Academic Radiology最新文献

Rationale and objectives: The aim of this study was to compare the image quality of a deep learning (DL)-accelerated volumetric interpolated breath-hold examination (VIBE) sequence with a standard (ST) VIBE sequence in assessing the uterus.

Materials and methods: Between April and December 2023, a total of 61 female patients (aged 41 ± 14 years) who were referred for an magnetic resonance imaging (MRI) of the pelvis were included in this prospective study, after providing informed consent. All examinations were performed with a 1.5 T MRI scanner. The DL VIBE and ST VIBE were acquired before (noncontrast [NC]) and after (contrast-enhanced [CE]) contrast administration in the sagittal orientation. Three readers independently evaluated the following aspects of the images' quality using 4-point Likert scales (1 = nondiagnostic; 4 = excellent): global image quality, anatomy delineation, and lesion detection/demarcation. Motion artifacts and noise were also assessed (1 = no artifacts; 4 = severe artifacts). In addition, all three readers selected their preferred sequence and the sequence in which they had the highest diagnostic confidence.

Results: After exclusions, the data for 54 patients were analyzed. The DL VIBE was preferred by all three readers in almost all cases (NC: 99%; CE: 96%) and rated highest for diagnostic confidence (NC: 98%; CE: 90%). The image quality of the DL VIBE was rated statistically significantly better than that of the ST VIBE, with simultaneously reduced noise and motion artifacts (p < 0.01). The image quality of the DL VIBE was predominantly rated with a score of 4 (NC: 54%; CE: 78%), while the image quality of the ST VIBE was mostly rated with a score of 3 (NC: 53%; CE: 80%). The anatomy of the female pelvis was significantly better delineated by the DL VIBE (p < 0.01; log[OR] = 5.3; 95% CI: 3.7-6.8), and lesions were more clearly demarcated (p < 0.01; log[OR] = 6.7; 95% CI: 4.5-8.8).

Conclusion: The DL VIBE sequence showed a significant overall improvement in all image quality characteristics for all readers and was preferred in most cases. The clinical implementation of DL VIBE in MRI of the female pelvis could improve the diagnostic value of the examination.

Background: This study investigates the influence of metabolic dysfunction-associated fatty liver disease (MAFLD)/metabolic dysfunction-associated steatotic liver disease (MASLD) on the incidence of hepatocellular carcinoma (HCC) among general population and patients with chronic hepatitis B (CHB). It also explores its implications for the long-term prognosis of HCC patients following hepatic resection.

Methods: Relevant studies were selected based on predefined inclusion and exclusion criteria, including adherence to diagnostic criteria for MAFLD/MASLD and reporting hazard ratios (HRs) using Cox proportional hazards models. The meta-analysis utilized R statistical software (version 4.3.0) with random-effects models to calculate pooled HRs. Sensitivity analyses were performed to ensure the robustness of results.

Results: Our analysis included 19 studies, among which 12 studies focused on the cumulative incidence of HCC in the general population (979,213 individuals; 294,984 with MAFLD/MASLD and 684,229 without). MAFLD/MASLD significantly increased the cumulative incidence of HCC in the general population (HR = 1.82; 95% CI, 1.34-2.48). In CHB patients (316,445 participants; 108,183 with MAFLD/MASLD and 208,262 without), the cumulative incidence of HCC was also higher in the MAFLD/MASLD group (HR = 1.36; 95% CI, 1.32-1.40). For 7383 postoperative HCC patients (2192 with MAFLD/MASLD and 5191 without), MAFLD/MASLD did not significantly affect overall survival (OS) (HR = 0.93; 95% CI, 0.69-1.26) or recurrence-free survival (RFS) (HR = 0.98; 95% CI, 0.86-1.13).

Conclusion: In conclusion, MAFLD/MASLD can significantly increase the incidence of HCC in both the general population and CHB patients. However, it does not significantly influence long-term prognosis after hepatic resection, suggesting that other factors may have a greater role in determining postoperative outcomes. This highlights the need for tailored management strategies for MAFLD/MASLD patients undergoing HCC resection.

Background: Granulomatous mastitis (GM) is an inflammatory breast condition with high recurrence risk, often complicating management. Existing imaging techniques provide limited predictive insight. This study aims to analyze the correlation between contrast-enhanced ultrasound (CEUS) features and the risk of GM recurrence, developing a predictive model.

Methods: A retrospective review included 510 patients diagnosed with GM from 2017 to 2022, divided into non-recurrence (non-recurrence, n=389) and recurrence (recurrence, n=121) groups. CEUS was conducted to assess lesion perfusion and enhancement patterns. Key features such as isoenhancement and perfusion defects were analyzed. Correlation analyses, ROC, univariate, and multivariate analyses informed the predictive model construction using XGBoost. External validation was performed to confirm model reliability.

Results: CEUS features like homogeneous (rho=0.137, P=0.002) and heterogeneous isoenhancement (rho=0.134, P=0.002) showed significant correlations with recurrence risk. Perfusion defects (rho=0.127, P=0.004) and not smooth edge lines of defects (rho=0.234, P<0.001) were also associated. The predictive model, integrating CEUS patterns, achieved an area under the curve (AUC) of 0.822, indicating strong predictive validity. External validation confirmed the model's efficacy (AUC=0.808).

Conclusion: CEUS imaging reveals specific vascular and enhancement patterns that correlate with the risk of GM recurrence, providing critical diagnostic and prognostic value.

Rationale and objectives: To develop a machine learning (ML) model based on clinicopathological and imaging features to predict the Human Epidermal Growth Factor Receptor 2 (HER2) positive expression (HER2-p) of breast cancer (BC), and to compare its performance with that of a logistic regression (LR) model.

Materials and methods: A total of 2541 consecutive female patients with pathologically confirmed primary breast lesions were enrolled in this study. Based on chronological order, 2034 patients treated between January 2018 and December 2022 were designated as the retrospective development cohort, while 507 patients treated between January 2023 and May 2024 were designated as the prospective validation cohort. The patients were randomly divided into a train cohort (n=1628) and a test cohort (n=406) in an 8:2 ratio within the development cohort. Pretreatment mammography (MG) and breast MRI data, along with clinicopathological features, were recorded. Extreme Gradient Boosting (XGBoost) in combination with Artificial Neural Network (ANN) and multivariate LR analyses were employed to extract features associated with HER2 positivity in BC and to develop an ANN model (using XGBoost features) and an LR model, respectively. The predictive value was assessed using a receiver operating characteristic (ROC) curve.

Results: Following the application of Recursive Feature Elimination with Cross-Validation (RFE-CV) for feature dimensionality reduction, the XGBoost algorithm identified tumor size, suspicious calcifications, Ki-67 index, spiculation, and minimum apparent diffusion coefficient (minimum ADC) as key feature subsets indicative of HER2-p in BC. The constructed ANN model consistently outperformed the LR model, achieving the area under the curve (AUC) of 0.853 (95% CI: 0.837-0.872) in the train cohort, 0.821 (95% CI: 0.798-0.853) in the test cohort, and 0.809 (95% CI: 0.776-0.841) in the validation cohort.

Conclusion: The ANN model, built using the significant feature subsets identified by the XGBoost algorithm with RFE-CV, demonstrates potential in predicting HER2-p in BC.

Rationale and objectives: Cognitive disorders, such as Alzheimer's disease (AD) and Parkinson's disease (PD), significantly impact the quality of life in older adults. Mild cognitive impairment (MCI) is a critical stage for intervention and can predict the development of dementia. The causes of these two diseases are not fully understood, but there is an overlap in their neuropathology. There is a lack of direct comparison regarding the changes in functional connectivity within and between different brain networks during cognitive impairment in these two diseases.

Objective: This study aims to investigate changes in brain network connectivity of AD and PD with mild cognitive impairment, shedding light on the underlying neuropathological mechanisms and potential treatment options.

Methods: A total of 33 AD-MCI patients, 55 PD-MCI patients, and 34 healthy controls (HCs) underwent resting-state functional MRI and cognitive function assessment using Independent Components Analysis (ICA). We compared intra- and inter-network functional connectivity among the three groups and analyzed the correlation between changes in functional connectivity and cognitive domain performance.

Results: Using ICA, we identified eight functional networks. In the AD-MCI group, reductions in internetwork functional connectivity were mainly around the default mode network (DMN). Intra-network functional connectivity was widely reduced, especially in the DMN, while intra-network functional connectivity in the Salience Network (SN) increased. In contrast, in the PD-MCI group, reductions in internetwork functional connectivity were mainly around the SN. Intra-network functional connectivity in the SN decreased, while intra-network functional connectivity in other networks increased.

Conclusion: This study highlights distinct yet overlapping changes in brain network connectivity in AD and PD, providing new insights into the underlying mechanisms of cognitive impairment disorders.

Rationale and objectives: To create a radiomics model based on computed tomography (CT) to predict overall survival in ovarian cancer patients. To combine Rad-score with genomic data to explore the association between gene expression and Rad-score.

Materials and methods: Imaging and clinical data from 455 patients with ovarian cancer were retrospectively analyzed. Patients were categorized into training cohort, validation cohort and test cohort. Cox regression analysis and the least absolute shrinkage and selection operator (LASSO) methods were utilized to identify characteristics and develop the Rad-score. Radiomics models were developed and evaluated for predictive efficacy and clinical incremental value. Application of genomic data from the cancer genome atlas (TCGA) to reveal differential genes in different Rad-score groups. Screening hub genes and exploring the functions of hub genes through bioinformatics analysis and machine learning.

Results: Prognostic models based on FIGO, tumor residual disease and Rad-score were developed. The receiver operating characteristic (ROC) curves showed that the 1, 3, and 5 year area under curves (AUCs) of the model were in the training group (0.816, 0.865 and 0.862, respectively), validation group (0.845, 0.877, 0.869, respectively) and test group (0.899, 0.906 and 0.869, respectively) had good predictive accuracy. Calibration curves showed good agreement between observations and predictions. Decision curve analysis revealed a high net benefit of the clinical-radiomics model. The clinical impact curve (CIC) showed good clinical applicability of the clinical-radiomics model. Analysis of sequencing data from the TCGA database revealed EMP1 as a hub gene for radiomics modeling. It revealed that its biological function may be associated with extracellular matrix organization and focal adhesion.

Conclusion: Prognostic models based on FIGO, Tumor residual disease, and Rad-score can effectively predict the overall survival (OS) of ovarian cancer patients. Rad-score may enable prognostic prediction of ovarian cancer patients by revealing the expression level of EMP1 and its biological function.

Rationale and objectives: Accurate distinguish malignant from benign renal masses remains a challenge for radiologists. The purpose of this study was to evaluate the value of Color Doppler Flow Imaging (CDFI), MicroFlow Imaging (MFI) and Contrast-enhanced Ultrasound (CEUS) in diagnosing solid renal tumors.

Materials and methods: A total of 291 patients with 300 solid renal tumors pathologically confirmed were retrospectively analyzed between January 2020 and December 2022. Each patient underwent CDFI, MFI, and CEUS examinations before surgery. The diagnostic efficacy of CDFI, MFI and CEUS in assessing renal tumors was compared based on blood flow grade, vascular morphology and CEUS characteristics.

Results: MFI identified 243 renal lesions (81%) with blood flow grade (2, 3) and vascular morphology (IV, V), significantly outperforming CDFI, which detected 147 cases (49%). MFI demonstrated statistically significant differences in detecting blood flow signals and predicting renal malignancy compared to CDFI (p < 0.001). In CEUS examination, significant differences were observed in wash-in, enhancement intensity, wash-out, and perilesional rim-like enhancement of the contrast agent between malignant and benign renal lesions (all p < 0.001). The areas under the receiver operating characteristic curves (AUCs) for MFI and CEUS were 0.838 and 0.788, respectively, both higher than that for CDFI (0.695). In diagnosing solid renal tumors, MFI and CEUS showed significant differences compared to CDFI (p < 0.05), although no significant difference was found between MFI and CEUS (p = 0.075). The diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of CDFI, MFI and CEUS were as follows: 0.600 vs.0.893 vs.0.920; 0.554 vs. 0.920 vs.0.984; 0.837 vs. 0.755 vs.0.592; 0.946 vs. 0.951 vs.0.925; 0.268 vs. 0.649 vs.0.879.

Conclusion: MFI demonstrates higher sensitivity in detecting microvascular signs of renal tumors compared to CDFI. Moreover, MFI exhibits comparable diagnostic performance to CEUS in distinguishing malignant from benign renal masses.

Rationale and objectives: Non-invasive assessment of renal fibrosis in patients with chronic kidney disease (CKD) remains a clinical challenge. This study aims to integrate radiomics and clinical factors to develop an end-to-end pipeline for predicting interstitial fibrosis (IF) in CKD patients.

Materials and methods: This retrospective study included 80 patients with CKD, with 53 patients in training set and 27 patients in test set. All patients underwent renal computed tomography (CT) scans and biopsy. Patients were classified into two groups based on their renal IF grade: mild-moderate and severe. Radiomics features were extracted from the automatically segmented right renal region on CT images, and univariate analysis along with multiple Least Absolute Shrinkage and Selection Operator (LASSO) was employed to construct the radiomics signature. Subsequently, logistic regression models were developed to create the radiomics model and the combined model. The predictive performance of both models was evaluated through discrimination, calibration, and decision curve analysis (DCA), and a nomogram was constructed for the model demonstrating superior performance.

Results: The combined model significantly outperformed the radiomics model, achieving a cross-validated AUC of 0.935±0.041 in the training set, compared to 0.804±0.024 for the radiomics model. In the test set, the combined model outperformed the radiomics model, with an AUC of 0.918 [95% CI 0.799-1] vs. 0.764 [95% CI 0.549-0.979], p=0.031 (DeLong test, Statistic: -2.152). Calibration curves and DCA indicated that the combined model demonstrated good calibration and better clinical net benefit.

Conclusion: This end-to-end workflow could serve as a potential non-invasive tool to predict renal IF grade (mild-moderate vs. severe) in CKD patients.

Rationale and objectives: Alzheimer's disease (AD) is the most common pathogenesis of dementia, and mild cognitive impairment (MCI) is considered as the intermediate stage from normal elderly to AD. Early detection of MCI is an essential step for the timely intervention of AD to slow the progression of this disease. Different form previous studies in the whole-brain spontaneous activities, this research aimed to explore the low-frequency amplitude spectrum activities of patients with MCI within the default mode network (DMN), which has been involved in the process of maintaining normal cognitive function.

Materials and methods: Based on resting-state functional magnetic resonance imaging, the amplitude of low-frequency fluctuation (ALFF) was used to analyze alterations in brain regions. The Mini-Mental State Examination and Montreal Cognitive Assessment were used for cognitive assessments. The correlation between imaging and behavioral results was analyzed among patients with MCI (n=36) and normal controls (n=26).

Results: The DMN is the highest coverage of brain network regarding changes in local brain activity in patients with MCI. And the MCI group showed significant aberrant lateralization of the ALFF value.

Conclusion: The current results of our study has confirmed the hypothesis of cerebral functional impairment and compensation, and suggests that functional changes in the brain regions with reduced values of the ALFF occurred earlier than those with increased values. In a word, it suggested that the aberrant spontaneous brain activity in the DMN might be a specific imaging marker for improving MCI diagnoses.