RESUMO
OBJECTIVE: Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost. METHODS: In this work, we propose a novel training strategy for IMplicit UNrolled NEtworks (IMUNNE) for highly-undersampled, multi-coil dynamic MRI reconstruction. It formulates the MRI reconstruction problem as an implicit fixed-point equation and leverages gradient approximation for backpropagation, enabling training of deep architectures with fixed memory cost. This study represents the first application of implicit network theory in the context of real-time cine MRI. The proposed method is evaluated using a prospectively undersampled, real-time cine dataset using radial k-space sampling, comprising balanced steady-state free precession (b-SSFP) readouts. Experiments include a hyperparameter search, head-to-head comparisons with a complex U-Net (CU-Net) and an alternating unrolled network (Alt-UN), and an analysis of robustness under noise perturbations; peak signal-to-noise ratio, structural similarity index, normalized root mean-square error, spatio-temporal entropic difference, and a blur metric were used. RESULTS: IMUNNE produced significantly and slightly better image quality compared to CU-Net and Alt-UN, respectively. Compared with Alt-UN, IMUNNE significantly reduced training and inference times, making it a promising approach for highly-accelerated, multi-coil real-time cine MRI reconstruction. CONCLUSION: IMUNNE strategy successfully applies unrolled networks to image reconstruction of highly-accelerated, real-time radial cine MRI. SIGNIFICANCE: Implicit training enables rapid, high-quality, and cost-effective CMR exams by reducing training and inference times and lowering memory cost associated with advanced reconstruction methods.
RESUMO
While single-shot late gadolinium enhancement (LGE) is useful for imaging patients with arrhythmia and/or dyspnea, it produces low spatial resolution. One approach to improve spatial resolution is to accelerate data acquisition using compressed sensing (CS). Our previous work described a single-shot, multi-inversion time (TI) LGE pulse sequence using radial k-space sampling and CS, but over-regularization resulted in significant image blurring that muted the benefits of data acceleration. The purpose of the present study was to improve the spatial resolution of the single-shot, multi-TI LGE pulse sequence by incorporating view sharing (VS) and k-space weighted contrast (KWIC) filtering into a GRASP-Pro reconstruction. In 24 patients (mean age = 61 ± 16 years; 9/15 females/males), we compared the performance of our improved multi-TI LGE and standard multi-TI LGE, where clinical standard LGE was used as a reference. Two clinical raters independently graded multi-TI images and clinical LGE images visually on a five-point Likert scale (1, nondiagnostic; 3, clinically acceptable; 5, best) for three categories: the conspicuity of myocardium or scar, artifact, and noise. The summed visual score (SVS) was defined as the sum of the three scores. Myocardial scar volume was quantified using the full-width at half-maximum method. The SVS was not significantly different between clinical breath-holding LGE (median 13.5, IQR 1.3) and multi-TI LGE (median 12.5, IQR 1.6) (P = 0.068). The myocardial scar volumes measured from clinical standard LGE and multi-TI LGE were strongly correlated (coefficient of determination, R2 = 0.99) and in good agreement (mean difference = 0.11%, lower limit of the agreement = -2.13%, upper limit of the agreement = 2.34%). The inter-rater agreement in myocardial scar volume quantification was strong (intraclass correlation coefficient = 0.79). The incorporation of VS and KWIC into GRASP-Pro improved spatial resolution. Our improved 25-fold accelerated, single-shot LGE sequence produces clinically acceptable image quality, multi-TI reconstruction, and accurate myocardial scar volume quantification.
Assuntos
Meios de Contraste , Gadolínio , Masculino , Feminino , Humanos , Pessoa de Meia-Idade , Idoso , Cicatriz/patologia , Imageamento por Ressonância Magnética/métodos , Miocárdio/patologiaRESUMO
Tissue phase mapping (TPM) is an MRI technique for quantification of regional biventricular myocardial velocities. Despite its potential, clinical use is limited due to the requisite labor-intensive manual segmentation of cardiac contours for all time frames. The purpose of this study was to develop a deep learning (DL) network for automated segmentation of TPM images, without significant loss in segmentation and myocardial velocity quantification accuracy compared with manual segmentation. We implemented a multi-channel 3D (three dimensional; 2D + time) dense U-Net that trained on magnitude and phase images and combined cross-entropy, Dice, and Hausdorff distance loss terms to improve the segmentation accuracy and suppress unnatural boundaries. The dense U-Net was trained and tested with 150 multi-slice, multi-phase TPM scans (114 scans for training, 36 for testing) from 99 heart transplant patients (44 females, 1-4 scans/patient), where the magnitude and velocity-encoded (Vx , Vy , Vz ) images were used as input and the corresponding manual segmentation masks were used as reference. The accuracy of DL segmentation was evaluated using quantitative metrics (Dice scores, Hausdorff distance) and linear regression and Bland-Altman analyses on the resulting peak radial and longitudinal velocities (Vr and Vz ). The mean segmentation time was about 2 h per patient for manual and 1.9 ± 0.3 s for DL. Our network produced good accuracy (median Dice = 0.85 for left ventricle (LV), 0.64 for right ventricle (RV), Hausdorff distance = 3.17 pixels) compared with manual segmentation. Peak Vr and Vz measured from manual and DL segmentations were strongly correlated (R ≥ 0.88) and in good agreement with manual analysis (mean difference and limits of agreement for Vz and Vr were -0.05 ± 0.98 cm/s and -0.06 ± 1.18 cm/s for LV, and -0.21 ± 2.33 cm/s and 0.46 ± 4.00 cm/s for RV, respectively). The proposed multi-channel 3D dense U-Net was capable of reducing the segmentation time by 3,600-fold, without significant loss in accuracy in tissue velocity measurements.
Assuntos
Aprendizado Profundo , Ventrículos do Coração/diagnóstico por imagem , Imagem Cinética por Ressonância Magnética/métodos , Adulto , Idoso , Feminino , Transplante de Coração , Humanos , Masculino , Pessoa de Meia-IdadeRESUMO
Highly accelerated real-time cine MRI using compressed sensing (CS) is a promising approach to achieve high spatio-temporal resolution and clinically acceptable image quality in patients with arrhythmia and/or dyspnea. However, its lengthy image reconstruction time may hinder its clinical translation. The purpose of this study was to develop a neural network for reconstruction of non-Cartesian real-time cine MRI k-space data faster (<1 min per slice with 80 frames) than graphics processing unit (GPU)-accelerated CS reconstruction, without significant loss in image quality or accuracy in left ventricular (LV) functional parameters. We introduce a perceptual complex neural network (PCNN) that trains on complex-valued MRI signal and incorporates a perceptual loss term to suppress incoherent image details. This PCNN was trained and tested with multi-slice, multi-phase, cine images from 40 patients (20 for training, 20 for testing), where the zero-filled images were used as input and the corresponding CS reconstructed images were used as practical ground truth. The resulting images were compared using quantitative metrics (structural similarity index (SSIM) and normalized root mean square error (NRMSE)) and visual scores (conspicuity, temporal fidelity, artifacts, and noise scores), individually graded on a five-point scale (1, worst; 3, acceptable; 5, best), and LV ejection fraction (LVEF). The mean processing time per slice with 80 frames for PCNN was 23.7 ± 1.9 s for pre-processing (Step 1, same as CS) and 0.822 ± 0.004 s for dealiasing (Step 2, 166 times faster than CS). Our PCNN produced higher data fidelity metrics (SSIM = 0.88 ± 0.02, NRMSE = 0.014 ± 0.004) compared with CS. While all the visual scores were significantly different (P < 0.05), the median scores were all 4.0 or higher for both CS and PCNN. LVEFs measured from CS and PCNN were strongly correlated (R2 = 0.92) and in good agreement (mean difference = -1.4% [2.3% of mean]; limit of agreement = 10.6% [17.6% of mean]). The proposed PCNN is capable of rapid reconstruction (25 s per slice with 80 frames) of non-Cartesian real-time cine MRI k-space data, without significant loss in image quality or accuracy in LV functional parameters.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Imagem Cinética por Ressonância Magnética , Redes Neurais de Computação , Idoso , Compressão de Dados , Feminino , Humanos , MasculinoRESUMO
PURPOSE: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)-based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non-contrast material-enhanced MR angiographic k-space data faster than a central processing unit (CPU)-based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel-diameter measurements. MATERIALS AND METHODS: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years ± 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source three-dimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. RESULTS: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds ± 40.5 and 204.9 seconds ± 40.5), respectively, than for CS (14 152.3 seconds ± 1708.6) (P < .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 ± 0.02, NRMSE = 2.8% ± 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). CONCLUSION: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing time-resolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non-contrast-enhanced MR angiograms. Supplemental material is available for this article. © RSNA, 2020.
RESUMO
Compressed sensing (CS) is a promising method for accelerating cardiac perfusion MRI to achieve clinically acceptable image quality with high spatial resolution (1.6 × 1.6 × 8 mm3 ) and extensive myocardial coverage (6-8 slices per heartbeat). A major disadvantage of CS is its relatively lengthy processing time (~8 min per slice with 64 frames using a graphics processing unit), thereby making it impractical for clinical translation. The purpose of this study was to implement and test whether an image reconstruction pipeline including a neural network is capable of reconstructing 6.4-fold accelerated, non-Cartesian (radial) cardiac perfusion k-space data at least 10 times faster than CS, without significant loss in image quality. We implemented a 3D (2D + time) U-Net and trained it with 132 2D + time datasets (coil combined, zero filled as input; CS reconstruction as reference) with 64 time frames from 28 patients (8448 2D images in total). For testing, we used 56 2D + time coil-combined, zero-filled datasets (3584 2D images in total) from 12 different patients as input to our trained U-Net, and compared the resulting images with CS reconstructed images using quantitative metrics of image quality and visual scores (conspicuity of wall enhancement, noise, artifacts; each score ranging from 1 (worst) to 5 (best), with 3 defined as clinically acceptable) evaluated by readers. Including pre- and post-processing steps, compared with CS, U-Net significantly reduced the reconstruction time by 14.4-fold (32.1 ± 1.4 s for U-Net versus 461.3 ± 16.9 s for CS, p < 0.001), while maintaining high data fidelity (structural similarity index = 0.914 ± 0.023, normalized root mean square error = 1.7 ± 0.3%, identical mean edge sharpness of 1.2 mm). The median visual summed score was not significantly different (p = 0.053) between CS (14; interquartile range (IQR) = 0.5) and U-Net (12; IQR = 0.5). This study shows that the proposed pipeline with a U-Net is capable of reconstructing 6.4-fold accelerated, non-Cartesian cardiac perfusion k-space data 14.4 times faster than CS, without significant loss in data fidelity or image quality.
Assuntos
Coração/diagnóstico por imagem , Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , Perfusão , Feminino , Humanos , Imageamento Tridimensional , Masculino , Pessoa de Meia-IdadeRESUMO
Retrospective electrocardiogram-gated, 2D phase-contrast (PC) flow MRI is routinely used in clinical evaluation of valvular/vascular disease in pediatric patients with congenital heart disease (CHD). In patients not requiring general anesthesia, clinical standard PC is conducted with free breathing for several minutes per slice with averaging. In younger patients under general anesthesia, clinical standard PC is conducted with breath-holding. One approach to overcome this limitation is using either navigator gating or self-navigation of respiratory motion, at the expense of lengthening scan times. An alternative approach is using highly accelerated, free-breathing, real-time PC (rt-PC) MRI, which to date has not been evaluated in CHD patients. The purpose of this study was to develop a 38.4-fold accelerated 2D rt-PC pulse sequence using radial k-space sampling and compressed sensing with 1.5 × 1.5 × 6.0 mm3 nominal spatial resolution and 40 ms nominal temporal resolution, and evaluate whether it is capable of accurately measuring flow in 17 pediatric patients (aortic valve, pulmonary valve, right and left pulmonary arteries) compared with clinical standard 2D PC (either breath-hold or free breathing). For clinical translation, we implemented an integrated reconstruction pipeline capable of producing DICOMs of the order of 2 min per time series (46 frames). In terms of association, forward volume, backward volume, regurgitant fraction, and peak velocity at peak systole measured with standard PC and rt-PC were strongly correlated (R2 > 0.76; P < 0.001). Compared with clinical standard PC, in terms of agreement, forward volume (mean difference = 1.4% (3.0% of mean)) and regurgitant fraction (mean difference = -2.5%) were in good agreement, whereas backward volume (mean difference = -1.1 mL (28.2% of mean)) and peak-velocity at peak systole (mean difference = -21.3 cm/s (17.2% of mean)) were underestimated by rt-PC. This study demonstrates that the proposed rt-PC with the said spatial resolution and temporal resolution produces relatively accurate forward volumes and regurgitant fractions but underestimates backward volumes and peak velocities at peak systole in pediatric patients with CHD.
Assuntos
Algoritmos , Cardiopatias Congênitas/diagnóstico por imagem , Imageamento por Ressonância Magnética , Criança , Eletrocardiografia , Estudos de Viabilidade , Feminino , Humanos , Modelos Lineares , Masculino , Imagens de FantasmasRESUMO
OBJECTIVE: The aim of this study was to determine whether it is feasible to visualize the coronary origins in patients with congenital heart disease (CHD) using single-shot coronary quiescent-interval slice-selective (QISS) magnetic resonance angiography (MRA) with compressed sensing (CS). METHODS: This retrospective study leveraged a parent study, which aimed to compare breath-hold, 2.1-fold accelerated, 2-shot coronary QISS MRA and clinical standard contrast-enhanced (CE) MRA in 14 patients with CHD (mean age, 17.0 ± 8.6 years, 6 females and 8 males). We evaluated the feasibility of single-shot coronary QISS MRA by retrospectively undersampling the 2-shot data set by an additional factor of 2, performing CS reconstruction, and comparing the retrospectively derived single-shot QISS MRA to 2-shot coronary QISS MRA and clinical standard CE MRA. For quantitative analysis, structural similarity index and normalized root mean square error were calculated. For qualitative analysis, 2 experienced readers scored the conspicuity of coronary origins on a 5-point Likert scale (1 = nondiagnostic, 2 = poor, 3 = clinically acceptable, 4 = good, 5 = excellent). RESULTS: Compared with 2-shot QISS, single-shot QISS produced normalized root mean square error of 5.8% ± 0.8% and structural similarity index of 95.4% ± 1.6%, suggesting high data fidelity by CS reconstruction. Compared with the mean conspicuity scores for clinical CE MRA (4.2 ± 0.5 and 4.1 ± 0.6 for right and left coronary origins, respectively), the mean conspicuity scores were not significantly different (P > 0.3) for 2-shot QISS (4.4 ± 0.9 and 4.2 ± 1.1, respectively) and single-shot QISS with CS (4.3 ± 1.1 and 3.8 ± 1.3, respectively) and deemed clinically acceptable to good (scores ≥3.0). CONCLUSIONS: This study shows that it is feasible to visualize the coronary origins in patients with CHD with clinically acceptable to good image quality using single-shot coronary QISS MRA with CS.
Assuntos
Cardiopatias Congênitas/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Processamento de Imagem Assistida por Computador/métodos , Angiografia por Ressonância Magnética/métodos , Adolescente , Meios de Contraste , Estudos de Viabilidade , Feminino , Coração/diagnóstico por imagem , Humanos , Aumento da Imagem/métodos , Masculino , Reprodutibilidade dos Testes , Estudos RetrospectivosRESUMO
This paper reported a method of multiwalled carbon nanotubes (MWCNTs) fusion inside a scanning electron microscope (SEM). A CNT was picked up by nanorobotics manipulator system which was constructed in SEM with 21 DOFs and 1 nm resolution. The CNT was picked up and placed on two manipulators. The tensile force was 140 nN when the CNT was pulled into two parts. Then, two parts of the CNT were connected to each other by two manipulators. The adhered force between two parts was measured to be about 20 nN. When the two parts of CNT were connected again, the contact area was fused by focused electron beam irradiation for 3 minutes. The tensile force of the junction was measured to be about 100 nN. However, after fusion, the tensile force was five times larger than the tensile force connected only by van der Waals force. This force was 70 percent of the tensile force before pulling out of CNTs. The results revealed that the electron beam irradiation was a promising method for CNT fusion. We hope this technology will be applied to nanoelectronics in the near future.
RESUMO
SUMOylation is a post-translational modification exerted various effects on the target proteins. SUMOylation is a highly dynamic and reversible process, which has been shown to play an important role in tumorigenesis. However, the roles of sentrin/SUMO-specific proteases (SENPs), which mediate the reverse process of SUMOylation, in tumorigenesis remains largely unexplored. Here, we uncover a critical role of SENP6 in promoting gastric cancer cells growth via regulating the deSUMOylation of a transcription factor forkhead box protein M1 (FoxM1). We demonstrated that the mRNA and protein levels were elevated in gastric cancer tissues. Overexpression of SENP6 promoted, while RNA interference depletion of endogenous SENP6 inhibited gastric cancer cells growth and the ability of colony formation. By using biochemical assays, we identified FoxM1 as a novel substrate of SENP6 in gastric cancer cells. Thus, our data suggest that SENP6, which is highly expressed in gastric cancer cells, regulates the transcriptional activity and stability of FoxM1 through deSUMOylation.
Assuntos
Carcinogênese/genética , Cisteína Endopeptidases/genética , Fatores de Transcrição Forkhead/metabolismo , Neoplasias Gástricas/genética , Linhagem Celular Tumoral , Proliferação de Células/genética , Cisteína Endopeptidases/biossíntese , Proteína Forkhead Box M1 , Fatores de Transcrição Forkhead/genética , Regulação Neoplásica da Expressão Gênica , Humanos , Processamento de Proteína Pós-Traducional/genética , RNA Mensageiro/biossíntese , Neoplasias Gástricas/patologia , Sumoilação/genéticaRESUMO
OBJECTIVE: To explore the clinical values of detecting drug related molecules excision repair cross complementing 1 (ERCC1) and top-isomerase I (TOPO I) in individualized therapies of metastatic colorectal cancer. METHODS: From June 2009 to December 2011, 90 patients at Huadong Hospital with metastatic colorectal cancer were randomly separated into 2 groups after operation. Each group had 45 patients without difference in gender, age or TNM stage. The expressions of ERCC1 and TOPO Iin cancer tissues were detected by immunohistochemical staining. The testing group received individualized chemotherapies following the expression results while the control group had random chemotherapies. The survival difference between two groups was analyzed by log-rank test and Kaplan-Meier analysis. And curative effect was analyzed by χ(2) or Fisher's analysis. RESULTS: The expressions of ERCC1 and TOPO I had no statistical significance between two groups (both P > 0.05). In the testing group, the median survival time was 281 days and the beneficial ratio 51.1% (23/45) versus 246 days and 44.4% (20/45) respectively in the control group. The inter-group comparisons of survival (P = 0.235) and curative effect (χ(2) = 0.04, P > 0.05) showed no statistical significance. In the estimated drug tolerated group (ERCC1 high expression or TOPO I low expression), the median survival time was 196 days and the beneficial ratio 4/14 versus 304 days and 51.3% (39/76) in the estimated drug sensitive group. The inter-group comparisons of survival and curative effect (both P < 0.05) had statistical significance. The median survival time and beneficial ratio significantly increased in estimated drug sensitive group than those in estimated drug tolerated group. CONCLUSIONS: The expression of drug related molecule in colorectal cancer tissue is significantly associated with curative effect in patients. Patients with down-regulated ERCC1 on Oxaliplatin or up-regulated TOPO Ion Irinotecan have longer survival and better curative effect. And chemotherapies guided by drug related molecule detection may boost curative effects in metastatic colorectal cancer.
Assuntos
Neoplasias Colorretais/diagnóstico , DNA Topoisomerases Tipo I/genética , Proteínas de Ligação a DNA/genética , Endonucleases/genética , Adulto , Idoso , Neoplasias Colorretais/tratamento farmacológico , Neoplasias Colorretais/patologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Metástase Neoplásica , Patologia Molecular , PrognósticoRESUMO
AIM: To observe the therapeutic efficacy of high-dose Vitamin C (Vit. C) on acute pancreatitis (AP), and to explore its potential mechanisms. METHODS: Eighty-four AP patients were divided into treatment group and control group, 40 healthy subjects were taken as a normal group. In the treatment group, Vit. C (10 g/day) was given intravenously for 5 days, whereas in the control group, Vit. C (1 g/day) was given intravenously for 5 days. Symptoms, physical signs, duration of hospitalization, complications and mortality rate were monitored. Meanwhile, serum amylase, urine amylase and leukocyte counts were also determined. The concentration of plasma vitamin C (P-VC), plasma lipid peroxide (P-LPO), plasma vitamin E (P-VE), plasma beta-carotene (P-beta-CAR), whole blood glutathione (WB-GSH) and the activity of erythrocyte surperoxide dimutase (E-SOD) and erythrocyte catalase (E-CAT) as well as T lymphocyte phenotype were measured by spectrophotometry in the normal group and before and after treatment with Vit. C in the treatment and the control group. RESULTS: Compared with the normal group, the average values of P-VC, P-VE, P-beta-CAR, WB-GSH and the activity of E-SOD and E-CAT in AP patients were significantly decreased and the average value of P-LPO was significantly increased, especially in severe acute pancreatitis (SAP) patients (P<0.05. P-VC, P=0.045; P-VE, P=0.038; P=0.041; P-beta-CAR, P=0.046; WB-GSH, P=0.039; E-SOD, P=0.019; E-CAT, P=0.020; P-LPO, P=0.038). Compared with the normal group, CD3 and CD4 positive cells in AP patients were significantly decreased. The ratio of CD4/CD8 and CD4 positive cells were decreased, especially in SAP patients (P<0.05. CD4/CD8, P=0.041; CD4, P =0.019). Fever and vomiting disappeared, and leukocyte counts and amylase in urine and blood become normal quicker in the treatment group than in the control group. Moreover, patients in treatment group also had a higher cure rate, a lower complication rate and a shorter in-ward days compared with those in he control group. After treatment, the average value of P-VC was significantly higher and the values of SIL-2R, TNF-alpha, IL-6 and IL-8 were significantly lower in the treatment group than in the control group (P<0.05 P-VC, P=0.045; SIL-2R, P=0.012; TNF-alpha, P=0.030; IL-6, P=0.015; and IL-8, P=0.043). In addition, the ratio of CD4/CD8 and CD4 positive cells in the patients of treatment group were significantly higher than that of the control group after treatment (P<0.05. CD4/CD8, P=0.039; CD4, P=0.024). CONCLUSION: High-dose vitamin C has therapeutic efficacy on acute pancreatitis. The potential mechanisms include promotion of anti-oxidizing ability of AP patients, blocking of lipid peroxidation in the plasma and improvement of cellular immune function.