NSUN2 promotes lung adenocarcinoma progression through stabilizing PIK3R2 mRNA in an m5C-dependent manner.

It is well known that 5-methylcytosine (m5C) is involved in variety of crucial biological processes in cancers. However, its biological roles in lung adenocarcinoma (LAUD) remain to be determined. The LUAD samples were used to assess the clinical value of NOP2/Sun RNA Methyltransferase 2 (NSUN2). Dot blot was used to determine global m5C levels. ChIP and dual-luciferase assays were performed to investigate the MYC-associated zinc finger protein (MAZ)-binding sites in NSUN2 promoter. RNA-seq was used to explore the downstream molecular mechanisms of NSUN2. Dual luciferase reporter assay, m5C-RIP-qPCR, and mRNA stability assay were conducted to explore the effect of NSUN2-depletion on target genes. Cell viability, transwell, and xenograft mouse model were designed to demonstrate the characteristic of NSUN2 in promoting LUAD progression. The m5C methyltransferase NSUN2 was highly expressed and caused elevated m5C methylation in LUAD samples. Mechanistically, MAZ positively regulated the transcription of NSUN2 and was related to poor survival of LUAD patients. Silencing NSUN2 decreased the global m5C levels, suppressed proliferation, migration and invasion, and inhibited activation of PI3K-AKT signaling in A549 and SPAC-1 cells. Phosphoinositide-3-Kinase Regulatory Subunit 2 (PIK3R2) was upregulated by NSUN2-mediated m5C methylation by enhancing its mRNA stabilization and activated the phosphorylation of the PI3K-AKT signaling. The present study explored the underlying mechanism and biological function of NSUN2-meditated m5C RNA methylation in LUAD. NSUN2 was discovered to facilitate the malignancy progression of LUAD through regulating m5C modifications to stabilize PIK3R2 activating the PI3K-AKT signaling, suggesting that NSUN2 could be a novel biomarker and promising therapeutic target for LUAD patients.

Tumor Cell Membrane-Encapsulated MLA Solid Lipid Nanoparticles for Targeted Diagnosis and Radiosensitization Therapy of Cutaneous Squamous Cell Carcinoma.

Squamous cell carcinoma (SCC) is a common nonmelanoma skin cancer. Radiotherapy plays an integral role in treating SCC due to its characteristics, such as diminished intercellular adhesion, heightened cell migration and invasion capabilities, and immune evasion. These problems lead to inaccurate tumor boundary positioning and radiotherapy tolerance in SCC treatment. Thus, accurate localization and enhanced radiotherapy sensitivity are imperative for effective SCC treatment. To address the existing limitations in SCC therapy, we developed monoglyceride solid lipid nanoparticles (MG SLNs) and enveloped them with the A431 cell membrane (A431 CM) to create A431@MG. The characterization results showed that A431@MG was spherical. Furthermore, A431@MG had specific targeting for A431 cells. In A431 tumor-bearing mice, A431@MG demonstrated prolonged accumulation within tumors, ensuring precise boundary localization of SCC. We further advanced the approach by preparing MG SLNs encapsulating 5-aminolevulinic acid methyl ester (MLA) and desferrioxamine (DFO) with an A431 CM coating to yield A431@MG-MLA/DFO. Several studies have revealed that DFO effectively reduced iron content, impeding protoporphyrin IX (PpIX) biotransformation and promoting PpIX accumulation. Simultaneously, MLA was metabolized into PpIX upon cellular entry. During radiotherapy, the heightened PpIX levels enhanced reactive oxygen species (ROS) generation, inducing DNA and mitochondrial damage and leading to cell apoptosis. In A431 tumor-bearing mice, the A431@MG-MLA/DFO group exhibited notable radiotherapy sensitization, displaying superior tumor growth inhibition. Combining A431@MG-MLA/DFO with radiotherapy significantly improved anticancer efficacy, highlighting its potential to serve as an integrated diagnostic and therapeutic strategy for SCC.

TXNIP-NLRP3-GSDMD axis-mediated inflammation and pyroptosis of islet ß-cells is involved in cigarette smoke-induced hyperglycemia, which is alleviated by andrographolide.

Epidemiologic surveys have indicated that cigarette smoking is an important risk factor for diabetes, but its mechanisms remain unclear. Andrographolide, an herb traditionally utilized in medicine, provides anti-inflammatory benefits for various diseases. In the present work, 265 patients with Type 2 diabetes (T2D) were investigated, and male C57BL/6 mice were exposed to cigareete smoke (CS) and/or to intraperitoneally injected andrographolide for 3 months. To elucidate the mechanism of CS-induced hyperglycemia and the protective mechanism of andrographolide, MIN6 cells were exposed to cigarette smoke extract (CSE) and/or to andrographolide. Our data from 265 patients with T2D showed that urinary creatinine and serum inflammatory cytokines (interleukin 6 (IL-6), IL-8, IL-1ß, and tumor necrosis factor α (TNF-α)) increased with smoking pack-years. In a mouse model, CS induced hyperglycemia, decreased insulin secretion, and elevated inflammation and pyroptosis in ß-cells of mice. Treatment of mice with andrographolide preserved pancreatic function by reducing the expression of inflammatory cytokines; the expression of TXNIP, NLRP3, cleaved caspase 1, IL-1ß; and the N-terminal of gasdermin D (GSDMD) protein. For MIN6 cells, CSE caused increasing secretion of the inflammatory cytokines IL-6 and IL-1ß, and the expression of TXNIP and pyroptosis-related proteins; however, andrographolide alleviated these changes. Furthermore, silencing of TXNIP showed that the blocking effect of andrographolide may be mediated by TXNIP. In sum, our results indicate that CS induces hyperglycemia through TXNIP-NLRP3-GSDMD axis-mediated inflammation and pyroptosis of islet ß-cells and that andrographolide is a potential therapeutic agent for CS-induced hyperglycemia.

[Research on Position Verification of Multi-Leaf Collimator (MLC) and Dose Verification Based on Electronic Portal Imaging Device].

Objective: A quality control (QC) system based on the electronic portal imaging device (EPID) system was used to realize the Multi-Leaf Collimator (MLC) position verification and dose verification functions on Primus and VenusX accelerators. Methods: The MLC positions were calculated by the maximum gradient method of gray values to evaluate the deviation. The dose of images acquired by EPID were reconstructed using the algorithm combining dose calibration and dose calculation. The dose data obtained by EPID and two-dimensional matrix (MapCheck/PTW) were compared with the dose calculated by Pinnacle/TiGRT TPS for γ passing rate analysis. Results: The position error of VenusX MLC was less than 1 mm. The position error of Primus MLC was significantly reduced after being recalibrated under the instructions of EPID. For the dose reconstructed by EPID, the average γ passing rates of Primus were 98.86% and 91.39% under the criteria of 3%/3 mm, 10% threshold and 2%/2 mm, 10% threshold, respectively. The average γ passing rates of VenusX were 98.49% and 91.11%, respectively. Conclusion: The EPID-based accelerator quality control system can improve the efficiency of accelerator quality control and reduce the workload of physicists.

Neglected immunoregulation: M2 polarization of macrophages triggered by low-dose irradiation plays an important role in bone regeneration.

Current studies have found that low-dose irradiation (IR) can promote bone regeneration. However, mechanism studies of IR-triggered bone regeneration mainly focus on the effects of osteoblasts, neglecting the role of the surrounding immune microenvironment. Here in this study, in vitro proliferation experiments showed that low-dose IR ≤2 Gy could promote the proliferation of bone marrow mesenchymal stem cells (BMSCs), and qRT-PCR assay showed that low-dose IR ≤2 Gy could exert the M2 polarization of Raw264.7 cells, while IR >2 Gy inhibited BMSC proliferation and triggered M1 polarization in Raw264.7 cells. The ALP and mineralized nodules staining showed that low-dose IR ≤2 Gy not only promoted osteoblast mineralization through IR-triggered osteoblast proliferation but also through M2 polarization of Raw264.7 cells, while high-dose IR >2 Gy had the opposite effect. The co-incubation of BMSC with low-dose IR irradiated Raw264.7 cell supernatants increased the mRNA expression of BMP-2 and Osx. The rat cranial defects model revealed that low-dose IR ≤2 Gy gradually promoted bone regeneration, while high-dose IR >2 Gy inhibited bone regeneration. Detection of macrophage polarity in peripheral blood samples showed that low-dose IR ≤2 Gy increased the expression of CD206 and CD163, but decreased the expression of CD86 and CD80 in macrophages, which indicated M2 polarization of macrophages in vivo, while high-dose IR had the opposite effect. Our finding innovatively revealed that low-dose IR ≤2 Gy promotes bone regeneration not only by directly promoting the proliferation of osteoblasts but also by triggering M2 polarization of macrophages, which provided a new perspective for immune mechanism study in the treatment of bone defects with low-dose IR.

Robust deep learning-based PET prognostic imaging biomarker for DLBCL patients: a multicenter study.

OBJECTIVE: To develop and independently externally validate robust prognostic imaging biomarkers distilled from PET images using deep learning techniques for precise survival prediction in patients with diffuse large B cell lymphoma (DLBCL). METHODS: A total of 684 DLBCL patients from three independent medical centers were included in this retrospective study. Deep learning scores (DLS) were generated from PET images using deep convolutional neural network architecture known as VGG19 and DenseNet121. These DLSs were utilized to predict progression-free survival (PFS) and overall survival (OS). Furthermore, multiparametric models were designed based on results from the Cox proportional hazards model and assessed through calibration curves, concordance index (C-index), and decision curve analysis (DCA) in the training and validation cohorts. RESULTS: The DLSPFS and DLSOS exhibited significant associations with PFS and OS, respectively (P<0.05) in the training and validation cohorts. The multiparametric models that incorporated DLSs demonstrated superior efficacy in predicting PFS (C-index: 0.866) and OS (C-index: 0.835) compared to competing models in training cohorts. In external validation cohorts, the C-indices for PFS and OS were 0.760 and. 0.770 and 0.748 and 0.766, respectively, indicating the reliable validity of the multiparametric models. The calibration curves displayed good consistency, and the decision curve analysis (DCA) confirmed that the multiparametric models offered more net clinical benefits. CONCLUSIONS: The DLSs were identified as robust prognostic imaging biomarkers for survival in DLBCL patients. Moreover, the multiparametric models developed in this study exhibited promising potential in accurately stratifying patients based on their survival risk.

AMPFinder: A computational model to identify antimicrobial peptides and their functions based on sequence-derived information.

Antimicrobial peptides (AMPs) called host defense peptides have existed among all classes of life with 5-100 amino acids generally and can kill mycobacteria, envelop viruses, bacteria, fungi, cancerous cells and so on. Owing to the non-drug resistance of AMP, it has been a wonderful agent to find novel therapies. Therefore, it is urgent to identify AMPs and predict their function in a high-throughput way. In this paper, we propose a cascaded computational model to identify AMPs and their functional type based on sequence-derived and life language embedding, called AMPFinder. Compared with other state-of-the-art methods, AMPFinder obtains higher performance both on AMP identification and AMP function prediction. AMPFinder shows better performance with improvement of F1-score (1.45%-6.13%), MCC (2.92%-12.86%) and AUC (5.13%-8.56%) and AP (9.20%-21.07%) on an independent test dataset. And AMPFinder achieve lower bias of R2 on a public dataset by 10-fold cross-validation with an improvement of (18.82%-19.46%). The comparison with other state-of-the-art methods shows that AMP can accurately identify AMP and its function types. The datasets, source code and user-friendly application are available at https://github.com/abcair/AMPFinder.

A Facile Way To Improve the Bioavailability of Nanomedicine Based on the Threshold Theory.

One of the most significant barriers to the clinical transformation of nanomedicines is low drug distribution in solid tumors due to quick clearance of nanomedicine after injection. Studies have revealed that the distribution of nanomedicine in tumor sites can be considerably improved when the number of nanoparticles supplied in a short period surpasses the threshold. Most routinely employed nanomaterials have dose-related safety concerns. To resolve this problem, we use highly biocompatible albumin to construct blank nanoparticles and doxorubicin loading nanoparticles. Under the guidance of the threshold theory, when the quantity of drug loading nanoparticles is constant, the drug delivery effectiveness improves with the addition of blank nanoparticles. This enhanced impact was verified both in vitro and in vivo. The area under the curve of the high dose group (19.5 × 1011) is 2.5 times higher than that of the low dose group (6.5 × 1011). In addition, the drug distribution of the high dose group at the tumor site was also improved by 1.5 times compared with the low dose group. The results of histopathological sections also showed that the administration of excess blank nanoparticles within 24 h has no damage to the animals. This study contributes to the clinical transition of nanomedicine by providing fresh ideas for anticancer nanomedicine research.

Mild Hyperthermia Induced by Hollow Mesoporous Prussian Blue Nanoparticles in Alliance with a Low Concentration of Hydrogen Peroxide Shows Powerful Antibacterial Effect.

The emergence of superbacteria as well as the drug resistance of the current bacteria gives rise to worry regarding a bacterial pandemic and also calls for the development of novel ways to combat the bacteria. Here in this article, we demonstrate that mild hyperthermia induced by hollow mesoporous Prussian blue nanoparticles (HMPBNPs) in alliance with a low concentration of hydrogen peroxide (H2O2) shows a powerful inhibition effect on bacteria. Our results demonstrate that this therapeutic regime could realize almost full growth inhibition of both Gram-positive (Staphylococcus aureus, S. aureus) and -negative bacteria (Escherichia coli, E. coli), as well as potent inhibition/elimination of the S. aureus biofilm. The wound healing results indicate that combination regime of the antibacterial system could be conveniently used for wound disinfection in vivo and could promote wound healing. To our limited knowledge, this is one of the few pioneer works to apply mild hyperthermia for the combat of bacteria, which provides a novel strategy to inspire future studies.

Augmented reality-guided positioning system for radiotherapy patients.

In modern radiotherapy, error reduction in the patients' daily setup error is important for achieving accuracy. In our study, we proposed a new approach for the development of an assist system for the radiotherapy position setup by using augmented reality (AR). We aimed to improve the accuracy of the position setup of patients undergoing radiotherapy and to evaluate the error of the position setup of patients who were diagnosed with head and neck cancer, and that of patients diagnosed with chest and abdomen cancer. We acquired the patient's simulation CT data for the three-dimensional (3D) reconstruction of the external surface and organs. The AR tracking software detected the calibration module and loaded the 3D virtual model. The calibration module was aligned with the Linac isocenter by using room lasers. And then aligned the virtual cube with the calibration module to complete the calibration of the 3D virtual model and Linac isocenter. Then, the patient position setup was carried out, and point cloud registration was performed between the patient and the 3D virtual model, such the patient's posture was consistent with the 3D virtual model. Twenty patients diagnosed with head and neck cancer and 20 patients diagnosed with chest and abdomen cancer in the supine position setup were analyzed for the residual errors of the conventional laser and AR-guided position setup. Results show that for patients diagnosed with head and neck cancer, the difference between the two positioning methods was not statistically significant (P > 0.05). For patients diagnosed with chest and abdomen cancer, the residual errors of the two positioning methods in the superior and inferior direction and anterior and posterior direction were statistically significant (t = -5.80, -4.98, P < 0.05). The residual errors in the three rotation directions were statistically significant (t = -2.29 to -3.22, P < 0.05). The experimental results showed that the AR technology can effectively assist in the position setup of patients undergoing radiotherapy, significantly reduce the position setup errors in patients diagnosed with chest and abdomen cancer, and improve the accuracy of radiotherapy.

Capillary electrophoretic method for Staphylococcus aureus detection by using a novel antimicrobial peptide.

A novel peptide containing antimicrobial sequence and gelatinase cleavage sites was designed for Staphylococcus aureus detection. Since Staphylococcus aureus could secrete gelatinase, the fluorescein labeled peptide GKRWWKWWRRPLGVRGC could be recognized and cleaved. The obtained products were able to be analyzed by capillary electrophoresis with fluorescence detection. To explore the effect of Staphylococcus aureus concentration on enzyme digestion ability of peptide, Staphylococcus aureus with different concentrations were incubated with the peptide. Results indicated that capillary electrophoretic method was efficient for determining Staphylococcus aureus content. Compared with traditional approaches for Staphylococcus aureus detection, capillary electrophoresis possessed higher efficiency, enhanced sensitivity, and low sample consumption. Moreover, the proposed peptide also presented desirable antimicrobial activity. It suggested that the novel antimicrobial peptide used in this research opens a new path of detecting Staphylococcus aureus by capillary electrophoretic method.

Multienzyme detection and in-situ monitoring of enzyme activity by bending CE using quantum dots-based polypeptide substrate.

Multienzyme detection and monitoring enzyme activity in situ are significant for the disease to diagnose. This study aims to develop a quantum dots (QDs)-based nanoprobe Cyanine5-DDDLEVLFQFPGLVPRGSGGHHHHHH-QDs (Cy5-LEVLVP-QD), which is able to detect two enzymes inside a bent capillary using CE. Cy5-LEVLVP and QDs were allowed to bind with each other through metal affinity interaction and then injected the Cy5-LEVLVP-QD complex into a capillary with different bends, followed by related enzyme that can cleave the Cy5-LEVLVP peptide. The fluorescence of Cy5 was excited by QDs due to Förster resonance energy transfer. By monitoring the peaks produced by the original Cy5-LEVLVP-QD complex and a significant fluorescence change, sensitive analysis of two different enzymes was conducted. Therefore, the novel approach of using capillaries with semicircular bends could prove particularly useful for enzyme investigating in disease.

Carbon Fiber-Based Flow-Through Electrode System (FES) for Water Disinfection via Direct Oxidation Mechanism with a Sequential Reduction-Oxidation Process.

Flow-through configuration for electrochemical disinfection is considered as a promising approach to minimize the formation of toxic byproducts and energy consumption via the enhanced convective mass transport as compared with conventional flow-by one. Under this hydrodynamic condition, it is essential to ascertain the effect of sequential electro-redox processes with the cathode/anode then anode/cathode arrangements on disinfection performance. Here, carbon fiber felt (CFF) was utilized to construct two flow-through electrode systems (FESs) with sequential reduction-oxidation (cathode-anode) or oxidation-reduction (anode-cathode) processes to systematically compare their disinfection performance toward a model Escherichia coli ( E. coli) pathogen. In-situ sampling and live/dead backlight staining experiments revealed that E. coli inactivation mainly occurred on anode via an adsorption-inactivation-desorption process. In reduction-oxidation system, after the cathode-pretreatment, bulk solution pH increased significantly, leading to the negative charge of E. coli cells. Hence, E. coli cells were adsorbed and inactivated easily on the subsequent anode, finally resulting in its much better disinfection performance and energy efficiency than the oxidation-reduction system. Application of 3.0 V resulted in ∼6.5 log E. coli removal at 1500 L m-2 h-1 (50 mL min-1), suggesting that portable devices can be designed from CFF-based FES with potential application for point-of-use water disinfection.

[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.

Advances in Composite Biofilm Biomimetic Nanodrug Delivery Systems for Cancer Treatment.

Single biofilm biomimetic nanodrug delivery systems based on single cell membranes, such as erythrocytes and cancer cells, have immune evasion ability, good biocompatibility, prolonged blood circulation, and high tumor targeting. Because of the different characteristics and functions of each single cell membrane, more researchers are using various hybrid cell membranes according to their specific needs. This review focuses on several different types of biomimetic nanodrug-delivery systems based on composite biofilms and looks forward to the challenges and possible development directions of biomimetic nanodrug-delivery systems based on composite biofilms to provide reference and ideas for future research.

Identification of m6A/m5C-related lncRNA signature for prediction of prognosis and immunotherapy efficacy in esophageal squamous cell carcinoma.

N6-methyladenosine (m6A) and 5-methylcytosine (m5C) RNA modifications have garnered significant attention in the field of epigenetic research due to their close association with human cancers. This study we focus on elucidating the expression patterns of m6A/m5C-related long non-coding RNAs (lncRNAs) in esophageal squamous cell carcinoma (ESCC) and assessing their prognostic significance and therapeutic potential. Transcriptomic profiles of ESCC were derived from public resources. m6A/m5C-related lncRNAs were obtained from TCGA using Spearman's correlations analysis. The m6A/m5C-lncRNAs prognostic signature was selected to construct a RiskScore model for survival prediction, and their correlation with the immune microenvironment and immunotherapy response was analyzed. A total of 606 m6A/m5C-lncRNAs were screened, and ESCC cases in the TCGA cohort were stratified into three clusters, which showed significantly distinct in various clinical features and immune landscapes. A RiskScore model comprising ten m6A/m5C-lncRNAs prognostic signature were constructed and displayed good independent prediction ability in validation datasets. Patients in the low-RiskScore group had a better prognosis, a higher abundance of immune cells (CD4 + T cell, CD4 + naive T cell, class-switched memory B cell, and Treg), and enhanced expression of most immune checkpoint genes. Importantly, patients with low-RiskScore were more cline benefit from immune checkpoint inhibitor treatment (P < 0.05). Our findings underscore the potential of RiskScore system comprising ten m6A/m5C-related lncRNAs as effective biomarkers for predicting survival outcomes, characterizing the immune landscape, and assessing response to immunotherapy in ESCC.

Nanofabrications of Erythrocyte Membrane-Coated Telmisartan Delivery System Effective for Radiosensitivity of Tumor Cells in Mice Model.

Background: Radiation stimulates the secretion of tumor stroma and induces resistance, recurrence, and metastasis of stromal-vascular tumors during radiotherapy. The proliferation and activation of tumor-associated fibroblasts (TAFs) are important reasons for the production of tumor stroma. Telmisartan (Tel) can inhibit the proliferation and activation of TAFs (resting TAFs), which may promote radiosensitization. However, Tel has a poor water solubility. Methods: In this study, self-assembled telmisartan nanoparticles (Tel NPs) were prepared by aqueous solvent diffusion method to solve the insoluble problem of Tel and achieve high drug loading of Tel. Then, erythrocyte membrane (ECM) obtained by hypotonic lysis was coated on the surface of Tel NPs (ECM/Tel) for the achievement of in vivo long circulation and tumor targeting. Immunofluorescence staining, western blot and other biological techniques were used to investigate the effect of ECM/Tel on TAFs activation inhibition (resting effect) and mechanisms involved. The multicellular spheroids (MCSs) model and mouse breast cancer cells (4T1) were constructed to investigate the effect of ECM/Tel on reducing stroma secretion, alleviating hypoxia, and the corresponding promoting radiosensitization effect in vitro. A mouse orthotopic 4T1 breast cancer model was constructed to investigate the radiosensitizing effect of ECM/Tel on inhibiting breast cancer growth and lung metastasis of breast cancer. Results: ECM/Tel showed good physiological stability and tumor-targeting ability. ECM/Tel could rest TAFs and reduce stroma secretion, alleviate hypoxia, and enhance penetration in tumor microenvironment. In addition, ECM/Tel arrested the cell cycle of 4T1 cells to the radiosensitive G2/M phase. In mouse orthotopic 4T1 breast cancer model, ECM/Tel played a superior role in radiosensitization and significantly inhibited lung metastasis of breast cancer. Conclusion: ECM/Tel showed synergistical radiosensitization effect on both the tumor microenvironment and tumor cells, which is a promising radiosensitizer in the radiotherapy of stroma-vascular tumors.

GAN-based metal artifacts region inpainting in brain MRI imaging with reflective registration.

BACKGROUND AND OBJECTIVE: Metallic magnetic resonance imaging (MRI) implants can introduce magnetic field distortions, resulting in image distortion, such as bulk shifts and signal-loss artifacts. Metal Artifacts Region Inpainting Network (MARINet), using the symmetry of brain MRI images, has been developed to generate normal MRI images in the image domain and improve image quality. METHODS: T1-weighted MRI images containing or located near the teeth of 100 patients were collected. A total of 9000 slices were obtained after data augmentation. Then, MARINet based on U-Net with a dual-path encoder was employed to inpaint the artifacts in MRI images. The input of MARINet contains the original image and the flipped registered image, with partial convolution used concurrently. Subsequently, we compared PConv with partial convolution, and GConv with gated convolution, SDEdit using a diffusion model for inpainting the artifact region of MRI images. The mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) for the mask were used to compare the results of these methods. In addition, the artifact masks of clinical MRI images were inpainted by physicians. RESULTS: MARINet could directly and effectively inpaint the incomplete MRI images generated by masks in the image domain. For the test results of PConv, GConv, SDEdit, and MARINet, the masked MAEs were 0.1938, 0.1904, 0.1876, and 0.1834, respectively, and the masked PSNRs were 17.39, 17.40, 17.49, and 17.60 dB, respectively. The visualization results also suggest that the network can recover the tissue texture, alveolar shape, and tooth contour. Additionally, for clinical artifact MRI images, MARINet completed the artifact region inpainting task more effectively when compared with other models. CONCLUSIONS: By leveraging the quasi-symmetry of brain MRI images, MARINet can directly and effectively inpaint the metal artifacts in MRI images in the image domain, restoring the tooth contour and detail, thereby enhancing the image quality.

Uncertainty estimation- and attention-based semi-supervised models for automatically delineate clinical target volume in CBCT images of breast cancer.

OBJECTIVES: Accurate segmentation of the clinical target volume (CTV) of CBCT images can observe the changes of CTV during patients' radiotherapy, and lay a foundation for the subsequent implementation of adaptive radiotherapy (ART). However, segmentation is challenging due to the poor quality of CBCT images and difficulty in obtaining target volumes. An uncertainty estimation- and attention-based semi-supervised model called residual convolutional block attention-uncertainty aware mean teacher (RCBA-UAMT) was proposed to delineate the CTV in cone-beam computed tomography (CBCT) images of breast cancer automatically. METHODS: A total of 60 patients who undergone radiotherapy after breast-conserving surgery were enrolled in this study, which involved 60 planning CTs and 380 CBCTs. RCBA-UAMT was proposed by integrating residual and attention modules in the backbone network 3D UNet. The attention module can adjust channel and spatial weights of the extracted image features. The proposed design can train the model and segment CBCT images with a small amount of labeled data (5%, 10%, and 20%) and a large amount of unlabeled data. Four types of evaluation metrics, namely, dice similarity coefficient (DSC), Jaccard, average surface distance (ASD), and 95% Hausdorff distance (95HD), are used to assess the model segmentation performance quantitatively. RESULTS: The proposed method achieved average DSC, Jaccard, 95HD, and ASD of 82%, 70%, 8.93, and 1.49 mm for CTV delineation on CBCT images of breast cancer, respectively. Compared with the three classical methods of mean teacher, uncertainty-aware mean-teacher and uncertainty rectified pyramid consistency, DSC and Jaccard increased by 7.89-9.33% and 14.75-16.67%, respectively, while 95HD and ASD decreased by 33.16-67.81% and 36.05-75.57%, respectively. The comparative experiment results of the labeled data with different proportions (5%, 10% and 20%) showed significant differences in the DSC, Jaccard, and 95HD evaluation indexes in the labeled data with 5% versus 10% and 5% versus 20%. Moreover, no significant differences were observed in the labeled data with 10% versus 20% among all evaluation indexes. Therefore, we can use only 10% labeled data to achieve the experimental objective. CONCLUSIONS: Using the proposed RCBA-UAMT, the CTV of breast cancer CBCT images can be delineated reliably with a small amount of labeled data. These delineated images can be used to observe the changes in CTV and lay the foundation for the follow-up implementation of ART.

A 4D-CBCT correction network based on contrastive learning for dose calculation in lung cancer.

OBJECTIVE: This study aimed to present a deep-learning network called contrastive learning-based cycle generative adversarial networks (CLCGAN) to mitigate streak artifacts and correct the CT value in four-dimensional cone beam computed tomography (4D-CBCT) for dose calculation in lung cancer patients. METHODS: 4D-CBCT and 4D computed tomography (CT) of 20 patients with locally advanced non-small cell lung cancer were used to paired train the deep-learning model. The lung tumors were located in the right upper lobe, right lower lobe, left upper lobe, and left lower lobe, or in the mediastinum. Additionally, five patients to create 4D synthetic computed tomography (sCT) for test. Using the 4D-CT as the ground truth, the quality of the 4D-sCT images was evaluated by quantitative and qualitative assessment methods. The correction of CT values was evaluated holistically and locally. To further validate the accuracy of the dose calculations, we compared the dose distributions and calculations of 4D-CBCT and 4D-sCT with those of 4D-CT. RESULTS: The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) of the 4D-sCT increased from 87% and 22.31 dB to 98% and 29.15 dB, respectively. Compared with cycle consistent generative adversarial networks, CLCGAN enhanced SSIM and PSNR by 1.1% (p < 0.01) and 0.42% (p < 0.01). Furthermore, CLCGAN significantly decreased the absolute mean differences of CT value in lungs, bones, and soft tissues. The dose calculation results revealed a significant improvement in 4D-sCT compared to 4D-CBCT. CLCGAN was the most accurate in dose calculations for left lung (V5Gy), right lung (V5Gy), right lung (V20Gy), PTV (D98%), and spinal cord (D2%), with the relative dose difference were reduced by 6.84%, 3.84%, 1.46%, 0.86%, 3.32% compared to 4D-CBCT. CONCLUSIONS: Based on the satisfactory results obtained in terms of image quality, CT value measurement, it can be concluded that CLCGAN-based corrected 4D-CBCT can be utilized for dose calculation in lung cancer.