A deep learning and radiomics based Alberta stroke program early CT score method on CTA to evaluate acute ischemic stroke.

BACKGROUND: Alberta stroke program early CT score (ASPECTS) is a semi-quantitative evaluation method used to evaluate early ischemic changes in patients with acute ischemic stroke, which can guide physicians in treatment decisions and prognostic judgments. OBJECTIVE: We propose a method combining deep learning and radiomics to alleviate the problem of large inter-observer variance in ASPECTS faced by physicians and assist them to improve the accuracy and comprehensiveness of the ASPECTS. METHODS: Our study used a brain region segmentation method based on an improved encoding-decoding network. Through the deep convolutional neural network, 10 regions defined for ASPECTS will be obtained. Then, we used Pyradiomics to extract features associated with cerebral infarction and select those significantly associated with stroke to train machine learning classifiers to determine the presence of cerebral infarction in each scored brain region. RESULTS: The experimental results show that the Dice coefficient for brain region segmentation reaches 0.79. Three radioactive features are selected to identify cerebral infarction in brain regions, and the 5-fold cross-validation experiment proves that these 3 features are reliable. The classifier trained based on 3 features reaches prediction performance of AUC = 0.95. Moreover, the intraclass correlation coefficient of ASPECTS between those obtained by the automated ASPECTS method and physicians is 0.86 (95% confidence interval, 0.56-0.96). CONCLUSIONS: This study demonstrates advantages of using a deep learning network to replace the traditional template registration for brain region segmentation, which can determine the shape and location of each brain region more precisely. In addition, a new brain region classifier based on radiomics features has potential to assist physicians in clinical stroke detection and improve the consistency of ASPECTS.

Accelerating image reconstruction for multi-contrast MRI based on Y-Net3.

BACKGROUND: As one of the significant preoperative imaging modalities in medical diagnosis, Magnetic resonance imaging (MRI) takes a long scanning time due to its special imaging principle. OBJECTIVE: We propose an innovative MRI reconstruction strategy and data consistency method based on deep learning to reconstruct high-quality brain MRIs from down-sampled data and accelerate the MR imaging process. METHODS: Sixteen healthy subjects undergoing T1-weighted spin-echo (SE) and T2-weighted fast spin-echo (FSE) sequences by a 1.5T MRI scanner were recruited. A Y-Net3+ network was used to facilitate the high-quality MRI reconstruction through context information. In addition, the existing data consistency fidelity method was improved. The difference between the reconstructed K-space and the original K-space was shorten by the linear regression algorithm. Therefore, the redundant artifacts derived from under-sampling were avoided. The Structural Similarity (SSIM) and Peak Signal to Noise Ratio (PSNR) were applied to quantitatively evaluate image reconstruction performance of different down-sampling patterns. RESULTS: Compared with the classical Y-Net, Y-Net3+ network improved SSIM and PSNR of MRI images from 0.9164±0.0178 and 33.2216±3.2919 to 0.9387±0.0363 and 35.1785±3.3105, respectively, under compressed sensing reconstruction with acceleration factor of 4. The improved network increases signal-to-noise ratio and adds more image texture information in the reconstructed images. Furthermore, in the process of data consistency, linear regression analysis was used to reduce the difference between the reconstructed K-space and the original K-space, so that the SSIM and PSNR were increased to 0.9808±0.0081 and 40.9254±1.1911, respectively. CONCLUSIONS: The improved Y-Net combined with data consistency fidelity method elucidates its potential in reconstructing high-quality T2-weighted images from the down-sampled data by fully exploring the T1-weighted information. With the advantage of avoiding down-sampled artifacts, the improved network exhibits remarkable clinical promise for fast MRI applications.

Corticosteroid treatment in severe patients with SARS-CoV-2 and chronic HBV co-infection: a retrospective multicenter study.

BACKGROUND: The impact of corticosteroids on patients with severe coronavirus disease 2019 (COVID-19)/chronic hepatitis B virus (HBV) co-infection is currently unknown. We aimed to investigate the association of corticosteroids on these patients. METHODS: This retrospective multicenter study screened 5447 confirmed COVID-19 patients hospitalized between Jan 1, 2020 to Apr 18, 2020 in seven centers in China, where the prevalence of chronic HBV infection is moderate to high. Severe patients who had chronic HBV and acute SARS-cov-2 infection were potentially eligible. The diagnosis of chronic HBV infection was based on positive testing for hepatitis B surface antigen (HBsAg) or HBV DNA during hospitalization and a medical history of chronic HBV infection. Severe patients (meeting one of following criteria: respiratory rate > 30 breaths/min; severe respiratory distress; or SpO2 ≤ 93% on room air; or oxygen index < 300 mmHg) with COVID-19/HBV co-infection were identified. The bias of confounding variables on corticosteroids effects was minimized using multivariable logistic regression model and inverse probability of treatment weighting (IPTW) based on propensity score. RESULTS: The prevalence of HBV co-infection in COVID-19 patients was 4.1%. There were 105 patients with severe COVID-19/HBV co-infections (median age 62 years, 57.1% male). Fifty-five patients received corticosteroid treatment and 50 patients did not. In the multivariable analysis, corticosteroid therapy (OR, 6.32, 95% CI 1.17-34.24, P = 0.033) was identified as an independent risk factor for 28-day mortality. With IPTW analysis, corticosteroid treatment was associated with delayed SARS-CoV-2 viral RNA clearance (OR, 2.95, 95% CI 1.63-5.32, P < 0.001), increased risk of 28-day and in-hospital mortality (OR, 4.90, 95% CI 1.68-14.28, P = 0.004; OR, 5.64, 95% CI 1.95-16.30, P = 0.001, respectively), and acute liver injury (OR, 4.50, 95% CI 2.57-7.85, P < 0.001). Methylprednisolone dose per day and cumulative dose in non-survivors were significantly higher than in survivors. CONCLUSIONS: In patients with severe COVID-19/HBV co-infection, corticosteroid treatment may be associated with increased risk of 28-day and in-hospital mortality.

Diagnostic performance of MRI for detecting intraplaque hemorrhage in the carotid arteries: a meta-analysis.

OBJECTIVES: To investigate the diagnostic performance of MRI in diagnosing carotid atherosclerotic intraplaque hemorrhage (IPH) and to provide a clinical guide for MRI application. METHODS: We searched MEDLINE, Embase, and Cochrane library from the earliest available date of indexing through November 30, 2017. All investigators screened and selected studies comparing the use of MRI with histology. The accuracy to diagnose pathological IPH was expressed by sensitivity, specificity, negative likelihood ratios (LRs), positive LRs, and the area under summary receiver-operating characteristic (SROC) curve. We calculated the post-test probability to assess the clinical utility of MRI. RESULTS: We analyzed 696 patients from 20 articles. The sensitivity and specificity were 87% (95% CI, 81-91%) and 92% (95% CI, 87-95%), respectively. The positive and negative LRs were 10.27 (95% CI, 6.76-15.59) and 0.15 (95% CI, 0.10-0.21), respectively. The area under SROC curve was 0.95 (95% CI, 0.93-0.97). MRI was accurate in confirming or in ruling out disease over a wide range of pre-test probabilities of IPH: MRI could increase the post-test probability to > 80% in patients with a pre-test probability > 27% and could decrease the post-test probability to < 20% in patients with a pre-test probability < 64%. CONCLUSION: Non-invasive MRI has excellent specificity and good sensitivity for diagnosing IPH. MRI is a tool for confirming or ruling out carotid atherosclerotic IPH. KEY POINTS: • Non-invasive MRI has excellent performance for diagnosing IPH, which is a component of vulnerable plaque. • The high accuracy of MRI for IPH helps clinicians analyze the prognosis of clinical events and plan personalized treatment.

Automatic assessment of DWI-ASPECTS for acute ischemic stroke based on deep learning.

BACKGROUND: Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a standardized semi-quantitative method for early ischemic changes in acute ischemic stroke. PURPOSE: However, ASPECTS is still affected by expert experience and inconsistent results between readers in clinical. This study aims to propose an automatic ASPECTS scoring model based on diffusion-weighted imaging (DWI) mode to help clinicians make accurate treatment plans. METHODS: Eighty-two patients with stroke were included in the study. First, we designed a new deep learning network for segmenting ASPECTS scoring brain regions. The network is improved based on U-net, which integrates multiple modules. Second, we proposed using hybrid classifiers to classify brain regions. For brain regions with larger areas, we used brain grayscale comparison algorithm to train machine learning classifiers, while using hybrid feature training for brain regions with smaller areas. RESULTS: The average DICE coefficient of the segmented hindbrain area can reach 0.864. With the proposed hybrid classifier, our method performs significantly on both region-level ASPECTS and dichotomous ASPECTS. The sensitivity and accuracy on the test set are 95.51% and 93.43%, respectively. For dichotomous ASPECTS, the intraclass correlation coefficient (ICC) between our automated ASPECTS score and the expert reading was 0.87. CONCLUSIONS: This study proposed an automated model for ASPECTS scoring of patients with acute ischemic stroke based on DWI images. Experimental results show that the method of segmentation first and then classification is feasible. Our method has the potential to assist physicians in the Alberta Stroke Program with early CT scoring and clinical stroke diagnosis.

Automated Cerebrovascular Segmentation and Visualization of Intracranial Time-of-Flight Magnetic Resonance Angiography Based on Deep Learning.

Time-of-flight magnetic resonance angiography (TOF-MRA) is a non-contrast technique used to visualize neurovascular. However, manual reconstruction of the volume render (VR) by radiologists is time-consuming and labor-intensive. Deep learning-based (DL-based) vessel segmentation technology may provide intelligent automation workflow. To evaluate the image quality of DL vessel segmentation for automatically acquiring intracranial arteries in TOF-MRA. A total of 394 TOF-MRA scans were selected, which included cerebral vascular health, aneurysms, or stenoses. Both our proposed method and two state-of-the-art DL methods are evaluated on external datasets for generalization ability. For qualitative assessment, two experienced clinical radiologists evaluated the image quality of cerebrovascular diagnostic and visualization (scoring 0-5 as unacceptable to excellent) obtained by manual VR reconstruction or automatic convolutional neural network (CNN) segmentation. The proposed CNN outperforms the other two DL-based methods in clinical scoring on external datasets, and its visualization was evaluated by readers as having the appearance of the radiologists' manual reconstructions. Scoring of proposed CNN and VR of intracranial arteries demonstrated good to excellent agreement with no significant differences (median, 5.0 and 5.0, P ≥ 12) at healthy-type scans. All proposed CNN image quality were considered to have adequate diagnostic quality (median scores > 2). Quantitative analysis demonstrated a superior dice similarity coefficient of cerebrovascular overlap (training sets and validation sets; 0.947 and 0.927). Automatic cerebrovascular segmentation using DL is feasible and the image quality in terms of vessel integrity, collateral circulation and lesion morphology is comparable to expert manual VR without significant differences.

Feature Fusion for Multi-Coil Compressed MR Image Reconstruction.

Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI's principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called "Multi-coil Feature Fusion Variation Network" (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622 dB and 0.0021 dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network's architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.

Robot-Assisted Ocular Tumour Radiotherapy Positioning and Tracking System.

BACKGROUND: Precise dose position distribution is crucial for ocular proton therapy. METHODS: A non-invasive eye positioning and tracking system with novel structure is designed to reduce eye movement and facilitate precise dose by guiding the direction of patients' gaze. The system helps to achieve gaze guidance by controlling the light source fixed on two turntables above the patient's face. Tracking of the eye is achieved by cameras attached to the end of a 6DOFs robotic arm to capture the image reflected from a mirror above the patient's face. RESULTS: After all operation steps, the accuracy of the robotic arm is 0.18 mm (SD 0.25 mm) and the accuracy of the turntables is 0.01° (SD 0.02°). The EPTS is tested to be remotely controlled in real time with sufficient precision and repeatability. CONCLUSION: The system is expected to improve the safety and efficiency of ocular proton therapy.

Prognostic value and drug sensitivity of F­box and leucine­rich repeat protein 6 in glioma.

Gliomas are highly malignant and invasive tumors lacking clear boundaries. Previous bioinformatics and experimental analyses have indicated that F-box and leucine-rich repeat protein 6 (FBXL6), a protein crucial for the cell cycle and tumorigenesis, is highly expressed in certain types of tumors. The high expression level of FBXL6 is reported to promote tumor growth and adversely affect patient survival. However, the molecular mechanism, prognostic value and drug sensitivity of FBXL6 in glioma remain unclear. To address this, the present study analyzed FBXL6 expression in gliomas, utilizing data from The Cancer Genome Atlas and Chinese Glioma Genome Atlas databases. Analysis of FBXL6 mRNA expression levels, combined with patient factors such as age, sex and tumor grade using Kaplan-Meier plots and nomograms, demonstrated a strong correlation between FBXL6 expression and glioma progression. Co-expression networks provided further insights into the biological function of FBXL6. Additionally, using CIBERSORT and TISDB tools, the correlation between FBXL6 expression correlation tumor-infiltrating immune cells and immune genes was demonstrated to be statistically significant. These findings were validated by examining FBXL6 mRNA and protein levels in glioma tissues using various techniques, including western blot, reverse transcription-quantitative PCR and immunohistochemistry. These assays demonstrated the role of FBXL6 in glioma progression. Furthermore, drug sensitivity analysis demonstrated a strong correlation between FBXL6 expression and various drugs, which indicated that FBXL6 may potentially act as a future promising therapeutic target in glioma treatment. Therefore, the present study identified FBXL6 as a diagnostic and prognostic marker in patients with gliomas and highlighted its potential role in glioma progression.

Robot-assisted system for non-invasive wide-range flexible eye positioning and tracking in particle radiotherapy.

Particle (proton, carbon ion, or others) radiotherapy for ocular tumors is highly dependent on precise dose distribution, and any misalignment can result in severe complications. The proposed eye positioning and tracking system (EPTS) was designed to non-invasively position eyeballs and is reproducible enough to ensure accurate dose distribution by guiding gaze direction and tracking eye motion. Eye positioning was performed by guiding the gaze direction with separately controlled light sources. Eye tracking was performed by a robotic arm with cameras and a mirror. The cameras attached to its end received images through mirror reflection. To maintain a light weight, certain materials, such as carbon fiber, were utilized where possible. The robotic arm was controlled by a robot operating system. The robotic arm, turntables, and light source were actively and remotely controlled in real time. The videos captured by the cameras could be annotated, saved, and loaded into software. The available range of gaze guidance is 360° (azimuth). Weighing a total of 18.55 kg, the EPTS could be installed or uninstalled in 10 s. The structure, motion, and electromagnetic compatibility were verified via experiments. The EPTS shows some potential due to its non-invasive wide-range flexible eye positioning and tracking, light weight, non-collision with other equipment, and compatibility with CT imaging and dose delivery. The EPTS can also be remotely controlled in real time and offers sufficient reproducibility. This system is expected to have a positive impact on ocular particle radiotherapy.

Enhancing prostate cancer segmentation on multiparametric magnetic resonance imaging with background information and gland masks.

BACKGROUND: The landscape of prostate cancer (PCa) segmentation within multiparametric magnetic resonance imaging (MP-MRI) was fragmented, with a noticeable lack of consensus on incorporating background details, culminating in inconsistent segmentation outputs. Given the complex and heterogeneous nature of PCa, conventional imaging segmentation algorithms frequently fell short, prompting the need for specialized research and refinement. PURPOSE: This study sought to dissect and compare various segmentation methods, emphasizing the role of background information and gland masks in achieving superior PCa segmentation. The goal was to systematically refine segmentation networks to ascertain the most efficacious approach. METHODS: A cohort of 232 patients (ages 61-73 years old, prostate-specific antigen: 3.4-45.6 ng/mL), who had undergone MP-MRI followed by prostate biopsies, was analyzed. An advanced segmentation model, namely Attention-Unet, which combines U-Net with attention gates, was employed for training and validation. The model was further enhanced through a multiscale module and a composite loss function, culminating in the development of Matt-Unet. Performance metrics included Dice Similarity Coefficient (DSC) and accuracy (ACC). RESULTS: The Matt-Unet model, which integrated background information and gland masks, outperformed the baseline U-Net model using raw images, yielding significant gains (DSC: 0.7215 vs. 0.6592; ACC: 0.8899 vs. 0.8601, p < 0.001). CONCLUSION: A targeted and practical PCa segmentation method was designed, which could significantly improve PCa segmentation on MP-MRI by combining background information and gland masks. The Matt-Unet model showcased promising capabilities for effectively delineating PCa, enhancing the precision of MP-MRI analysis.

Joint two-stage convolutional neural networks for intracranial aneurysms detection on 3D TOF-MRA.

Objective. This study aims to develop a three-dimensional convolutional neural network utilizing computer-aided diagnostic technology to facilitate the detection of intracranial aneurysms and automatically assess their location and extent, thereby enhancing the efficiency of radiologists, and streamlining clinical workflows.Approach. A retrospective study was conducted, proposing a joint segmentation and classification network (JSCD-Net) that employs 3D time-of-flight magnetic resonance angiography images for preliminary detection of aneurysms and the minimization of false positives. Specifically, the U-Net++ network was utilized for pre-detection of aneurysms. This was followed by the creation of a multi-path network, co-trained with U-Net++ to correct the results of the first stage to further reduce the rate of false positives. Model effectiveness and robustness were evaluated using sensitivity and false positive analyses on internal and external datasets. A cross-validated free-response receiver operating characteristic curve was also plotted.Main results. JSCD-Net demonstrated a sensitivity of 91.2% (31 of 34; 95% CI: 77.0, 97.0) with an average of 3.55 false positives per scan on the internal test set. For the external test set, it identified 97.2% (70 of 72; 95% CI: 90.4, 99.2) of aneurysms with an average of 2.7 false positives per scan.Significance. When compared with the existing studies, the proposed model shows high sensitivity in detecting intracranial aneurysms with a reasonable number of false positives per case. This result emphasizes the model's potential as a valuable tool in aiding clinical diagnoses.

Significance of cuproptosis- related genes in the diagnosis and classification of psoriasis.

Cuproptosis is a novel form of cell death linked to mitochondrial metabolism and is mediated by protein lipoylation. The mechanism of cuproptosis in many diseases, such as psoriasis, remains unclear. In this study, signature diagnostic markers of cuproptosis were screened by differential analysis between psoriatic and non-psoriatic patients. The differentially expressed cuproptosis-related genes (CRGs) for patients with psoriasis were screened using the GSE178197 dataset from the gene expression omnibus database. The biological roles of CRGs were identified by GO and KEGG enrichment analyses, and the candidates of cuproptosis-related regulators were selected from a nomogram model. The consensus clustering approach was used to classify psoriasis into clusters and the principal component analysis algorithms were constructed to calculate the cuproptosis score. Finally, latent diagnostic markers and drug sensitivity were analyzed using the pRRophetic R package. The differential analysis revealed that CRGs (MTF1, ATP7B, and SLC31A1) are significantly expressed in psoriatic patients. GO and KEGG enrichment analyses showed that the biological functions of CRGs were mainly related to acetyl-CoA metabolic processes, the mitochondrial matrix, and acyltransferase activity. Compared to the machine learning method used, the random forest model has higher accuracy in the occurrence of cuproptosis. However, the decision curve of the candidate cuproptosis regulators analysis showed that patients can benefit from the nomogram model. The consensus clustering analysis showed that psoriasis can be grouped into three patterns of cuproptosis (clusterA, clusterB, and clusterC) based on selected important regulators of cuproptosis. In advance, we analyzed the immune characteristics of patients and found that clusterA was associated with T cells, clusterB with neutrophil cells, and clusterC predominantly with B cells. Drug sensitivity analysis showed that three cuproptosis regulators (ATP7B, SLC31A1, and MTF1) were associated with the drug sensitivity. This study provides insight into the specific biological functions and related mechanisms of CRGs in the development of psoriasis and indicates that cuproptosis plays a non-negligible role. These results may help guide future treatment strategies for psoriasis.

Clinical application of computed tomography angiography and fractional flow reserve computed tomography in patients with coronary artery disease: A meta-analysis based on pre- and post-test probability.

PURPOSE: To assess the diagnostic role of coronary computed tomography angiography (CCTA) and fractional flow reserve computed tomography (FFRCT) in confirming or excluding ischemic coronary artery disease (CAD) and to provide a rational use of CCTA and FFRCT in different pre-test probability (PTP) of CAD. METHODS: We searched the electronic databases from the earliest relevant literature to July 2020 comparing FFRCT or CCTA with FFR. The bivariate random-effects models and Bayes' theorem were used to investigate the diagnostic performance of CCTA and FFRCT with the sensitivity, specificity, pre- and post-test probability. RESULTS: Fifty-three articles with 4817 patients and 7026 vessels finally met our inclusion criteria. At the patient level, the sensitivity and specificity of CCTA were (0.94, 0.89-0.97), and (0.50, 0.43-0.58), respectively. For FFRCT, the sensitivity and specificity were (0.90, 0.87-0.93) and (0.81, 0.73-0.87). CCTA or FFRCT could increase the post-test probability to >85 % in patients with a PTP > 74.9 % or 54.5 %; CCTA or FFRCT could decrease the post-test probability to <15 % in patients with a pre-test probability <61.3 % or 59.3 %. CONCLUSIONS: In patients with low to intermediate PTP, CCTA is suggested to exclude CAD, while the time-consuming calculation of FFRCT may be unnecessary. If CCTA detects significant or uncertain stenosis with intermediate to high PTP of CAD, further FFRCT is suggested. The advantages of FFRCT for guiding CAD treatment have sufficiently been demonstrated.