Angiography­based quantitative flow ratio for functional assessment of intracranial atherosclerotic disease.

BACKGROUND: Intracranial atherosclerotic stenosis (ICAS), an important cause of stroke, is associated with a considerable stroke recurrence rate despite optimal medical treatment. Further assessment of the functional significance of ICAS is urgently needed to enable individualised treatment and, thus, improve patient outcomes. AIMS: We aimed to evaluate the haemodynamic significance of ICAS using the quantitative flow ratio (QFR) technique and to develop a risk stratification model for ICAS patients. METHODS: Patients with moderate to severe stenosis of the middle cerebral artery, as shown on angiography, were retrospectively enrolled. For haemodynamic assessment, the Murray law-based QFR (µQFR) was performed on eligible patients. Multivariate logistic regression models composed of µQFR and other risk factors were developed and compared for the identification of symptomatic lesions. Based on the superior model, a nomogram was established and validated by calibration. RESULTS: Among 412 eligible patients, symptomatic lesions were found in 313 (76.0%) patients. The µQFR outperformed the degree of stenosis in discriminating culprit lesions (area under the curve [AUC]: 0.726 vs 0.631; DeLong test p-value=0.001), and the model incorporating µQFR and conventional risk factors also performed better than that containing conventional risk factors only (AUC: 0.850 vs 0.827; DeLong test p-value=0.034; continuous net reclassification index=0.620, integrated discrimination improvement=0.057; both p<0.001). The final nomogram showed good calibration (p for Hosmer-Lemeshow test=0.102) and discrimination (C-statistic 0.850, 95% confidence interval: 0.812-0.883). CONCLUSIONS: The µQFR was significantly associated with symptomatic ICAS and outperformed the angiographic stenosis severity. The final nomogram effectively discriminated symptomatic lesions and may provide a useful tool for risk stratification in ICAS patients.

Prediction of high Ki-67 proliferation index of gastrointestinal stromal tumors based on CT at non-contrast-enhanced and different contrast-enhanced phases.

OBJECTIVES: To evaluate and analyze radiomics models based on non-contrast-enhanced computed tomography (CT) and different phases of contrast-enhanced CT in predicting Ki-67 proliferation index (PI) among patients with pathologically confirmed gastrointestinal stromal tumors (GISTs). METHODS: A total of 383 patients with pathologically proven GIST were divided into a training set (n = 218, vendor 1) and 2 validation sets (n = 96, vendor 2; n = 69, vendors 3-5). Radiomics features extracted from the most recent non-contrast-enhanced and three contrast-enhanced CT scan prior to pathological examination. Random forest models were trained for each phase to predict tumors with high Ki-67 proliferation index (Ki-67>10%) and were evaluated using the area under the receiver operating characteristic curve (AUC) and other metrics on the validation sets. RESULTS: Out of 107 radiomics features extracted from each phase of CT images, four were selected for analysis. The model trained using the non-contrast-enhanced phase achieved an AUC of 0.792 in the training set and 0.822 and 0.711 in the two validation sets, similar to models trained on different contrast-enhanced phases (p > 0.05). Several relevant features, including NGTDM Busyness and tumor size, remained predictive in non-contrast-enhanced and different contrast-enhanced images. CONCLUSION: The results of this study indicate that a radiomics model based on non-contrast-enhanced CT matches that of models based on different phases of contrast-enhanced CT in predicting the Ki-67 PI of GIST. GIST may exhibit similar radiological patterns irrespective of the use of contrast agent, and such radiomics features may help quantify these patterns to predict Ki-67 PI of GISTs. CLINICAL RELEVANCE STATEMENT: GIST may exhibit similar radiomics patterns irrespective of contrast agent; thus, radiomics models based on non-contrast-enhanced CT could be an alternative for risk stratification in GIST patients with contraindication to contrast agent. KEY POINTS: • Performance of radiomics models in predicting Ki-67 proliferation based on different CT phases is evaluated. • Non-contrast-enhanced CT-based radiomics models performed similarly to contrast-enhanced CT in risk stratification in GIST patients. • NGTDM Busyness remains stable to contrast agents in GISTs in radiomics models.

Diagnostic performance of double inversion recovery MRI sequence for synovitis of the wrist joints in rheumatoid arthritis.

PURPOSE: To assess the diagnostic accuracy of double inversion recovery (DIR) magnetic resonance imaging (MRI) sequences for synovitis of the wrist joints in patients with rheumatoid arthritis (RA). MATERIAL AND METHODS: Participants with newly diagnosed RA were enrolled between November 2019 and November 2020. MRI examinations of the wrist joints were performed using a contrast-enhanced T1-weighted imaging sequence (CE-T1WI) and DIR sequence. We measured synovitis score, number of synovial areas, synovial volume, mean synovium-to-bone signal ratio (SBR), and synovial contrast-to-noise ratio (SNR). The inter-reviewer agreement rated on a four-point scale was evaluated by calculating the weighted k statistics. Two MRI sequences were assessed using Bland-Altman analyses, and the diagnostic performance of DIR images was calculated using the chi-square test. RESULTS: A total of 47 participants were evaluated, and 282 joint regions in 5076 images were reviewed by two readers. There was no significant difference in synovitis scores (P = 0.67), number of synovial areas (P = 0.89), and synovial volume (P = 0.086) between the two MRI sequences. DIR images showed better SBR and SNR (all P < 0.01). There was good agreement between the two reviewers in terms of synovitis distribution (κ = 0.79). The synovitis was well agreed upon by the two readers according to Bland-Altman analyses. Using CE-T1WI as the reference standard, DIR imaging demonstrated a sensitivity of 94.1% and a specificity of 84.6% at the patient level. CONCLUSION: The non-contrast DIR sequence showed good consistency with CE-T1WI and potential for evaluating synovitis in patients with RA.

Cerebral hemodynamics in symptomatic anterior circulation intracranial stenosis measured by angiography-based quantitative flow ratio: association with CT perfusion.

OBJECTIVES: Cerebral hemodynamics is important for the management of intracranial atherosclerotic stenosis (ICAS). This study aimed to determine the utility of angiography-based quantitative flow ratio (QFR) to reflect cerebral hemodynamics in symptomatic anterior circulation ICAS by evaluating its association with CT perfusion (CTP). METHODS: Sixty-two patients with unilateral symptomatic stenosis in the intracranial internal carotid artery or middle cerebral artery who received percutaneous transluminal angioplasty (PTA) or PTA with stenting were included. Murray law-based QFR (µQFR) was computed from a single angiographic view. CTP parameters including cerebral blood flow, cerebral blood volume, mean transit time (MTT), and time to peak (TTP) were calculated, and relative values were obtained as the ratio between symptomatic and contralateral hemispheres. Relationships between µQFR and perfusion parameters, and between µQFR and perfusion response after intervention, were analyzed. RESULTS: Thirty-eight patients had improved perfusion after treatment. µQFR was significantly correlated with relative values of TTP and MTT, with correlation coefficients of -0.45 and -0.26, respectively, on a per-patient basis, and -0.72 and -0.43, respectively, on a per-vessel basis (all p < 0.05). Sensitivity and specificity for µQFR to diagnose hypoperfusion at a cut-off value of 0.82 were 94.1% and 92.1%, respectively. Multivariate analysis revealed that µQFRpost (adjusted odds ratio [OR], 1.48; p = 0.002), collateral score (adjusted OR, 6.97; p = 0.01), and current smoking status (adjusted OR, 0.03; p = 0.01) were independently associated with perfusion improvement after treatment. CONCLUSIONS: µQFR was associated with CTP in patients with symptomatic anterior circulation ICAS and may be a potential marker for real-time hemodynamic evaluation during interventional procedures. KEY POINTS: • Murray law-based QFR (µQFR) is associated with CT perfusion parameters in intracranial atherosclerotic stenosis and can differentiate hypoperfusion from normal perfusion. • Post-intervention µQFR, collateral score, and current smoking status are independent factors associated with improved perfusion after treatment.

A shortcut weighted fusion pyramid network for microcalcification detection in breast mammograms.

BACKGROUND: High-precision detection for individual and clustered microcalcifications in mammograms is important for the early diagnosis of breast cancer. Large-scale differences between the two types and low-contrast images are major difficulties faced by radiologists when performing diagnoses. OBJECTIVE: Deep learning-based methods can provide end-to-end solutions for efficient detection. However, multicenter data bias, the low resolution of network inputs, and scale differences between microcalcifications lead to low detection rates. Aiming to overcome the aforementioned limitations, we propose a pyramid feature network for microcalcification detection in mammograms, MicroDMa, with adaptive image adjustment and shortcut connections. METHODS: First, mammograms from multiple centers are represented as histograms and cropped by adaptive image adjustment, which mitigates the impact of dataset bias. Second, the proposed shortcut connection pyramid network ensures that the feature map contains more information for multiscale objects, while a shortcut path that jumps over layers enhances the efficiency of feature propagation from bottom to top. Third, the weights of each feature map at different scales in the fusion are trainable; thus, the network can automatically learn the contributions of all feature maps in the fusion stage. RESULT: Experiments were conducted on our in-house dataset and the public dataset INbreast. When the average number of positives per image is one on the in-house dataset, the recall rates of MicroDMa are the 96.8% for individual microcalcification and 98.9% for clustered microcalcification, which are higher than 69.1% and 91.2% achieved by recent deep learning model. Free-response receiver operating characteristic curve of MicroDMa is also higher than other methods when models are performed on INbreast. CONCLUSION: MicroDMa network is better than other methods and it can effectively help radiologists detect and identify two types of microcalcifications in clinical applications.

Evaluation of skeletal muscle perfusion changes in patients with peripheral artery disease before and after percutaneous transluminal angioplasty using multiparametric MR imaging.

PURPOSE: To evaluate muscle perfusion in patients with peripheral artery disease (PAD) before and after percutaneous transluminal angioplasty (PTA) of the limb by means of MR arterial spin labeling (ASL) and intravoxel incoherent motion (IVIM) under the resting state. METHODS: Twenty-eight patients with lower extremity PAD were enrolled. Skeletal muscles in lower extremities were examined at rest by using ASL and IVIM at 3.0 T. Imaging metrics, including blood flow (BF), perfusion fraction f, diffusion coefficient D, and pseudodiffusion coefficient D⁎, were measured in the anterior, lateral, soleus, and gastrocnemius muscle groups. Paired t-test was used to compare the imaging parameters before and after PTA. Pearson correlation analysis was conducted between imaging parameter changes and ankle brachial index (ABI) changes after PTA. RESULTS: ABI was significantly improved after PTA (P < 0.001). For ASL and IVIM imaging, significant changes were noted in ASL-BF and IVIM-D values in the lateral, soleus, and gastrocnemius muscle groups (all P < 0.0125) when comparing pre- and postoperative measurements. Changes in ASL-BF and IVIM-f values in the anterior muscle group, and in IVIM-D⁎ value in the anterior and soleus muscle groups after PTA, were found to be significantly correlated with ABI improvement (all P < 0.05). CONCLUSION: Multiparametric MR techniques including ASL and IVIM can detect the perfusion changes of lower limb tissue before and after PTA in patients with PAD under resting state.

Liver tumor segmentation and classification using FLAS-UNet++ and an improved DenseNet.

BACKGROUND: The incidence of liver tumors is among the top three in China. The treatments of benign and malignant tumors are different. Accurate diagnosis plays an important role in guiding the treatment of tumors. OBJECTIVE: The aim of this study is to solve the following: (1) blurred boundary between the liver tumor and other organs causes incorrect segmentation of liver tumor boundaries; (2) large difference in tumor size and the diversity in texture and grayscale are major challenges in liver tumor classification tasks. METHODS: Firstly, the liver tumor is segmented from the original CT images by a tumor segmentation network, UNet++ with fusion loss and atrous spatial pyramid pooling (FLAS-UNet++). The proposed segmentation method can solve the problem of tumor edge segmentation error by learning the tumor edge information. Secondly they are adaptively cropped according to the tumor volume to reduce the over-fitting and over-sensitivity of the deep network. Thirdly an improved Dense Block is designed to pay more attention to the changes in grayscale and texture between benign and malignant tumors. Finally, the features extracted from the network combined with tumor volume, patient's sex and age, are sent to a classifier for diagnosis. RESULT: Liver tumor segmentation results show that the dice, HD95 reached 71.9%, 12.1 mm, respectively. The classification results show that the accuracy, specificity, sensitivity and area under curve reached 82.4%, 79.8%, 84.4%, 87.5%, respectively. The segmentation and classification results are both better than other's methods and mainstream networks. CONCLUSIONS: In order to solve existing problems of liver tumor CT image classification methods, our method realizes the accurate segmentation and classification of liver tumors in CT images and has important clinical application value.

Using the apparent diffusion coefficient histogram analysis to predict response to neoadjuvant chemotherapy in patients with breast cancer: comparison among three region of interest selection methods.

Background: The apparent diffusion coefficient (ADC) value using histogram analysis is helpful to predict responses to neoadjuvant chemotherapy (NAC) in breast cancer. However, the measurement method has not reached a consensus. This study was to assess the diagnostic performance of the ADC histogram analysis at predicting patient response prior to NAC in breast cancer patients using different region of interest (ROI) selection methods. Methods: A total of 75 patients who underwent diffusion weighted imaging (DWI) prior to NAC were retrospectively enrolled from February 2017 to December 2019. Images were measured using small 2-dimensional (2D) ROI, large 2D ROI, and volume ROI methods. The measurement time and ROI size were recorded. Histopathologic responses were acquired using the Miller-Payne grading system after surgery. The inter- and intra-observer repeatability was analyzed and the ADC histogram values from the three ROI methods were compared. The efficacy of each method at predicting patient response prior to NAC was assessed using the area under the receiver operating characteristic curve (AUC) for the whole study population and subgroups according to molecular subtype. Results: Among the 75 enrolled patients, 26 (34.67%) were responsive to NAC therapy. The ADC histogram values were significantly different among the three ROI methods (P≤0.038). Inter- and intra-observer repeatability of the large 2D ROI method and the volume ROI method was generally greater than that observed with the 2D ROI method. The 10% ADC value of the large 2D ROI method showed the greatest AUC (0.701) in the whole study population and in the luminal subgroup (AUC 0.804). The volume ROI method required significantly more time than the other two ROI methods (P<0.001). Conclusions: The small 2D ROI method is not appropriate for predicting response prior to NAC in breast cancer patients due to the poor repeatability. When choosing the ROI method and the histogram parameters for predicting response prior to NAC in breast cancer patients using ADC-derived histogram analysis, 10% of the large 2D ROI method is recommended, especially in luminal A subtype patients.

The predictive value of DKI in breast cancer: Does tumour subtype affect pathological response evaluations?

PURPOSE: To explore the differences in quantitative parameters based on diffusion weighted imaging (DWI) and diffusion kurtosis imaging (DKI) between different immunohistochemical indicator statuses and their predictive value for neoadjuvant chemotherapy (NAC) among different phenotypes of breast cancer. METHODS: Eighty-one breast cancer patients who underwent NAC were enrolled in this retrospective study. Correlations between diffusion parameters and immunohistochemical indicators were determined using Spearman's test, and receiver operating characteristic (ROC) curves were constructed to assess the apparent diffusion coefficient (ADC), mean diffusivity (MD), and mean kurtosis (MK) in predicting the pathologic complete response (PCR). RESULTS: Correlations were observed between MK values and hormone receptor (HR) expression (oestrogen receptor (ER): r = 0.315 and progesterone receptor (PR): r = 0.268). The parameters ADC(0,1000), MK, and MD all showed correlations with Ki67 expression (r = 0.276, 0.316 and - 0.224, respectively). ER and Ki67 expression and the parameters MD and MK were significantly different between the PCR and non-PCR groups (AUC = 0.783, 0.688, 0.649 and 0.684, respectively). After splitting patients into subgroups, no significant differences were observed between the PCR and non-PCR groups with human epidermal growth factor receptor 2 (HER2) + and triple-negative (TN) breast cancer. However, we were surprised to find that ADC(0, 1000), MD, and MK were significantly different between different remission groups with HR+/HER2+ subtypes, and the AUCs of each parameter reached 0.794, 0.825, and 0.712, respectively. CONCLUSION: MK was correlated with HR expression. ADC(0, 1000) and DKI were correlated with Ki67 expression. ADC(0, 1000) and the non-Gaussian diffusion model are suitable for predicting PCR in patients with HR+/HER2+ breast cancer before NAC.

[Texture filtering based unsupervised registration methods and its application in liver computed tomography images].

Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.

A Novel Radiomics Nomogram for the Prediction of Secondary Loss of Response to Infliximab in Crohn's Disease.

PURPOSE: The prediction of the loss of response (LOR) to infliximab (IFX) is crucial for optimizing treatment strategies and shifting biologics. However, a secondary LOR is difficult to predict by endoscopy due to the intestinal stricture, perforation, and fistulas. This study aimed to develop and validate a radiomic nomogram for the prediction of secondary LOR to IFX in patients with Crohn's disease (CD). PATIENTS AND METHODS: A total of 186 biologic-naive patients diagnosed with CD between September 2016 and June 2019 were enrolled. Secondary LOR was determined during week 54. Computed tomography enterography (CTE) texture analysis (TA) features were extracted from lesions and analyzed using LIFEx software. Feature selection was performed by least absolute shrinkage and selection operator (LASSO) and ten-fold cross validation. A nomogram was constructed using multivariable logistic regression, and the internal validation was approached by ten-fold cross validation. RESULTS: Predictors contained in the radiomics nomogram included three first-order and five second-order signatures. The prediction model presented significant discrimination (AUC, 0.880; 95% CI, 0.816-0.944) and high calibration (mean absolute error of = 0.028). Decision curve analysis (DCA) indicated that the nomogram provided clinical net benefit. Ten-fold cross validation assessed the stability of the nomogram with an AUC of 0.817 and an accuracy of 0.819. CONCLUSION: This novel radiomics nomogram provides a predictive tool to assess secondary LOR to IFX in patients with Crohn's disease. This tool will help physicians decide when to switch therapy.

Diffusion-weighted MRI for predicting pathologic response to neoadjuvant chemotherapy in breast cancer: evaluation with mono-, bi-, and stretched-exponential models.

BACKGROUND: To investigate the performance of diffusion-weighted (DW) MRI with mono-, bi- and stretched-exponential models in predicting pathologic complete response (pCR) to neoadjuvant chemotherapy (NACT) for breast cancer, and further outline a predictive model of pCR combining DW MRI parameters, contrast-enhanced (CE) MRI findings, and/or clinical-pathologic variables. METHODS: In this retrospective study, 144 women who underwent NACT and subsequently received surgery for invasive breast cancer were included. Breast MRI including multi-b-value DW imaging was performed before (pre-treatment), after two cycles (mid-treatment), and after all four cycles (post-treatment) of NACT. Quantitative DW imaging parameters were computed according to the mono-exponential (apparent diffusion coefficient [ADC]), bi-exponential (pseudodiffusion coefficient and perfusion fraction), and stretched-exponential (distributed diffusion coefficient and intravoxel heterogeneity index) models. Tumor size and relative enhancement ratio of the tumor were measured on contrast-enhanced MRI at each time point. Pre-treatment parameters and changes in parameters at mid- and post-treatment relative to baseline were compared between pCR and non-pCR groups. Receiver operating characteristic analysis and multivariate regression analysis were performed. RESULTS: Of the 144 patients, 54 (37.5%) achieved pCR after NACT. Overall, among all DW and CE MRI measures, flow-insensitive ADC change (ΔADC200,1000) at mid-treatment showed the highest diagnostic performance for predicting pCR, with an area under the receiver operating characteristic curve (AUC) of 0.831 (95% confidence interval [CI]: 0.747, 0.915; P < 0.001). The model combining pre-treatment estrogen receptor and human epidermal growth factor receptor 2 statuses and mid-treatment ΔADC200,1000 improved the AUC to 0.905 (95% CI: 0.843, 0.966; P < 0.001). CONCLUSION: Mono-exponential flow-insensitive ADC change at mid-treatment was a predictor of pCR after NACT in breast cancer.

Three-dimensional breast tumor segmentation on DCE-MRI with a multilabel attention-guided joint-phase-learning network.

Accurate breast and tumor segmentations from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is vital in breast disease diagnosis. Here, we propose a novel attention-guided joint-phase-learning network for multilabel segmentation including the breast and tumors simultaneously and automatically. Instead of common multichannel inputs, our novel network consists of five separated streams designed for extracting comprehensive features for each DCE-MRI phase to fully use the dynamic intensity of enhanced images. A new time-signal intensity map was designed based on the DCE-MRI pixel-by-pixel values and added as an additional stream to reflect breast tumor dynamic variations. The multiple streams were fused in a fully connected layer to integrate the comprehensive tumor information. Weighted-loss was applied to the multilabel strategy to highlight breast tumor segmentation. In addition, the net applies the self-attention module with grid-based attention coefficients based on a global feature vector to emphasize breast regions and suppress irrelevant non-breast tissue features. We trained our method on 144 DCE-MRI datasets acquired from Philips and achieved mean Dice coefficients of 0.92 and 0.86 for breast and tumor segmentations that were superior to common networks with multichannel structures. The model was extended to an independent test set with 59 cases from two different MRI machines and achieved a Dice coefficient of 0.83 for breast tumor segmentation, which illustrates the robustness of our framework. The automatically generated masks can improve the accuracy and time of diagnosis of malignant and benign breast tumors. Qualitative comparisons illustrate that the proposed method has high precision and generalizability.

A cascade-network framework for integrated registration of liver DCE-MR images.

Registration of hepatic dynamic contrast-enhanced magnetic resonance images (DCE-MRIs) is an important task for evaluation of transarterial chemoembolization (TACE) or radiofrequency ablation by quantifying enhancing viable residue tumor against necrosis. However, intensity changes due to contrast agents combined with spatial deformations render technical challenges for accurate registration of DCE-MRI, and traditional deformable registration methods using mutual information are often computationally intensive in order to tolerate such intensity enhancement and shape deformation variability. To address this problem, we propose a cascade network framework composed of a de-enhancement network (DE-Net) and a registration network (Reg-Net) to first remove contrast enhancement effects and then register the liver images in different phases. In experiments, we used DCE-MRI series of 97 patients from Renji Hospital of Shanghai Jiaotong University and registered the arterial phase and the portal venous phase images onto the pre-contrast phases. The performance of the cascade network framework was compared with that of the traditional registration method SyN in the ANTs toolkit and Reg-Net without DE-Net. The results showed that the proposed method achieved comparable registration performance with SyN but significantly improved the efficiency.

Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach.

PURPOSE: Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 mutation in LGGs. MATERIALS AND METHODS: A total of 102 LGG patients were allocated to training (n = 67) and validation (n = 35) cohorts and were subject to Visually Accessible Rembrandt Images (VASARI) feature extraction (23 features) from conventional multimodal MRI and radiomics feature extraction (56 features) from apparent diffusion coefficient maps. Feature selection was conducted using the maximum Relevance Minimum Redundancy method and 0.632+ bootstrap method. A machine learning model to predict IDH1 mutation was then established using a random forest classifier. The predictive performance was evaluated using receiver operating characteristic (ROC) curves. RESULTS: After feature selection, the top 5 VASARI features were enhancement quality, deep white matter invasion, tumor location, proportion of necrosis, and T1/FLAIR ratio, and the top 10 radiomics features included 3 histogram features, 3 gray-level run-length matrix features, and 3 gray-level size zone matrix features and one shape feature. Using the optimal VASARI or radiomics feature sets for IDH1 prediction, the trained model achieved an area under the ROC curve (AUC) of 0.779 ± 0.001 or 0.849 ± 0.008 on the validation cohort, respectively. The fusion model that integrated outputs of both optimal VASARI and radiomics models improved the AUC to 0.879. CONCLUSION: The proposed machine learning approach using VASARI and radiomics features can predict IDH1 mutation in LGGs.

Blood oxygenation level-dependent cardiovascular magnetic resonance of the skeletal muscle in healthy adults: Different paradigms for provoking signal alterations.

PURPOSE: Stress blood oxygenation level-dependent (BOLD) cardiovascular magnetic resonance allows for quantitative evaluation of blood flow reserve in skeletal muscles. This study aimed to prospectively compare three commonly used skeletal BOLD cardiovascular magnetic resonance paradigms in healthy adults: gas inhalation, cuff compression-induced ischemia and postocclusive reactive hyperemia, and exercise. METHODS: Twelve young (22 ± 0.9 years) and 10 elderly (58 ± 5.0 years) healthy subjects underwent BOLD cardiovascular magnetic resonance under the three paradigms. T2∗ signal intensity time curves were generated and quantitative parameters were calculated. Meanwhile, stress transcutaneous oxygen pressure measurements were obtained as comparison. Measurement reproducibility was assessed with intraclass correlation coefficients. Differences in the T2∗ BOLD variation, the correlation with transcutaneous oxygen pressure, and the age-related change between paradigms were statistically analyzed. RESULTS: Minimum ischemic value and maximum hyperemic peak value showed the highest interobserver and interscan reproducibilities (intraclass correlation coefficient >0.90). The plantar dorsiflexion exercise paradigm elicited the largest T2∗ BOLD variation (15.48% ± 10.56%), followed by ischemia (8.30% ± 6.33%). Negligible to weak changes were observed during gas inhalation. Correlations with transcutaneous oxygen pressure measurements were found in the ischemic phase (r = 0.966; P < .001) and in the postexercise phase (r = -0.936; P < .001). Minimum ischemic value, maximum hyperemic peak value, maximum postexercise value, and slope of postexercise signal decay showed significant differences between young and elderly subjects (P < .01). CONCLUSION: Ischemia and reactive hyperemia have superior reproducibility, and exercise could induce the largest T2∗ variation. Key parameters from the two paradigms show age-related differences.

Diagnostic Utility of the Simplified Perfusion Fraction for Identifying Myocardial Injury in Patients With Reperfused ST-segment Elevation Myocardial Infarction.

BACKGROUND: Acute myocardial infarction (AMI) is a disease with high morbidity and mortality worldwide and the evaluation of myocardial injury and perfusion status following myocardial ischemia and reperfusion is of clinical value. PURPOSE: To assess the diagnostic utility of simplified perfusion fraction (SPF) in differentiating salvage and infarcted myocardium and its predictive value for left ventricular remodeling in patients with reperfusion ST-segment elevation myocardial infarction (STEMI). STUDY TYPE: Prospective. POPULATION: Forty-one reperfused STEMI patients and 20 healthy volunteers. FIELD STRENGTH/SEQUENCE: 3.0T MRI. The MR examination included cine, T2 -short tau inversion recovery (T2 -STIR), first pass perfusiong (FPP)，phase sensitive inversion recovery (PSIR), and diffusion-weighted imaging (DWI). ASSESSMENT: SPF values among different myocardium regions (infarcted, salvaged, remote, and MVO) and stages of reperfused STEMI patients as well as normal controls were measured. The diagnostic utility of SPF values in differentiating salvaged and infarcted myocardium was assessed. STATISTICAL ANALYSIS: Independent t-test and the Mann-Whitney U-test. Logistic regression. RESULTS: SPF values in healthy controls were not significantly different than SPF values in the remote myocardium of patients (40.09 ± 1.47% vs. 40.28 ± 1.93%, P = 0.698). In reperfusion STEMI patients, SPF values were lower in infarcted myocardium compared to remote and salvaged myocardium (32.15 ± 2.36% vs. 40.28 ± 1.93%, P < 0.001; 32.15 ± 2.36% vs. 36.68 ± 2.71%, P < 0.001). SPF values of infarcted myocardium showed a rebound increase from acute to convalescent stages (32.15 ± 2.36% vs. 34.69 ± 3.69%, P < 0.001). When differentiating infarcted and salvaged myocardium, SPF values demonstrated an area under the curve (AUC) of 0.89 (sensitivity 85.4%, specificity 80.5%, cutoff 34.42%). Lower SPF values were associated with lower odds ratio (OR = 0.304) of left ventricular remodeling after adjusting for potential confounders with a confidence interval (CI) of 0.129-0.717, P = 0.007. DATA CONCLUSION: SPF might be able to differentiate salvaged and infarcted myocardium and is a strong predictor of left ventricular remodeling in reperfused STEMI patients. Level of Evidence 2 Technical Efficacy Stage 2.

Impact of different scanners and acquisition parameters on robustness of MR radiomics features based on women's cervix.

MR Radiomics based on cervical lesions from one single scanner has achieved promising results. However, it is a challenge to achieve clinical translation. Considering multi-scanners and non-uniform scanning parameters from different centers in a real-world medical scenario, we should first identify the influence of such conditions on the robustness of MR radiomics features (RFs) based on the female cervix. In this study, 9 healthy female volunteers were enrolled and 3 kiwis were selected as references. Each of them underwent T2 weighted imaging in three different 3.0-T MR scanners with uniform acquisition parameters, and in one MR scanner with various scanning parameters. A total of 396 RFs were extracted from their images with and without decile intensity normalization. The RFs' reproducibility was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). Representative features were selected using the hierarchical cluster analysis and their discrimination abilities were estimated by ROC analysis through retrospective comparison with the junctional zone and the outer muscular layer of healthy cervix in patients (n = 58) with leiomyoma. This study showed that only a few RFs were robust across different MR scanners and acquisition parameters based on females' cervix, which might be improved by decile intensity normalization method.

Simplified perfusion fraction from diffusion-weighted imaging in preoperative prediction of IDH1 mutation in WHO grade II-III gliomas: comparison with dynamic contrast-enhanced and intravoxel incoherent motion MRI.

Background Effect of isocitr ate dehydrogenase 1 (IDH1) mutation in neovascularization might be linked with tissue perfusion in gliomas. At present, the need of injection of contrast agent and the increasing scanning time limit the application of perfusion techniques. We used a simplified intravoxel incoherent motion (IVIM)-derived perfusion fraction (SPF) calculated from diffusion-weighted imaging (DWI) using only three b-values to quantitatively assess IDH1-linked tissue perfusion changes in WHO grade II-III gliomas (LGGs). Additionally, by comparing accuracy with dynamic contrast-enhanced (DCE) and full IVIM MRI, we tried to find the optimal imaging markers to predict IDH1 mutation status. Patients and methods Thirty patients were prospectively examined using DCE and multi-b-value DWI. All parameters were compared between the IDH1 mutant and wild-type LGGs using the Mann-Whitney U test, including the DCE MRI-derived Ktrans, ve and vp, the conventional apparen t diffusion coefficient (ADC0,1000), IVIM-de rived perfusion fraction (f), diffusion coefficient (D) and pseudo-diffusion coefficient (D*), SPF. We evaluated the diagnostic performance by receive r operating characteristic (ROC) analysis. Results Significant differences were detected between WHO grade II-III gliomas for all perfusion and diffusion parameters (P < 0.05). When compared to IDH1 mutant LGGs, IDH1 wild-type LGGs exhibited significantly higher perfusion metrics (P < 0.05) and lower diffusion metrics (P < 0.05). Among all parameters, SPF showed a higher diagnostic performance (area under the curve 0.861), with 94.4% sensitivity and 75% specificity. Conclusions DWI, DCE and IVIM MRI may noninvasively help discriminate IDH1 mutation statuses in LGGs. Specifically, simplified DWI-derived SPF showed a superior diagnostic performance.