values of the measurement results of dose uncertainty in PGTV, PGTVnd, PTV1, and PTV2 were 42.510, 43.121, 17.054, and 7.795, respectively (P < 0.05). The differences were statistically significant. The gamma pass rate (2%/2 mm) of pseudo-CT obtained by the new model was 94.94% (0.73%), and the numerical results were better than those of the three other comparison models. CONCLUSIONS: The pseudo-medical images acquired based on TGAN were close to the real images in anatomy and dosimetry. The pseudo-medical images synthesized by the TGAN model have good application prospects in clinical adaptive radiotherapy.

Synthesis of pseudo-CT images from pelvic MRI images based on an MD-CycleGAN model for radiotherapy.

Objective.A multi-discriminator-based cycle generative adversarial network (MD-CycleGAN) model is proposed to synthesize higher-quality pseudo-CT from MRI images.Approach.MRI and CT images obtained at the simulation stage with cervical cancer were selected to train the model. The generator adopted DenseNet as the main architecture. The local and global discriminators based on a convolutional neural network jointly discriminated the authenticity of the input image data. In the testing phase, the model was verified by a fourfold cross-validation method. In the prediction stage, the data were selected to evaluate the accuracy of the pseudo-CT in anatomy and dosimetry, and they were compared with the pseudo-CT synthesized by GAN with the generator based on the architectures of ResNet, sUNet, and FCN.Main results.There are significant differences (P < 0.05) in the fourfold cross-validation results on the peak signal-to-noise ratio and structural similarity index metrics between the pseudo-CT obtained based on MD-CycleGAN and the ground truth CT (CTgt). The pseudo-CT synthesized by MD-CycleGAN had closer anatomical information to the CTgtwith a root mean square error of 47.83 ± 2.92 HU, a normalized mutual information value of 0.9014 ± 0.0212, and a mean absolute error value of 46.79 ± 2.76 HU. The differences in dose distribution between the pseudo-CT obtained by MD-CycleGAN and the CTgtwere minimal. The mean absolute dose errors of Dosemax, Dosemin, and Dosemeanbased on the planning target volume were used to evaluate the dose uncertainty of the four pseudo-CT. The u-values of the Wilcoxon test were 55.407, 41.82, and 56.208, and the differences were statistically significant. The 2%/2 mm-based gamma pass rate (%) of the proposed method was 95.45 ± 1.91, and the comparison methods (ResNet_GAN, sUnet_GAN, and FCN_GAN) were 93.33 ± 1.20, 89.64 ± 1.63, and 87.31 ± 1.94, respectively.Significance.The pseudo-CT images obtained based on MD-CycleGAN have higher imaging quality and are closer to the CTgtin terms of anatomy and dosimetry than other GAN models.

Development and validation of bone-suppressed deep learning classification of COVID-19 presentation in chest radiographs.

Background: Coronavirus disease 2019 (COVID-19) is a pandemic disease. Fast and accurate diagnosis of COVID-19 from chest radiography may enable more efficient allocation of scarce medical resources and hence improved patient outcomes. Deep learning classification of chest radiographs may be a plausible step towards this. We hypothesize that bone suppression of chest radiographs may improve the performance of deep learning classification of COVID-19 phenomena in chest radiographs. Methods: Two bone suppression methods (Gusarev et al. and Rajaraman et al.) were implemented. The Gusarev and Rajaraman methods were trained on 217 pairs of normal and bone-suppressed chest radiographs from the X-ray Bone Shadow Suppression dataset (https://www.kaggle.com/hmchuong/xray-bone-shadow-supression). Two classifier methods with different network architectures were implemented. Binary classifier models were trained on the public RICORD-1c and RSNA Pneumonia Challenge datasets. An external test dataset was created retrospectively from a set of 320 COVID-19 positive patients from Queen Elizabeth Hospital (Hong Kong, China) and a set of 518 non-COVID-19 patients from Pamela Youde Nethersole Eastern Hospital (Hong Kong, China), and used to evaluate the effect of bone suppression on classifier performance. Classification performance, quantified by sensitivity, specificity, negative predictive value (NPV), accuracy and area under the receiver operating curve (AUC), for non-suppressed radiographs was compared to that for bone suppressed radiographs. Some of the pre-trained models used in this study are published at (https://github.com/danielnflam). Results: Bone suppression of external test data was found to significantly (P<0.05) improve AUC for one classifier architecture [from 0.698 (non-suppressed) to 0.732 (Rajaraman-suppressed)]. For the other classifier architecture, suppression did not significantly (P>0.05) improve or worsen classifier performance. Conclusions: Rajaraman suppression significantly improved classification performance in one classification architecture, and did not significantly worsen classifier performance in the other classifier architecture. This research could be extended to explore the impact of bone suppression on classification of different lung pathologies, and the effect of other image enhancement techniques on classifier performance.