Accelerated 3D MR neurography of the brachial plexus using deep learning-constrained compressed sensing.

OBJECTIVES: To explore the use of deep learning-constrained compressed sensing (DLCS) in improving image quality and acquisition time for 3D MRI of the brachial plexus. METHODS: Fifty-four participants who underwent contrast-enhanced imaging and forty-one participants who underwent unenhanced imaging were included. Sensitivity encoding with an acceleration of 2 × 2 (SENSE4x), CS with an acceleration of 4 (CS4x), and DLCS with acceleration of 4 (DLCS4x) and 8 (DLCS8x) were used for MRI of the brachial plexus. Apparent signal-to-noise ratios (aSNRs), apparent contrast-to-noise ratios (aCNRs), and qualitative scores on a 4-point scale were evaluated and compared by ANOVA and the Friedman test. Interobserver agreement was evaluated by calculating the intraclass correlation coefficients. RESULTS: DLCS4x achieved higher aSNR and aCNR than SENSE4x, CS4x, and DLCS8x (all p < 0.05). For the root segment of the brachial plexus, no statistically significant differences in the qualitative scores were found among the four sequences. For the trunk segment, DLCS4x had higher scores than SENSE4x (p = 0.04) in the contrast-enhanced group and had higher scores than SENSE4x and DLCS8x in the unenhanced group (all p < 0.05). For the divisions, cords, and branches, DLCS4x had higher scores than SENSE4x, CS4x, and DLCS8x (all p ≤ 0.01). No overt difference was found among SENSE4x, CS4x, and DLCS8x in any segment of the brachial plexus (all p > 0.05). CONCLUSIONS: In three-dimensional MRI for the brachial plexus, DLCS4x can improve image quality compared with SENSE4x and CS4x, and DLCS8x can maintain the image quality compared to SENSE4x and CS4x. CLINICAL RELEVANCE STATEMENT: Deep learning-constrained compressed sensing can improve the image quality or accelerate acquisition of 3D MRI of the brachial plexus, which should be benefit in evaluating the brachial plexus and its branches in clinical practice. KEY POINTS: •Deep learning-constrained compressed sensing showed higher aSNR, aCNR, and qualitative scores for the brachial plexus than SENSE and CS at the same acceleration factor with similar scanning time. •Deep learning-constrained compressed sensing at acceleration factor of 8 had comparable aSNR, aCNR, and qualitative scores to SENSE4x and CS4x with approximately half the examination time. •Deep learning-constrained compressed sensing may be helpful in clinical practice for improving image quality and acquisition time in three-dimensional MRI of the brachial plexus.

Association Between Heart Failure With Preserved Left Ventricular Ejection Fraction and Impaired Left Atrial Phasic Function in Hypertrophic Cardiomyopathy: Evaluation by Cardiac MRI Feature Tracking.

BACKGROUND: The majority of heart failure (HF) in hypertrophic cardiomyopathy (HCM) manifests as a phenotype with preserved left ventricular (LV) ejection fraction; however, the exact contribution of left atrial (LA) phasic function to HF with preserved ejection fraction (HFpEF) in HCM remains unresolved. PURPOSE: To define the association between LA function and HFpEF in HCM patients using cardiac magnetic resonance imaging (MRI) feature tracking. STUDY TYPE: Retrospective. POPULATION: One hundred and fifty-four HCM patients (HFpEF vs. non-HF: 55 [34 females] vs. 99 [43 females]). FIELD STRENGTH/SEQUENCE: 3.0 T/balanced steady-state free precession. ASSESSMENT: LA reservoir function (reservoir strain [εs ], total ejection fraction [EF]), conduit function (conduit strain [εe ], passive EF), booster-pump function (booster strain [εa ] and active EF), LA volume index, and LV global longitudinal strain (LV GLS) were evaluated in HCM patients. STATISTICAL TESTS: Chi-square test, Student's t-test, Mann-Whitney U test, multivariate linear regression, logistic regression, and net reclassification analysis were used. Two-sided P < 0.05 was considered statistically significant. RESULTS: No significant difference was found in LV GLS between the non-HF and HFpEF group (-10.67 ± 3.14% vs. -10.14 ± 4.01%, P = 0.397), whereas the HFpEF group had more severely impaired LA phasic strain (εs : 27.40 [22.60, 35.80] vs. 18.15 [11.98, 25.90]; εe : 13.80 [9.20, 18.90] vs. 7.95 [4.30, 14.35]; εa : 13.50 [9.90, 17.10] vs. 7.90 [5.40, 14.15]). LA total EF (37.91 [29.54, 47.94] vs. 47.49 [39.18, 55.01]), passive EF (14.70 [7.41, 21.49] vs. 18.07 [9.32, 24.78]), and active EF (27.19 [17.79, 36.60] vs. 36.64 [26.63, 42.71]) were all significantly decreased in HFpEF patients compared with non-HF patients. LA reservoir (ß = 0.90 [0.85, 0.96]), conduit (ß = 0.93 [0.87, 0.99]), and booster (ß = 0.86 [0.78, 0.95]) strain were independently associated with HFpEF in HCM patients. The model including reservoir strain (Net Reclassification Index [NRI]: 0.260) or booster strain (NRI: 0.325) improved the reclassification of HFpEF based on LV GLS and minimum left atrial volume index (LAVImin ). DATA CONCLUSION: LA phasic function was severely impaired in HCM patients with HFpEF, whereas LV function was not further impaired compared with non-HF patients. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 3.

Automatic machine learning based on native T1 mapping can identify myocardial fibrosis in patients with hypertrophic cardiomyopathy.

OBJECTIVES: To investigate the feasibility of automatic machine learning (autoML) based on native T1 mapping to predict late gadolinium enhancement (LGE) status in hypertrophic cardiomyopathy (HCM). METHODS: Ninety-one HCM patients and 44 healthy controls who underwent cardiovascular MRI were enrolled. The native T1 maps of HCM patients were classified as LGE ( +) or LGE (-) based on location-matched LGE images. An autoML pipeline was implemented using the tree-based pipeline optimization tool (TPOT) for 3 binary classifications: LGE ( +) and LGE (-), LGE (-) and control, and HCM and control. TPOT modeling was repeated 10 times to obtain the optimal model for each classification. The diagnostic performance of the best models by slice and by case was evaluated using sensitivity, specificity, accuracy, and microaveraged area under the curve (AUC). RESULTS: Ten prediction models were generated by TPOT for each of the 3 binary classifications. The diagnostic accuracy obtained with the best pipeline in detecting LGE status in the testing cohort of HCM patients was 0.80 by slice and 0.79 by case. In addition, the TPOT model also showed discriminability between LGE (-) patients and control (accuracy: 0.77 by slice; 0.78 by case) and for all HCM patients and controls (accuracy: 0.88 for both). CONCLUSIONS: Native T1 map analysis based on autoML correlates with LGE ( +) or (-) status. The TPOT machine learning algorithm could be a promising method for predicting myocardial fibrosis, as reflected by the presence of LGE in HCM patients without the need for late contrast-enhanced MRI sequences. KEY POINTS: • The tree-based pipeline optimization tool (TPOT) is a machine learning algorithm that could help predict late gadolinium enhancement (LGE) status in patients with hypertrophic cardiomyopathy. • The TPOT could serve as an adjuvant method to detect LGE by using information from native T1 maps, thus avoiding the need for contrast agent. • The TPOT also detects native T1 map alterations in LGE-negative patients with hypertrophic cardiomyopathy.

Cardiac magnetic resonance T1 mapping for evaluating myocardial fibrosis in patients with type 2 diabetes mellitus: correlation with left ventricular longitudinal diastolic dysfunction.

OBJECTIVES: We aimed to evaluate myocardial fibrosis using cardiac magnetic resonance (CMR) T1 mapping in type 2 diabetes mellitus (T2DM) patients and investigate the association between left ventricular (LV) subclinical myocardial dysfunction and myocardial fibrosis. METHODS: The study included 37 short-term (≤ 5 years) and 44 longer-term (> 5 years) T2DM patients and 41 healthy controls. The LV global strain parameters and T1 mapping parameters were compared between the abovementioned three groups. The association of T1 mapping parameters with diabetes duration, in addition to other risk factors, was determined using multivariate linear regression analysis. The correlation between LV strain parameters and T1 mapping parameters was evaluated using Pearson's correlation. RESULTS: The peak diastolic strain rates (PDSRs) were significantly lower in longer-term T2DM patients compared to those in healthy subjects and short-term T2DM patients (p < 0.05). The longitudinal peak systolic strain rate and peak strain were significantly lower in the longer-term T2DM compared with the short-term T2DM group (p < 0.05). The extracellular volumes (ECVs) were higher in both subgroups of T2DM patients compared with control subjects (all p < 0.05). Multivariate linear regression analysis showed that diabetes duration was independently associated with ECV (ß = 0.413, p < 0.001) by taking covariates into account. Pearson's analysis showed that ECV was associated with longitudinal PDSR (r = - 0.441, p < 0.001). CONCLUSION: T1 mapping could detect abnormal myocardial fibrosis early in patients with T2DM, which can cause a decline in the LV diastolic function. KEY POINTS: • CMR T1 mapping could detect abnormal myocardial fibrosis early in patients with T2DM. • The diabetes duration was independently associated with ECV. • Myocardial fibrosis can cause a decline in the LV diastolic function in T2DM patients.

Noninvasive oxygenation assessment after acute myocardial infarction with breathing maneuvers-induced oxygenation-sensitive magnetic resonance imaging.

The safety profiles when performing stress oxygenation-sensitive magnetic resonance imaging (OS-MRI) have raised concerns in clinical practice. Adenosine infusion can cause side effects such as chest pain, dyspnea, arrhythmia, and even cardiac death. The aim of this study was to investigate the feasibility of breathing maneuvers-induced OS-MRI in acute myocardial infarction (MI). This was a prospective study, which included 14 healthy rabbits and nine MI rabbit models. This study used 3 T MRI/modified Look-Locker inversion recovery sequence for native T1 mapping, balanced steady-state free precession sequence for OS imaging, and phase-sensitive inversion recovery sequence for late gadolinium enhancement. The changes in myocardial oxygenation (ΔSI) were assessed under two breathing maneuvers protocols in healthy rabbits: a series of extended breath-holding (BH), and a combined maneuver of hyperventilation followed by the extended BH (HVBH). Subsequently, OS-MRI with HVBH in acute MI rabbits was performed, and the ΔSI was compared with that of adenosine stress protocol. Student's t-test, Wilcoxon rank test, and Friedman test were used to compare ΔSI in different subgroups. Pearson and Spearman correlation was used to obtain the association of ΔSI between breathing maneuvers and adenosine stress. Bland-Altman analysis was used to assess the bias of ΔSI between HVBH and adenosine stress. In healthy rabbits, BH maneuvers from 30 to 50 s induced significant increase in SI compared with the baseline (all p < 0.05). By contrast, hyperventilation for 60 s followed by 10 s-BH (HVBH 10 s) exhibited a comparable ΔSI to that of stress test (p = 0.07). In acute MI rabbits, HVBH 10 s-induced ΔSIs among infarcted, salvaged, and the remote myocardial area were no less effectiveness than adenosine stress when performing OS-MRI (r = 0.84; p < 0.05). Combined breathing maneuvers with OS-MRI have the potential to be used as a nonpharmacological alternative for assessing myocardial oxygenation in patients with acute MI. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.

Increased oxygenation is associated with myocardial inflammation and adverse regional remodeling after acute ST-segment elevation myocardial infarction.

OBJECTIVES: To explore the relationships between oxygenation signal intensity (SI) with myocardial inflammation and regional left ventricular (LV) remodeling in reperfused acute ST-segment elevation myocardial infarction (STEMI) using oxygenation-sensitive cardiovascular magnetic resonance (OS-CMR). METHODS: Thirty-three STEMI patients and 22 age- and sex-matched healthy volunteers underwent CMR. The protocol included cine function, OS imaging, precontrast T1 mapping, T2 mapping, and late gadolinium enhancement (LGE) imaging. A total of 880 LV segments were included for analysis based on the American Heart Association 16-segment model. For validation, 15 pigs (10 myocardial infarction (MI) model animals and 5 controls) received CMR and were sacrificed for immunohistochemical analysis. RESULTS: In the patient study, the acute oxygenation SI showed a stepwise rise among remote, salvaged, and infarcted segments compared with healthy myocardium. At convalescence, all oxygenation SI values besides those in infarcted segments with microvascular obstruction decreased to similar levels. Acute oxygenation SI was associated with early myocardial injury (T1: r = 0.38; T2: r = 0.41; all p < 0.05). Segments with higher acute oxygenation SI values exhibited thinner diastolic walls and decreased wall thickening during follow-up. Multivariable regression modeling indicated that acute oxygenation SI (ß = 2.66; p < 0.05) independently predicted convalescent segment adverse remodeling (LV wall thinning). In the animal study, alterations in oxygenation SI were correlated with histological inflammatory infiltrates (r = 0.59; p < 0.001). CONCLUSIONS: Myocardial oxygenation by OS-CMR could be used as a quantitative imaging biomarker to assess myocardial inflammation and predict convalescent segment adverse remodeling after STEMI. KEY POINTS: • Oxygenation signal intensity (SI) may be an imaging biomarker of inflammatory infiltration that could be used to assess the response to anti-inflammatory therapies in the future. • Oxygenation SI early after myocardial infarction (MI) was associated with left ventricular segment injury at acute phase and could predict regional functional recovery and adverse remodeling late after acute MI. • Oxygenation SI demonstrated a stepwise increase among remote, salvaged, and infarcted segments. Infarcted zones with microvascular obstruction demonstrated a higher oxygenation SI than those without. However, the former showed less pronounced changes over time.

[A Preliminary Study of Applying Geometric Deep Learning in Brain Morphometry for Diagnosis of Alzheimer's Disease].

OBJECTIVE: A predictive model of Alzheimer's disease (AD) was established based on brain surface meshes and geometric deep learning, and its performance was evaluated. METHODS: Seventy-six clinically diagnosed AD patients and 83 healthy older adults were enrolled and randomly assigned to the training set and the test set according to a 4-to-1 ratio. Brain surface mesh was constructed from 3-D T1-weighted high-resolution structural MR volumes of each participant. After applying a series of simplification to the surface meshes, the training set was fed into the geometric deep neural network for training. The performance of the prediction model was evaluated with the test set, and the evaluation metrics included accuracy, sensitivity and specificity. RESULTS: The prediction model trained on the right brain surface meshes with 6 000 faces achieved the best performance, with accuracy reaching 93.8%, sensitivity, 91.7%, and specificity, 94.1%. The evolution of the brain surface meshes during convolution and pooling revealed that AD patients had diffuse brain tissue loss compared with healthy older adults. CONCLUSION: Morphological brain analysis based on mesh data and geometric deep learning has great potential in the differential diagnosis of AD.

[Application of MRI-based Radiomics Models in the Assessment of Hepatic Metastasis of Rectal Cancer].

OBEJECTIVE: To explore the clinical value of using radiomics models based on different MRI sequences in the assessment of hepatic metastasis of rectal cancer. METHODS: 140 patients with pathologically confirm edrectal cancer were included in the study. They underwent baseline magnetic resonance imaging (MRI) between April 2015 and May 2018 before receiving any treatment. According to the results of liver biopsy, surgical pathology, and imaging, patients were put into two groups, the patients with hepatic metastasis and those without. T2 weighted images (T2WI), diffusion weighted images (DWI) and apparent diffusion coefficient (ADC) images were used to draw the region of interest (ROI) of primary lesions on consecutive slices on ITK-SNAP. 3-D ROIs were generated and loaded into Artificial Intelligent Kit for extraction of radiomics features and 396 features were extracted for each sequence. The feature data were preprocessed on Python and the samples were oversampled, using Support Vector Machine-Synthetic Minority Over-Sampling Technique (SVM-SMOTE) to balance the number of samples in the group with liver metastasis and the group with no liver metastasis at the end of the follow-up. Then, the samples were divided into the training cohort and the test cohort at a ratio of 2∶1. The logistic regression models were developed with selected radionomic features on R software. The receiver operating characteristics (ROC) curves and calibration curves were used to evaluate the performance of the models. RESULTS: In total, 52 patients with liver metastasis and 88 patients without liver metastasis at the end of follow-up were enrolled. Carcinoembryonic antigen (CEA) and T stage and N stage evaluated on the MRI images showed statistically significant difference between the two groups ( P<0.05). After data preprocessing and selecting, except for 17 non-radiomic features, the model combining T2WI, DWI and ADC features, the model of T2WI features alone, the model of DWI features alone and the model of ADC features alone were developed with 32 features, 10 features, 30 features and 15 features, respectively. The combined model (T2WI+DWI+ADC), the T2WI model, and the ADC model can assess hepatic metastasis accurately, with the area under curve ( AUC) on the train set reaching 93.5%, 89.2%, 90.6% and that of the test set reaching 80.8%, 80.5%, 81.4%, respectively. The combined model did not show a higher AUC than those of the T2WI and ADC alone models. Model based on DWI features has a slightly insufficient AUC of 90.3% in the train set and 75.1% in the test set. The calibration curve showed the smallest fluctuation in the combined model, which is closest fit to the diagonal reference line. The fluctuation in the three independent data set models were similar. The calibration curves of all the four models showed that as the risk increased, the prediction of the models turned from an underestimation to an overestimating the risk. In brief, the combined model showed the best performance, with the best fit to the diagonal reference line in calibration curve and high AUC comparable to the AUC of the T2WI model and ADC model. The performance of T2WI and ADC alone models were second to that of the combined model, while the DWI alone model showed relatively poor performance. CONCLUSION: Radiomics models based on MRI could be effectively used in assessing liver metastasis in rectal cancer, which may help determine clinical staging and treatment.

[Early Assessment of Myocardial Fibrosis of Hypertrophic Cardiomyopathy with Native-T1-Mapping-Based Deep Learning: A Preliminary Study].

OBJECTIVE: To explore the diagnostic performance of deep learning (DL) model in early detection of the interstitial myocardial fibrosis using native T1 maps of hypertrophic cardiomyopathy (HCM) without late gadolinium enhancement (LGE). METHODS: Sixty HCM patients and 44 healthy volunteers who underwent cardiac magnetic resonance were enrolled in this study. Each native T1 map was labeled according to its LGE status. Then, native T1 maps of LGE (-) and those of the controls were preprocessed and entered in the SE-ResNext-50 model as the matrix for the DL model for training, validation and testing. RESULTS: A total of 241 native T1 maps were entered in the SE-ResNext-50 model. The model achieved a specificity of 0.87, sensitivity of 0.79, and area under curve ( AUC) of 0.83 ( P<0.05) in distinguishing native T1 maps of LGE (-) from those of the controls in the testing set. CONCLUSION: The DL model based on SE-ResNext-50 could be used for identifying native T1 maps of LGE (-) with relatively high accuracy. It is a promising approach for early detection of myocardial fibrosis in HCM without the use of contrast agent.

[Application of 3.0T Time-of-flight Magnetic Resonance Angiography with Sparse Undersampling and Iterative Reconstruction in the Diagnosis of Unruptured Intracranial Aneurysms].

OBJECTIVE: To evaluate the diagnostic value of 3.0T time-of-flight MR angiography with sparse undersampling and iterative reconstruction (TOFu-MRA) for unruptured intracranial aneurysms (UIAs) on the basis of using digital subtraction angiography (DSA) as the reference standard. METHODS: A total of 65 patients with suspected UIAs were prospectively enrolled and all patients underwent TOFu-MRA and DSA. Relying on DSA as the reference standard, the sensitivity (SEN), specificity (SPE), positive predictive value (PPV) and negative predictive value (NPV) of using TOFu-MRA in UIA diagnosis were calculated, and the inter-observer agreement between two doctors was determined. Comparison of maximum intensity projection (MIP) and volume rendering (VR) image datasets was made to evaluate the agreement between DSA results and TOFu-MRA in the measurement of UIA morphological parameters, including the neck width (D neck), height (H) , and width (D width) of UIAs. RESULTS: The study covered 55 UIAs from 46 patients. The SEN, SPE, PPV and NPV of the two doctors using TOFu-MRA in UIA diagnosis were as follows: (95.7%, 95.7%), (94.7%, 94.7%), (97.8%, 97.8%) and (90.0%, 90.0%), respectively for patient-based assessment; (96.4%, 94.5%), (94.7%, 94.7%), (98.1%, 98.1%) and (90.0%, 85.7%), respectively, for aneurysm-based assessment. There is a strong inter-observer agreement (Kappa=0.93 for patient-based assessment and 0.96 for aneurysm-based assessment) between the two doctors. Moreover, Bland-Altman analysis showed that more than 95% points fell within the limits of agreement (LoA), suggesting strong agreement between the two examination methods for the measurement of UIAs morphological parameters. CONCLUSION: TOFu-MRA showed good diagnostic efficacy for UIAs and the results were in good agreement with those of DSA, the reference standard, for assessing UIA morphological parameter. TOFu-MRA can be used as a first choice for noninvasive diagnostic evaluation of UIAs.

[Noise Reduction Effect of Deep-learning-based Image Reconstruction Algorithms in Thin-section Chest CT].

OBJECTIVE: To evaluate the noise reduction effect of deep learning-based reconstruction algorithms in thin-section chest CT images by analyzing images reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction (ASIR), and deep learning image reconstruction (DLIR) algorithms. METHODS: The chest CT scan raw data of 47 patients were included in this study. Images of 0.625 mm were reconstructed using six reconstruction methods, including FBP, ASIR hybrid reconstruction (ASIR50%, ASIR70%), and deep learning low, medium and high modes (DL-L, DL-M, and DL-H). After the regions of interest were outlined in the aorta, skeletal muscle and lung tissue of each group of images, the CT values, SD values and signal-to-noise ratio (SNR) of the regions of interest were measured, and two radiologists evaluated the image quality. RESULTS: CT values, SD values and SNR of the images obtained by the six reconstruction methods showed statistically significant difference ( P<0.001). There were statistically significant differences in the image quality scores of the six reconstruction methods ( P<0.001). Images reconstruced with DL-H have the lowest noise and the highest overall quality score. CONCLUSION: The model based on deep learning can effectively reduce the noise of thin-section chest CT images and improve the image quality. Among the three deep-learning models, DL-H showed the best noise reduction effect.

[The Application Value of Artificial Intelligence-based Filtering and Interpolated Image Reconstruction Algorithm in Abdominal Magnetic Resonance Image Denoising].

OBJECTIVE: To compare the noise reduction performance of conventional filtering and artificial intelligence-based filtering and interpolation (AIFI) and to explore for optimal parameters of applying AIFI in the noise reduction of abdominal magnetic resonance imaging (MRI). METHODS: Sixty patients who underwent upper abdominal MRI examination in our hospital were retrospectively included. The raw data of T1-weighted image (T1WI), T2-weighted image (T2WI), and dualecho sequences were reconstructed with two image denoising techniques, conventional filtering and AIFI of different levels of intensity. The difference in objective image quality indicators, peak signal-to-noise ratio (pSNR) and image sharpness, of the different denoising techniques was compared. Two radiologists evaluated the image noise, contrast, sharpness, and overall image quality. Their scores were compared and the interobserver agreement was calculated. RESULTS: Compared with the original images, improvement of varying degrees were shown in the pSNR and the sharpness of the images of the three sequences, T1W1, T2W2, and dual echo sequence, after denoising filtering and AIFI were used (all P<0.05). In addition, compared with conventional filtering, the objective quality scores of the reconstructed images were improved when conventional filtering was combined with AIFI reconstruction methods in T1WI sequence, AIFI level≥3 was used in T2WI and echo1 sequence, and AIFI level≥4 was used in echo2 sequence (all P<0.05). The subjective scores given by the two radiologists for the image noise, contrast, sharpness, and overall image quality in each sequence of conventional filtering reconstruction, AIFI reconstruction (except for AIFI level=1), and two-method combination reconstruction were higher than those of the original images (all P<0.05). However, the image contrast scores were reduced for AIFI level=5. There was good interobserver agreement between the two radiologists (all r>0.75, P<0.05). After multidimensional comparison, the optimal parameters of using AIFI technique for noise reduction in abdominal MRI were conventional filtering+AIFI level=3 in the T1WI sequence and AIFI level=4 in the T2WI and dualecho sequences. CONCLUSION: AIFI is superior to filtering in imaging denoising at medium and high levels. It is a promising noise reduction technique. The optimal parameters of using AIFI for abdominal MRI are Filtering+AIFI level=3 in the T1WI sequence and AIFI level=4 in T2WI and dualecho sequences.

[The Clinical Effectiveness of Neural Network-based Boundary Recognition of Upper Abdominal Organs on CT Images].

OBJECTIVE: To assess the clinical effectiveness of boundary recognition of upper abdomen organs on CT images based on neural network model and the combination of different slices. METHODS: A total of 2 000 patients who underwent upper abdomen enhanced CT scans from March 2018 to March 2019 were included in the study. The quality of the CT images met the requirements for clinical diagnosis. Eight boundary layers (the upper and lower edge of liver, the upper and lower edge of spleen, the lower edge of left kidney, the lower edge of right kidney, the lower edge of the stomach and the lower edge of the gallbladder) of the main organs in the upper abdomen were labeled. The model training (training set, verification set and test set) based on different neural network methods and combinations of different slices were then performed to assess the accuracy of boundary recognition. Furthermore, clinical data from 50 cases were used as test group for assessing the accuracy and clinical effectiveness of this model. RESULTS: The fusion model created by integrating the two models according to different weight ratios yielded the highest accuracy, and then followed the EfficientNet-b3 model, with the Xception model showing the lowest accuracy. In each model, the boundary recognition accuracy of 5-slice image is higher than that of 3-silce image, and that of 1-slice image is the lowest. The recognition accuracy of fusion model of the 5-continuous-slice image for upper edge of liver, lower edge of liver, upper edge of spleen, lower edge of spleen, lower edge of left kidney, lower edge of right kidney, lower edge of stomach and lower edge of gallbladder was 91%, 87%, 92%, 85%, 92%, 95%, 76% and 74%, respectively. The fusion model was checked with the effectiveness data of 50 cases, yielding 88%, 86%, 88%, 80%, 82%, 80%, 69%, and 65% accuracy for 8-slice image, respectively, and the accuracy of meeting clinical application requirement was as high as 98%, 98%, 95%, 98%, 99%, 98%, 80% and 77%, respectively. CONCLUSION: By increasing boundary change logics in the continuous slices, the fusion model integrating different weight proportions demonstrates the highest accuracy for identifying the boundary of upper abdominal organs on CT images, achieving high examination effectiveness in clinical practice.

[Application of Deep Learning Reconstruction Algorithm in Low-Dose Thin-Slice Liver CT of Healthy Volunteers].

OBJECTIVE: To explore the clinical feasibility of applying deep learning (DL) reconstruction algorithm in low-dose thin-slice liver CT examination of healthy volunteers by comparing the reconstruction algorithm based on DL, filtered back projection (FBP) reconstruction algorithm and iterative reconstruction (IR) algorithm. METHODS: A standard water phantom with a diameter of 180 mm was scanned, using the 160 slice multi-detector CT scanning of United Imaging Healthcare, to compare the noise power spectrums of DL, FBP and IR algorithms. 100 healthy volunteers were prospectively enrolled, with 50 assigned to the normal dose group (ND) and 50 to the low dose group (LD). IR algorithm was used in the ND group to reconstruct images, while DL, FBP and IR algorithms were used in the LD group to reconstruct images. One-way analysis of variance was used to compare the liver CT values, the liver noise, liver signal-to-noise ratio (SNR), contrast noise ratio (CNR) and figure of merit (FOM) of the images of ND-IR, LD-FBP, LD-IR and LD-DL. The Kruskal-Wallis test was used to analyse subjective scores of anatomical structures. RESULTS: The DL algorithm had the lowest average peak value of noise power spectrum, and its shape was similar to that of medium-level IR algorithm. Liver CT values of ND-IR, LD-FBP, LD-IR and LD-DL did not show statistically significant difference. The noise of LD-DL was lower than that of LD-FBP, LD-IR and ND-IR ( P<0.05), and the SNR, CNR and FOM of LD-DL were higher than those of LD-FBP, LD-IR and ND-IR ( P<0.05). The subjective scores of anatomical structures of LD-DL did not show significant difference compared to those of ND-IR ( P >0.05), and were higher than those of LD-FBP and LD-IR. The radiation dose of the LD group was reduced by about 50.2% compared with that of the ND group. CONCLUSION: The DL algorithm with noise shape similar to the medium iterative grade IR commonly used in clinical practice showed higher noise reduction ability than IR did. Compared with FBP, the DL algorithm had smoother noise shape, but much better noise reduction ability. The application of DL algorithm in low-dose thin-slice liver CT of healthy volunteers can help achieve the standard image quality of liver CT.

[Application of Automated Machine Learning Based on Radiomics Features of T2WI and RS-EPI DWI to Predict Preoperative T Staging of Rectal Cancer].

OBJECTIVE: To explore the radiomics features of T2 weighted image (T2WI) and readout-segmented echo-planar imaging (RS-EPI) plus difusion-weighted imaging (DWI), to develop an automated mahchine-learning model based on the said radiomics features, and to test the value of this model in predicting preoperative T staging of rectal cancer. METHODS: The study retrospectively reviewed 131 patients who were diagnosed with rectal cancer confirmed by the pathology results of their surgical specimens at West China Hospital of Sichuan University between October, 2017 and December, 2018. In addition, these patients had preoperative rectal MRI. Tumor regions from preoperative MRI were manually segmented by radiologists with the ITK-SNAP software from T2WI and RS-EPI DWI images. PyRadiomics was used to extract 200 features-100 from T2WI and 100 from the apparent diffusion coefficient (ADC) calculated from the RS-EPI DWI. MWMOTE and NEATER were used to resample and balance the dataset, and 13 cases of T 1-2 stage simulation cases were added. The overall dataset was divided into a training set (111 cases) and a test set (37 cases) by a ratio of 3∶1. Tree-based Pipeline Optimization Tool (TPOT) was applied on the training set to optimize model parameters and to select the most important radiomics features for modeling. Five independent T stage models were developed accordingly. Accuracy and the area under the curve ( AUC) of receiver operating characteristic (ROC) were used to pick out the optimal model, which was then applied on the training set and the original dataset to predict the T stage of rectal cancer. RESULTS: The performance of the the five T staging models recommended by automated machine learning were as follows: The accuracy for the training set ranged from 0.802 to 0.838, sensitivity, from 0.762 to 0.825, specificity, from 0.833 to 0.896, AUC, from 0.841 to 0.893, and average precision (AP) from 0.870 to 0.901. After comparison, an optimal model was picked out, with sensitivity, specificity and AUC for the training set reaching 0.810, 0.875, and 0.893, respectively. The sensitivity, specificity and AUC for the test set were 0.810, 0.813, and 0.810, respectively. The sensitivity, specificity and AUC for the original dataset were 0.810, 0.830, and 0.860, respectively. CONCLUSION: Based on the radiomics data of T2WI and RS-EPI DWI, the model established by automated machine learning showed a fairly high accuracy in predicting rectal cancer T stage.

The additive effects of obesity on myocardial microcirculation in diabetic individuals: a cardiac magnetic resonance first-pass perfusion study.

BACKGROUND: The microvascular effects of obesity should be considered in diabetic individuals for elucidating underlying mechanisms and developing targeted therapies. This study aims to determine the effect of obesity on myocardial microvascular function in type 2 diabetes mellitus (T2DM) patients using cardiac magnetic resonance (CMR) first-pass perfusion imaging and assessed significant risk factors for microvascular dysfunction. MATERIALS AND METHODS: Between September 2016 and May 2018, 120 patients with T2DM (45.8% women [55 of 120]; mean age, 56.45 ± 11.97 years) and 79 controls (44.3% women [35 of 79]; mean age, 54.50 ± 7.79 years) with different body mass index (BMI) scales were prospectively enrolled and underwent CMR examination. CMR-derived perfusion parameters, including upslope, time to maximum signal intensity (TTM), maximum signal intensity (MaxSI), MaxSI (-baseline), and SI (baseline), and T2DM related risk factors were analyzed among groups/subgroups both in T2DM patients and controls. Univariable and multivariable linear and logistic regression analyses were performed to assess the potential additive effect of obesity on microvascular dysfunction in diabetic individuals. RESULTS: Compared with controls with comparable BMIs, patients with T2DM showed reduced upslope and MaxSI and increased TTM. For both T2DM and control subgroups, perfusion function gradually declined with increasing BMI, which was confirmed by all perfusion parameters, except for TTM (all P < 0.01). In multivariable linear regression analysis, BMI (ß = - 0.516; 95% confidence interval [CI], - 0.632 to - 0.357; P < 0.001), female sex (ß = 0.372; 95% CI, 0.215 to 0.475; P < 0.001), diabetes duration (ß = - 0.169; 95% CI, - 0.319 to - 0.025; P = 0.022) and glycated haemoglobin (ß = - 0.184; 95% CI, - 0.281 to - 0.039; P = 0.010) were significantly associated with global upslope in the T2DM group. Multivariable logistic regression analysis indicated that T2DM was an independent predictor of microvascular dysfunction in normal-weight (odds ratio[OR], 6.46; 95% CI, 2.08 to 20.10; P = 0.001), overweight (OR, 7.19; 95% CI, 1.67 to 31.07; P = 0.008) and obese participants (OR, 11.21; 95% CI, 2.38 to 52.75; P = 0.002). CONCLUSIONS: Myocardial microvascular function gradually declined with increasing BMI in both diabetes and non-diabetes status. T2DM was associated with an increased risk of microvascular dysfunction, and obesity exacerbated the adverse effect of T2DM.

Retraction Note: Prognostic value of heart failure in hemodialysis-dependent end-stage renal disease patients with myocardial fibrosis quantification by extracellular volume on cardiac magnetic resonance imaging.

An amendment to this paper has been published and can be accessed via the original article.

Prognostic value of heart failure in hemodialysis-dependent end-stage renal disease patients with myocardial fibrosis quantification by extracellular volume on cardiac magnetic resonance imaging.

BACKGROUND: End-stage renal disease (ESRD) patients are at high cardiovascular risk, and myocardial fibrosis (MF) accounts for most of their cardiac events. The purpose of this study is to investigate the prognostic value and risk stratification of MF as measured by extracellular volume (ECV) on cardiac magnetic resonance (CMR) for heart failure (HF) in patients with hemodialysis-dependent ESRD. METHODS: Sixty-six hemodialysis ESRD patients and 25 matched healthy volunteers were prospectively enrolled and underwent CMR to quantify multiple parameters of MF by T1 mapping and late gadolinium enhancement (LGE). All ESRD patients were followed up for 11-30 months, and the end-point met the 2016 ESC guidelines for the definition of HF. RESULTS: Over a median follow-up of 18 months (range 11-30 months), there were 26 (39.39%) guideline-diagnosed HF patients in the entire cohort of ESRD subjects. The native T1 value was elongated, and ECV was enlarged in the HF cohort relative to the non-HF cohort and normal controls (native T1, 1360.10 ± 50.14 ms, 1319.39 ± 55.44 ms and 1276.35 ± 56.56 ms; ECV, 35.42 ± 4.42%, 31.85 ± 3.01% and 26.97 ± 1.87%; all p<0.05). In the cardiac strain analysis, ECV was significantly correlated with global radial strain (GRS) (r = - 0.501, p = 0.009), global circumferential strain (GCS) (r = 0.553, p = 0.005) and global longitudinal strain (GLS) (r = 0.507, p = 0.008) in ESRD patients with HF. Cox proportional hazard regression models revealed that ECV (hazard ratio [HR] = 1.160, 95% confidence interval: 1.022 to 1.318, p = 0.022) was the only independent predictor of HF in ESRD patients. It also had a higher diagnostic accuracy for detecting MF (area under the curve [AUC] = 0.936; 95% confidence interval: 0.864 to 0.976) than native T1 and post T1 (all p ≤ 0.002). Kaplan-Meier analysis revealed that the high-ECV group had a shorter median overall survival time than the low-ECV group (18 months vs. 20 months, log-rank p = 0.046) and that ESRD patients with high ECV were more likely to have HF. CONCLUSIONS: Myocardial fibrosis quantification by ECV on CMR T1 mapping was shown to be an independent risk factor of heart failure, providing incremental prognostic value and risk stratification for cardiac events in ESRD patients. TRIAL REGISTRATION: Chinese Clinical Trial Registry ChiCTR-DND-17012976, 13/12/2017, Retrospectively registered.

Accurate identification of myocardial viability after myocardial infarction with novel manganese chelate-based MR imaging.

We developed a novel manganese (Mn2+ ) chelate for magnetic resonance imaging (MRI) assessment of myocardial viability in acute and chronic myocardial infarct (MI) models, and compared it with Gadolinium-based delay enhancement MRI (Gd3+ -DEMRI) and histology. MI was induced in 14 rabbits by permanent occlusion of the left circumflex coronary artery. Gd3+ -DEMRI and Mn2+ chelate-based delayed enhancement MRI (Mn2+ chelate-DEMRI) were performed at 7 days (acute MI, n = 8) or 8 weeks (chronic MI, n = 6) after surgery with sequential injection of 0.15 mmol/kg Gd3+ and Mn2+ chelate. The biodistribution of Mn2+ in tissues and blood was measured at 1.5 and 24 h. Blood pressure, heart rate (HR), left ventricular (LV) function, and infarct fraction (IF) were analyzed, and IF was compared with the histology. The Mn2+ chelate group maintained a stable hemodynamic status during experiment. For acute and chronic MI, all rabbits survived without significant differences in HR or LV function before and after injection of Mn2+ chelate or Gd3+ (p > 0.05). Mn2+ chelate mainly accumulated in the kidney, liver, spleen, and heart at 1.5 h, with low tissue uptake and urine residue at 24 h after injection. In the acute MI group, there was no significant difference in IF between Mn2+ chelate-DEMRI and histology (22.92 ± 2.21% vs. 21.79 ± 2.25%, respectively, p = 0.87), while Gd3+ -DEMRI overestimated IF, as compared with histology (24.54 ± 1.73%, p = 0.04). In the chronic MI group, there was no significant difference in IF between the Mn2+ chelate-DEMRI, Gd3+ -DEMRI, and histology (29.50 ± 11.39%, 29.95 ± 9.40%, and 29.00 ± 10.44%, respectively, p > 0.05), and all three were well correlated (r = 0.92-0.96, p < 0.01). We conclude that the use of Mn2+ chelate-DEMRI is reliable for MI visualization and identifies acute MI more accurately than Gd3+ -DEMRI.

[Automated Estimation of Stenosis Severity in Coronary Computed Tomography Angiography].

OBJECTIVE: To determine the value of automated detection in computed tomography angiography (CTA) for cases with greater than 70% coronary stenosis. METHODS: Fifty-seven patients who had both coronary CTA and digital subtraction angiography (DSA) were retrospectively recruited in this study. The patients were categorized into two groups using a cutoff value of 70% stenosis in DSA. The AW4.6 software was used to estimate the diameter and square values from the data obtained from CTA. The sensitivity (SE), specificity (SPE), positive predictive value (PPV) and negative predictive value (NPV) of the automated CTA estimations were calculated. RESULTS: A total of 178 vessels from the 57 patients were analyzed. The automated CTA estimations had moderate to high levels of agreements (Kappa value: 0.716-0.804, P < 0.001) with the DSA diagnoses, compared with low to moderate levels of agreements (Kappa value: 0.385-0.533, P < 0.001) in manual interpretations. The square estimations generated high SE (100%) and NPV (100%) for patient diagnoses (P < 0.016 7 vs. manual interpretations). The diameter estimations generated high SPE (90.48%) and PPV (94.12%) for patient diagnoses (P < 0.016 7, vs. manual interpretations). Similarly, high SE (96.92%) and NPV (97.89%) were found for square estimations in vessel diagnoses, while high SPE (94.69%) and PPV (90.16%) were found for diameter estimations in vessel diagnoses. CONCLUSIONS: Both automated diameter and square algorithms have high accuracy for diagnosing patients with greater than 70% coronary artery stenosis. The AW4.6 can improve the detection of severe stenosis that needs stent interventions.