BMC Medical Imaging最新文献

Background: Diabetic peripheral neuropathy (DPN) is a prevalent complication of diabetes mellitus, and is often underdiagnosed because of its variable clinical presentation and operator-dependent diagnostic tools. Shear wave elastography (SWE), which quantitatively evaluates tissue stiffness, has the potential to enhance conventional ultrasound by improving diagnostic accuracy and consistency. Nevertheless, a comprehensive analysis examining the extent to which the integration of SWE with conventional ultrasound can enhance the diagnostic performance of radiologists across varying levels of expertise has yet to be performed.

Methods: In this study, a total of 458 lower extremities from patients with type 2 diabetes were examined via ultrasound and SWE. Four radiologists (two seniors and two juniors) independently assessed the grayscale ultrasound, SWE, and combined images. Diagnostic performance was compared via receiver operating characteristic (ROC) curves and sensitivity and specificity metrics.

Results: SWE measurements revealed significantly greater stiffness of the tibial nerve in the DPN group than in the non-DPN group, with values of 37.30 kPa versus 25.40 kPa (P < 0.001) and corresponding shear wave velocities of 3.54 m/s versus 2.90 m/s (P < 0.001). The combined images improved diagnostic accuracy across all readers. Notably, junior radiologists exhibited a substantial improvement in terms of sensitivity (ΔSensitivity = 25.565, 95% CI: 18.477-32.653, P = 0.004). In contrast, for the senior radiologists, neither the sensitivity nor the specificity significantly increased with increasing integration SWE.

Conclusion: Combining SWE with conventional ultrasound improves the diagnostic accuracy for DPN and helps reduce performance gaps between junior and senior radiologists. SWE may serve as an effective adjunct to support early detection and consistent evaluation of DPN in clinical practice.

Background: Clear cell renal cell carcinoma (ccRCC) exhibits significant biological heterogeneity, with aggressive forms demonstrating poor prognosis. Accurate preoperative discrimination between aggressive and indolent ccRCC is critical for individualized treatment but remains challenging. This study aimed to evaluate the performance of machine learning models based on multiparametric MRI radiomics for distinguishing aggressive from indolent ccRCC.

Methods: This retrospective study included 157 patients with pathologically confirmed ccRCC, comprising 114 indolent and 43 aggressive cases. Regions of interest (ROIs) were manually delineated on five MRI sequences: T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), as well as the corticomedullary, nephrographic, and excretory phases of contrast-enhanced fat-suppressed T1WI (CE-fsT1WI). Thirty-one feature combinations derived from the five sequences were input into 168 classification models (constructed using 8 classifiers and 21 feature selection methods). The performance of 5,208 models was compared, and the top-ranked features were analyzed.

Results: Aggressive ccRCC showed significantly larger maximum tumor diameter compared with indolent tumors (8.3 [5.7-9.5] cm vs. 3.0 [2.2-4.2] cm, p < 0.05). Radiomic features derived from T2WI contributed most substantially to model performance relative to other MRI sequences, with the optimal classification model "RF + ICAP" achieving an area under the curve (AUC) of 0.960, accuracy of 86.1%, sensitivity of 86.4%, and specificity of 86.0%. Notably, the top 10 most predictive features from T2WI were predominantly shape-related features.

Conclusion: Radiomics features from renal T2WI demonstrated superior discriminative value compared with T1WI and contrast-enhanced T1WI in differentiating aggressive from indolent ccRCC. Through the integration of multiple classifiers and feature selection algorithms, the optimal classification model was identified, demonstrating the potential to distinguish aggressive ccRCC pathology.

Purpose: To explore alterations and correlations of multifidus (MF), erector spinae (ES), psoas major (PM), and gluteus medius (Gmed) in intervertebral disc degeneration (IVDD) using multi-echo Magnetic resonance imaging (MRI) based water-fat separation.

Methods: We retrospectively collected data from patients who presented to our hospital with low back pain. Proton density fat fraction (PDFF) was measured using the multi-echo Dixon VIBE sequence. IVDD at the L4-L5 level was assessed on T2-weighted sagittal images according to the Pfirrmann grading system. Spearman correlation coefficients were calculated to evaluate the relationships between MF, ES, PM, and Gmed cross-sectional area (CSA), PDFF, and IVDD. Multivariable linear regression analysis was performed to determine independent associations of gender, age, and Pfirrmann grade with CSA and PDFF of the MF, ES, PM and Gmed.

Results: A total of 506 patients with a mean age of 44.43 ± 13.49 years were included. As Pfirrmann grade increased, the CSA of the MF, ES, and PM progressively decreased. With advancing Pfirrmann grade, the PDFF of the MF, ES, and PM demonstrated a progressive increase. The Pfirrmann grade showed a moderate negative correlation with MF and ES CSA (Rho = -0.395, Rho = -0.348, p < 0.001), and a weak negative correlation with PM CSA (Rho = -0.293, p < 0.05). Conversely, Pfirrmann grade demonstrated a strong positive correlation with MF and ES PDFF (Rho = 0.595, Rho = 0.610, p < 0.001), and a moderate positive correlation with PM PDFF (Rho = 0.415, p < 0.001). Multivariate linear regression analysis revealed that gender, age, and IVDD were independently associated with CSA and PDFF of the MF and ES muscles (P < 0.001). However, for the PM muscle, only its PDFF showed independent correlations with IVDD, gender, and age, while PM CSA was independently linked to gender and age but not to Pfirrmann grade. With an increase in the Pfirrmann grade of intervertebral discs, Gmed CSA shows a tendency to increase. The Pfirrmann grade demonstrated weak positive correlations with both the Gmed CSA and PDFF (Rho = 0.160, Rho = 0.264, p < 0.001). After adjusting for the confounding effects of sex and age, the Pfirrmann grade remained an independent factor associated with Gmed CSA (β = 0.136, p = 0.001).

Conclusions: MRI reliably evaluates paraspinal muscles and Gmed atrophy, particularly in quantifying fat content. PDFF emerges as a valuable tool for assessing fat infiltration in paraspinal muscles.

Background: Spontaneous intracranial hypotension syndrome (SIH)-induced chronic subdural hematoma (CSDH) often presents with orthostatic headaches but is frequently misdiagnosed, leading to inappropriate treatments like fatal hematoma drainage instead of epidural blood patches. In clinical practice, reliable and quantitative diagnostic criteria for this condition are lacking. This study uses initial CT scans to identify novel radiographic markers for accurately diagnosing SIH-induced CSDH.

Methods: We retrospectively reviewed 310 consecutives hospitalized CSDH cases from January 2008 to May 2023. Among these, 54 were bilateral, with 11 induced by SIH; two secondary intracranial hypotension cases were excluded. We analyzed nine primary SIH-induced cases, comparing clinical and preoperative CT features with 43 non-SIH bilateral cases, focusing on the parasagittal subdural space (PSS) volume. We also conducted propensity score matching to validate our findings.

Results: Patients with SIH-induced bilateral CSDH were significantly younger than those without SIH (mean age 54.7 vs. 76.2 years; P < 0.001). Orthostatic headache was more common in the SIH group (66.7% vs. 2.3%, P < 0.001). While hematoma volumes were similar, PSS volume was significantly larger in the SIH group (mean 15.0 vs. 5.1 mL, P = 0.007). ROC analysis identified an exploratory PSS cut-off of 11.1 mm², which yielded a sensitivity of 86% and a specificity of 66.7% (P = 0.009). Linear regression and qualitative assessments indicated a significant association between PSS volume and crural-and-ambient cistern obliteration, as well as cerebellar ptosis in the SIH group (P < 0.001).

Conclusion: A preserved PSS on coronal CT represents a novel, quantitative marker for SIH-induced CSDH and may serve as a practical diagnostic clue, particularly when MRI is unavailable.

Purpose: To establish a combined model integrating imaging-based radiomics features and clinical parameters to predict the prognosis of hypoxic-ischemic encephalopathy (HIE) in full-term newborns one year after birth.

Methods: A total of 180 full-term neonates diagnosed with HIE were retrospectively analyzed. Based on cognitive and motor function scores at 12 months post-birth, patients were categorized into two groups: Group B, representing those with a good prognosis (n = 84), and Group W, representing those with a poor prognosis (n = 96). The dataset was randomly divided into a training dateset (n = 126) and a testing dateset (n = 54). Clinical characteristics were first compared between the two groups. Subsequently, three predictive models were developed: a clinical model, a radiomics model, and a combined model integrating both clinical and radiomics features. The predictive performances of these models were evaluated using receiver operating characteristic (ROC) curve analysis, and their discriminative abilities were quantified by calculating the area under the curve (AUC).

Results: The Apgar scores at 1, 5, and 10 min after birth were significantly higher in Group B compared to Group W (P < 0.05). In the clinical model, the Apgar score at 10 min was identified as the strongest prognostic factor, yielding an AUC of 0.857 in the training datest and 0.737 in the testing datest. In the radiomics model, nine radiomics features were significantly associated with prognosis, achieving AUCs of 0.916 and 0.770 in the training and testing datests, respectively. In the combined model, seven radiomics features together with the 5-minute and 10-minute Apgar scores were identified as independent predictors of prognosis. This integrated model demonstrated superior predictive performance, with AUCs of 0.952 in the training datest and 0.823 in the testing datest.

Conclusions: The combined model incorporating MR-based radiomics signatures and clinical parameters demonstrates high predictive accuracy for assessing the one-year prognosis of full-term neonates with HIE, suggesting a promising framework for early risk stratification and individualized management of affected infants.

Purpose: We investigated lung computed tomography (CT) radiomics features feasibility for brain metastasis (BM) prediction in patients with epidermal growth factor receptor-positive lung adenocarcinoma (LA-EGFRp).

Methods: Lung CT images and clinical data of patients were retrospectively analyzed. Patients were classified into BM and non-BM groups, and randomly divided into training and test sets (8:2 ratio). Clinical and CT radiomics features were extracted and trained with various machine-learning classifiers to construct the clinical, radiomics, and hybrid models, respectively. Model performance was assessed using receiver operating characteristic curves.

Results: Among 198 included patients, 72 developed BM. Areas under the curve (AUCs) for predicting BM in the training and test sets were 0.781 and 0.701, 0.989 and 0.865, and 0.957 and 0.929 for the clinical, radiomics, and hybrid models, respectively. The AUCs of the radiomics and hybrid models were significantly higher in the training set (P < 0.001) and that of the hybrid model in the test set was higher compared with the clinical model (P < 0.05).

Conclusions: Models based on clinical data, lung CT-derived radiomics features, and the two combined predicted BM in LA-EGFRp. Combining radiomics and clinical features significantly improved BM prediction, thereby providing an effective tool for clinical decision-making.