Current Medical Imaging Reviews最新文献

Background: Mediastinal cholesterol granuloma (MCG) is an exceedingly rare condition, with a limited number of cases reported worldwide. The clinical and imaging characteristics of MCG remain poorly understood and often lead to misdiagnosis. This case report of a young female patient contributes to the literature by summarizing the clinical features, imaging findings, and differential diagnosis of MCG in a demographic category rarely described in previous reports.

Case description: A 30-year-old female with a history of community-acquired pneumonia, pulmonary tuberculosis (cured), and syphilis was incidentally found to have an anterior mediastinal mass on imaging. This patient had no history of trauma or other risk factors related to the onset of MCG. Meanwhile, the gender and age characteristics were also different from those commonly seen in the literature. Surgical resection at our hospital confirmed the diagnosis of thymic cholesterol granuloma. Literature review identified 24 reported cases of MCG, predominantly in older males (94.74%; average age, 58.3 years), with a geographic distribution across Europe, East Asia, and North America (36.8%, 31.6%, and 26.3%, respectively). Notably, three of the cases involved young and middle-aged patients with a history of chest trauma. The imaging features varied, with magnetic resonance imaging (MRI) showing low signal (indicating cholesterol crystals) or high signal intensity (due to methemoglobin) on T1/T2-weighted images. Positron emission tomography (PET) scans typically revealed high uptake signals attributed to chronic granulomatous inflammation.

Conclusion: MCG is a rare anterior mediastinal lesion with nonspecific imaging features. A history of dyslipidemia or chest trauma combined with compatible imaging findings should prompt consideration of MCG in the differential diagnosis. The possibility of MCG should also be considered in young women with a history of tuberculosis or syphilis. This case highlights the importance of recognizing atypical presentations of MCG to reduce misdiagnoses and guide appropriate management.

Introduction: This study aimed to develop and validate a radiomics fusion model based on CT and MRI for distinguishing between spinal osteosarcoma and chondrosarcoma, and to compare the performance of models derived from different imaging modalities.

Methods: A retrospective analysis was conducted on 63 patients with histologically confirmed spinal osteosarcoma (n=20) and chondrosarcoma (n=43). Radiomics features were extracted from CT and MRI (T1-weighted, T2-weighted, and T2-weighted fat-suppressed) sequences, followed by feature selection using univariate logistic regression and LASSO. Eight machine learning models were utilized to construct radiomics models, based on CT, MR, both CT and MR, and clinical information combined with CT and MR. Models were evaluated via five-fold cross-validation and compared against radiologists' interpretations using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1 score, and Matthews correlation coefficient.

Results: The MRI-based radiomics model using linear discriminant analysis achieved the highest diagnostic performance (AUC=0.963, sensitivity=95.3%, specificity=80.0%), significantly outperforming both CT-based models (AUC=0.700) and radiologists' diagnosis (p<0.001). The CTMR and clinico-CTMR models did not show significant improvement over the MR model. The MR model demonstrated excellent calibration and clinical utility, with substantial net benefit across threshold probabilities.

Discussion: The superior performance of the MRI-based model highlighted the value of MRI radiomics in tumor differentiation. This clinically practical tool may support preoperative diagnosis using routine MRI, potentially facilitating more timely treatment decisions.

Conclusion: In conclusion, the MRI-based radiomics model enabled accurate preoperative discrimination between spinal osteosarcoma and chondrosarcoma.

Introduction: Inflammatory myofibroblastic tumor (IMT) is a neoplasm originating from mesenchymal tissue and can occur in multiple parts of the body, such as the lungs, abdomen, pelvis, and retroperitoneum. Although the lung is a relatively common site for IMT, airway involvement in adults is rare, and most reported cases involve the central airway. Reports of IMT arising within the bronchus are uncommon.

Case presentation: We, herein, report the case of a 72-year-old male patient with bronchial IMT who was admitted due to a recurrent cough that worsened over two weeks. Tumor markers showed no significant elevation, and imaging examinations suggested a tumor in the left upper lobe bronchus. Due to the suspicion of malignancy, the patient underwent thoracoscopic left upper lobectomy. Postoperative pathological examination revealed an inflammatory myxoid myofibroblastic tumor of the left upper lobe bronchus. During a 12-month postoperative follow-up, no significant signs of metastasis or recurrence were observed.

Conclusion: We have reported the case of endobronchial IMT in an adult, with a degree of contrast enhancement on CT lower than that previously reported for intratracheal IMT. The tumor lacks specific clinical symptoms and laboratory findings, which poses a challenge for accurate and timely preoperative diagnosis. Based on literature reports, in patients with recurrent cough, hemoptysis, or dyspnea, if CT shows a smoothly marginated endobronchial nodule with mild enhancement, the possibility of this disease should be considered.

Background: The histological differentiation of Non-Small Cell Lung Cancer (NSCLC) is a critical prognostic factor that influences therapeutic strategies and patient outcomes. However, conventional assessment methods relying on postoperative pathology or biopsy are invasive and limited by sampling bias. Therefore, it is of great clinical significance to develop a non-invasive, imaging-based approach for accurate preoperative differentiation evaluation.

Methods: This retrospective study included 184 NSCLC patients with preoperative chest CT scans and confirmed pathological differentiation grades from 2022 to 2024. Radiomics features were extracted using PyRadiomics, followed by feature selection via the LASSO algorithm. A novel three-task binary classification strategy was proposed to replace conventional trinary classification, including low vs. non-low, moderate vs. non-moderate, and high vs. non-high differentiation. Four machine learning models-GBDT, RF, XGBoost, and LightGBM-were constructed and evaluated using ROC analysis, confusion matrices, and SHAP-based interpretability analysis.

Results: The GBDT model achieved the highest AUC (0.849) in the low differentiation classification task, while the RF model outperformed others in predicting high differentiation (AUC = 0.7188). The moderate differentiation task showed relatively poor performance across all models (AUC < 0.55). SHAP analysis revealed that features such as original_firstorder_Kurtosis, glrlm_RunEntropy, and wavelet-HLL_firstorder_Median played key roles in differentiating tumor grades, highlighting their biological relevance and potential utility in clinical interpretation.

Discussion: The proposed multi-binary strategy improved classification granularity and interpretability. Ensemble learning models demonstrated robust performance across tasks, especially for extreme differentiation levels.

Conclusion: This study, which combines radiomics with a multi-task machine learning framework, demonstrates prediction and can improve the accuracy and interpretability of preoperative lung cancer differentiation. The proposed model provides a non-invasive, quantitative tool with the potential to support individualized clinical decision-making. Further multicenter validation and multimodal data integration are warranted to enhance its clinical applicability.

Introduction: The objective is to develop and compare risk prediction models for Iodine Contrast Media (ICM)-related Acute Adverse Reactions (AAR) in patients without a prior history of such reactions, and to construct a nomogram based on the superior model.

Methods: 546 patients without a history of ICM-related AAR who underwent ICM administration during CT contrast-enhanced scan were retrospectively enrolled, and divided into training (n=234), test (n=101), and external validation (n=211) sets. Clinical, medication information, and environmental factors were collected. Features were selected by univariate logistical analysis and least absolute shrinkage and selection operator, and four Machine Learning (ML) models, including Logistic Regression (LR), decision tree, k-nearst neighbors and linear support vector classification were used to construct ICM-related AAR risk prediction models were developed and evaluated using AUC, accuracy and F1 score. A nomogram was constructed based on the superior model.

Results: History of ICM exposure and allergy due to other factors, hypertension, type of ICMs, ICM dose, oral metformin, hyperglycaemia, and glomerular filtration rate were selected for modeling (all p < 0.05). The LR model demonstrated superior performance, with AUCs of 0.894 (test set) and 0.814 (external validation), and was used to construct a clinically applicable nomogram.

Discussion: The LR-based model effectively predicts ICM-related AAR risk using readily available clinical variables. It offers a practical tool for identifying high-risk patients prior to ICM administration, facilitating preventive measures.

Conclusion: LR can predict the risk of ICM-related AAR well in patients without a history of ICM-related AAR, and the corresponding nomogram is provided.

Background: The image quality of conventional coronary computed tomography angiography (CCTA) was affected by blooming and beam-hardening artifacts, leading to an overestimation of stenosis. Although subtraction CCTA has been used for several years, misregistration artifacts have limited its development.

Objective: To explore the potential of a newly developed subtraction technique in CCTA to improve image quality and vessel wall visibility without misregistration artifacts.

Methods: Fifty-six patients who underwent CCTA scans using dual-layer detector spectral CT (SDCT) were retrospectively enrolled. Dark-blood images were generated by subtracting virtual non-contrast (VNC) datasets from 70-keV datasets. Qualitative evaluations of dark-blood images included assessments of image quality, inner-wall visualization, and outer-wall visualization. Quantitative parameters were compared between conventional CCTA images and dark-blood images. The quantitative assessment involved evaluating contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR). SNRwall, SNRlumen, SNRperiaortic fat, CNRwall-lumen, and CNRwall-periaortic fat were calculated. Two experienced radiologists independently evaluated the images, and inter-rater variability was assessed.

Results: Patients were categorized into three groups based on plaque types: group A (calcified plaques, n=88), group B (non-calcified plaques, n=15), and group C (vessels without plaque, n=56). Dark-blood images of non-calcified plaques and vessels without plaque exhibited higher image quality and inner-wall visualization scores compared to calcified plaques (all P < 0.05). The subjective scores of radiologists showed good consistency (all kappa values > 0.7). Compared to conventional images, dark-blood images demonstrated higher quantitative scores in terms of SNRwall, SNRlumen, SNRperiaortic fat, CNRwall-lumen, and CNRwall-periaortic fat (all P < 0.001).

Conclusion: Dark-blood images derived from SDCT demonstrated improved image quality of coronary arteries without misregistration artifacts and enhanced visualization of the coronary vessel wall.

Introduction: Deformable image registration is essential in medical image analysis. The state-of-the-art approaches are unsupervised methods based on convolutional neural networks (CNN) and vision transformers (ViT). While CNNs perform well in extracting local features, ViTs perform better in extracting global features.

Objective: This study aimed to compare the performance of CNN and ViT in unsupervised deformable image registration.

Method: We have proposed a unified registration framework and evaluated both architectures. Experiments have been conducted using 4D-CT.

Results: The results have shown ViT-based registration to achieve superior performance compared to CNN-based methods.

Conclusion: The findings have indicated vision transformer architectures to be more effective than convolutional networks for unsupervised deformable registration on 4D-CT data. Foundation Item: This work is supported by the National Natural Science Foundation of China (No.61801413).

Introduction: We developed and validated a novel CT-based radiomics nomogram aimed at improving the differentiation between checkpoint inhibitor-related pneumonitis (CIP) and COVID-19 pneumonia, addressing the persistent clinical uncertainty in pneumonia diagnosis.

Methods: A total of 97 patients were enrolled. CT image segmentation was performed, extracting 1,688 radiomics features. Feature selection was conducted using variance thresholding, the least absolute shrinkage and selection operator (LASSO) regression, and the Select K Best methods, resulting in the identification of 33 optimal features. Several classification models (K-Nearest Neighbors [KNN], Support Vector Machine [SVM], and Stochastic Gradient Descent [SGD]) were trained and validated using a 70:30 split and fivefold cross-validation. A radiomics nomogram was subsequently developed, incorporating the radiomics signature (Rad-score) alongside clinical factors. It was assessed based on area under the curve (AUC), sensitivity, specificity, and decision curve analysis (DCA).

Results: The SVM classifier exhibited the highest performance, achieving an AUC of 0.988 in the training cohort and 0.945 in the validation cohort. The constructed radiomics nomogram demonstrated a markedly improved predictive accuracy compared to the clinical model alone (AUC: 0.853 vs. 0.810 in training; 0.932 vs. 0.924 in validation). Calibration curves indicated a strong alignment of the model with observed outcomes, while DCA confirmed a greater net benefit across various threshold probabilities.

Discussion: A radiomics nomogram integrated with radiomics signatures, demographics, and CT findings facilitates CIP differentiation from COVID-19, improving diagnostic efficacy.

Conclusion: Radiomics acts as a potential modality to supplement conventional medical examinations.

Accurate early diagnosis and assessment of liver fibrosis are important for patient treatment and prognosis. This study explored the value of Gd- BOPTA-enhanced T1 mapping via the B1 inhomogeneity-corrected Variable Flip Angle (VFA) method for staging liver fibrosis in rats.

Methods: Sprague‒Dawley rats were divided into one control group (n = 6) and four carbon tetrachloride-induced liver fibrosis groups (n = 6 each group). T1 mapping via B1 inhomogeneity-corrected VFA was performed before and 90 minutes after Gd-BOPTA administration. Precontrast T1 values (T1_pre), postcontrast T1 values (T1_post), and the reduction rate of T1 values (ΔT1%) were quantified on T1 mapping images. The diagnostic performance was evaluated by the Area Under the Receiver Operating Characteristic Curve (AUC). The correlations between T1pre, T1post, ΔT1% values, and the expression levels of hepatocyte transporters (Oatp1a1 and Mrp2) were evaluated.

Results: T1_post and ΔT1% were significantly correlated with liver fibrosis stage (r = 0.832, p < 0.001; r = -0.798, p < 0.001, respectively), whereas T1_pre was not significantly correlated with fibrosis stage (r = 0.357, p = 0.062). The AUCs of T1_post and ΔT1% were greater than those of postcontrast signal intensity for diagnosing stages F2-F4 (0.936, 0.941 vs. 0.791; p = 0.043, 0.038, respectively), F3-F4 (0.928, 0.861 vs. 0.660; p = 0.003, 0.028, respectively) and F4 (0.965, 0.896 vs. 0.761; p = 0.021, 0.049, respectively). Oatp1a1 and Mrp2 expression levels correlated significantly with T1_post (r = -0.859, p = 0.001; r = -0.697, p = 0.017) and ΔT1% (r = 0.891, p < 0.001; r = 0.685, p = 0.020), respectively.

Discussion: T1_post and ΔT1% were significantly correlated with liver fibrosis stages, and have good diagnostic performance for staging liver fibrosis. The protein expression levels of Oatp1a1 and Mrp2 correlated significantly with T1_post and ΔT1%.

Conclusion: Gd-BOPTA-enhanced T1 mapping via the B1 inhomogeneity-corrected VFA shows promise as a potentially accurate and reliable tool for quantifying liver fibrosis stages.

Introduction: This article presents a case of a patient with a broad ligament perivascular epithelioid cell tumor (PEComa), focusing on the analysis of its imaging features in CT and MRI to enhance understanding and awareness of this rare tumor.

Case Presentation: This article reports a case of a 27-year-old married woman who was found to have a pelvic mass two years ago. After detailed examination at our hospital, imaging studies, including enhanced CT and MRI, revealed a cystic-solid lesion in the left adnexal area, with preoperative considerations of ovarian cystadenoma or uterine leiomyoma. She was referred to a specialized obstetrics and gynecology hospital for surgery, and the postoperative pathology was diagnosed as PEComa. She has been undergoing regular follow-up at our hospital post-surgery. One year after the operation, her laboratory tests showed no significant abnormalities, and imaging studies did not reveal any signs of metastasis.

Conclusion: Uterine broad ligament PEComa is a rare tumor, and accurate imaging features and classification criteria can aid in improving preoperative diagnosis. A deeper understanding of the clinical and imaging characteristics of this rare disease is significant for enhancing diagnostic accuracy and treatment outcomes.