Current Medical Imaging Reviews最新文献

Introduction: The biexponential model of Intravoxel Incoherent Motion (IVIM) has been applied to estimate renal damage. However, the role of the biexponential and stretched exponential models in assessing early renal damage in Chronic Kidney Disease (CKD) is unclear.

Methods: In this prospective study, 61 patients with CKD and 19 healthy volunteers underwent renal IVIM imaging. The monoexponential model yielded the Apparent Diffusion Coefficient (ADC); the biexponential model provided the true diffusion coefficient (ADCslow), pseudo-diffusion coefficient (ADCfast), and perfusion fraction (f); and the stretched-exponential model provided the Distributed Diffusion Coefficient (DDC) and diffusion heterogeneity index alpha (α). The estimated Glomerular Filtration Rate (eGFR) was calculated for all participants, and pathological scores were assessed in CKD patients. Correlations of ADC, ADCslow, ADCfast, f, DDC, and α with eGFR and pathological scores were analyzed. Receiver operating characteristic analysis compared the diagnostic performance of ADCslow, ADCfast, f, DDC, and α for grading renal pathological injury.

Results: ADCfast, f, and α showed high diagnostic accuracy in differentiating controls from CKD patients (AUC: 0.964, 0.974, and 0.981, respectively), as well as from CKD patients with high eGFR (AUC: 0.933, 0.952, and 0.966, respectively). Pathological scores were significantly higher in the low eGFR group than in the high eGFR group (P < 0.05). ADCfast, f, and α were negatively correlated with pathological scores (P < 0.05).

Discussion: Renal cortical ADCfast, f, and α are sensitive biomarkers of early renal injury in CKD even when eGFR is preserved. Moreover, the ADCfast and f values of the renal cortex were significantly correlated with tubulointerstitial damage. The primary limitations of this study are the single-center data and the limited scope of the region of interest. Further work is needed to recruit more participants, and those results will be verified by external centers.

Conclusion: Biexponential and stretched exponential model-derived parameters may be superior to monoexponential model-derived parameters for evaluating early renal damage in CKD.

The rapid advancement of computational technologies has significantly transformed medical diagnostics, particularly in the realm of neurological disorders. This review provides a comprehensive analysis of the current computational approaches employed for the diagnosis of five major neurological disorders: Alzheimer's disease, Parkinson's disease, Epilepsy, Huntington's disease, and Amyotrophic Lateral Sclerosis. By evaluating 140 peer-reviewed studies, we explored a diverse array of diagnostic methods, including machine learning algorithms, neuroimaging techniques, and electrophysiological signal analysis. Our review highlights the efficacy, accuracy, and limitations of these diagnostic methods, emphasizing their role in early detection and differential diagnosis. Furthermore, we discuss the integration of multimodal data and the potential of emerging technologies such as deep learning and artificial intelligence to enhance diagnostic practices. We also address the current challenges in clinical implementation and propose future research directions to improve diagnostic precision and patient outcomes. This review aims to serve as a valuable resource for researchers, clinicians, and stakeholders in the field of neurodiagnostics, fostering a deeper understanding of computational methodologies that shape the future of neurological disorder diagnosis.

Background: Acute Aortic Dissection (AD) is of great concern due to its high mortality rate. The probability of young patients without underlying diseases developing acute aortic dissection is relatively low. In extreme regions such as high-altitude areas, for patients presenting with atypical chest pain, it is necessary to not only consider life-threatening diseases such as aortic dissection and acute coronary syndrome, but also to rule out the interference of emphysema in the diagnosis. This case provides experience in the diagnosis, evacuation, and treatment of aortic dissection patients in high-altitude areas.

Case presentation: We present the case of a young man who experienced sudden neck pain at an altitude of 5200 m during defecation. The pain persisted and radiated to the back, but there were no typical symptoms of aortic dissection. However, on physical examination, the patient was found to have unequal blood pressure in both arms. After completing a CT scan, the diagnosis was confirmed as aortic dissection with subcutaneous emphysema. The patient was transferred to a hospital at a lower altitude to undergo an "aortic arch replacement under cardiopulmonary bypass." After follow-up, the patient had a good prognosis and was able to independently perform general daily activities.

Conclusion: The purpose of this case report is to raise awareness of the diagnostic interference caused by subcutaneous emphysema and to emphasize accurate diagnosis and timely intervention when encountering patients with atypical chest pain in high-altitude environments, which is expected to gain a therapeutic time window for the patient.

Background: Anterior Inferior Cerebellar Artery (AICA) aneurysms are rare, accounting for 0.1% to 0.5% of posterior circulation aneurysms. They often present with diverse morphologies and clinical symptoms, challenging diagnosis and management.

Case descriptions: We report three cases of AICA aneurysms with distinct clinical presentations and management strategies. Case 1: A 56-year-old male presented with chronic headache and left hemiparesis. MRI and 3D TOF MRA revealed a fusiform AICA aneurysm compressing the pons, treated with microsurgical clipping via anterior petrosectomy, resulting in a favorable outcome (mRS score of 0). Case 2: A 26-year-old female with a sudden-onset sentinel headache had a wide-neck saccular aneurysm of the right AICA confirmed by DSA. A posterior petrosectomy approach with clipping was performed, achieving complete aneurysm exclusion without complications (mRS score of 0). Case 3: A 21-year-old male with an incidentally detected saccular aneurysm underwent DSA and 3D angio-CT, confirming a wide-neck saccular aneurysm in the AICA territory. Microsurgical clipping via anterior petrosectomy was successful, with no residual lesion (mRS score of 0).

Conclusion: Microsurgical clipping remains a viable option for managing wide-neck and fusiform AICA aneurysms, particularly those unsuitable for endovascular techniques. Advanced imaging modalities and tailored cranial base approaches are crucial for optimizing outcomes. Further studies are needed to refine management strategies for these rare aneurysms.

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.