Academic Radiology最新文献

Rationale and objectives: Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of non-small cell lung cancer (NSCLC). However, immune-related adverse events still occur, of which checkpoint inhibitor pneumonitis (CIP) is the most common. We aimed to construct and validate a contrast-enhanced computed tomography-based radiomic nomogram to predict the probability of CIP before ICIs treatment in NSCLC.

Materials and methods: We retrospectively analyzed 685 patients with NSCLC who were initially treated with ICIs. A total of 186 patients were included in our study, and an additional 52 patients from another hospital were considered for external validation. After radiomics feature extraction and selection, we applied a support vector machine classification model to distinguish CIP and used the probability as a radiomics signature. A radiomics-clinical logistic regression model was built using the filtered clinical parameters and a radiomic signature. Receiver operating characteristic, area under the curve (AUC), calibration curve, and decision curve analysis was used for inter-model comparison.

Results: The combined radiomics-clinical model constructed using age, interstitial lung disease, emphysema at baseline, and radiomics signature showed an AUC of 0.935, 0.905, and 0.923 for the training, validation, and external validation cohorts, respectively. Compared with the clinical-only (AUC of 0.829, 0.826, and 0.809) and radiomics-only models (0.865, 0.847, and 0.841), the radiomics-clinical displayed better predictive power.

Conclusion: This combined radiomics-clinical model predicted the probability of CIP during ICIs treatment in patients with NSCLC with favorable accuracy and could therefore be used as an effective tool to guide clinical ICIs decisions.

Rationale and objectives: The Kaiser score (KS) is a simple and intuitive machine-learning derived decision rule for characterizing breast lesions in a clinical setting and screening for breast cancer. The present study aims to investigate the applicability of the KS for contrast-enhanced mammography (CEM) in breast masses, and to compare its diagnostic accuracy with magnetic resonance imaging (MRI). CEM may provide an alternative option for patients with breast masses, especially for those with MRI contraindications.

Materials and methods: Two hundred and seventy-five patients with breast enhanced masses were included in the study from May 2019 to September 2022. Patients were further divided into benign and malignant groups based on pathological diagnosis. The CEM and MRI imaging characteristics of these two groups were analyzed statistically. The paired chi-square and Cohen's kappa coefficient (κ) analysis were used to compare imaging characteristics between CEM and MRI. The Breast Imaging Reporting and Data System (BI-RADS) and KS for CEM and MRI were evaluated based on imaging characteristics. The diagnostic performance of BI-RADS and KS for CEM and MRI was assessed and compared using receiver operating characteristic (ROC) analysis and DeLong's test.

Results: The imaging characteristics of root sign, time-signal intensity curve (TIC/mTIC), margin, internal enhancement pattern (IEP), edema, apparent diffusion coefficient (ADC) values, and suspicious malignant microcalcifications showed significant differences between benign and malignant lesions (all p ≤ 0.011). The detection rate of root sign and margin showed substantial agreement between CEM and MRI (κ = 0.656, κ = 0.640), but IEP, TIC/mTIC, and edema showed poor agreement (κ = 0.380, κ = 0.320, κ = 0.324). For all lesion analyses, the area under the curves (AUCs) of the KS (0.897 ∼ 0.932) were higher than that of BI-RADS (0.691) in CEM (all p < 0.001). The AUC of KS (calcification)-CEM (0.932) was higher than those of both KS-CEM and KS (edema)-CEM (0.897 and 0.899) (all p < 0.001). For subgroup analyses, the AUCs of the KS (0.875 ∼ 0.876) were higher than that of BI-RADS (0.740) in MRI (all p < 0.001). The AUCs of KS-MRI (0.876) and KS (ADC)-MRI (0.875) were similar to those of KS-CEM (0.878) and KS (edema)-CEM (0.870) (all p > 0.100). The AUC of KS (calcification)-CEM (0.934) was slightly higher than those of both KS-MRI (0.876) and KS (ADC)-MRI (0.875), but no significant difference was observed (p = 0.051; p = 0.071).

Conclusion: The KS for CEM provided high diagnostic accuracy in distinguishing breast masses, comparable to that of MRI. The application of KS (calcification)-CEM combined with suspicious malignant microcalcifications can improve diagnostic efficiency with an AUC of 0.932 ∼ 0.934. However, edema did not significantly improve performance when using the KS for CEM.

Rationale and objectives: The aim of this study was to develop and validate a novel computed tomography (CT)-based fracture risk assessment model (FRCT) specifically tailored for patients suffering from chronic obstructive pulmonary disease (COPD).

Methods: We conducted a retrospective analysis encompassing a cohort of 284 COPD patients, extracting data on demographics, clinical profiles, pulmonary function tests, and CT-based bone quantification metrics. The Boruta feature selection algorithm was employed to identify key variables for model construction, resulting in a user-friendly nomogram.

Results: Our analysis revealed that 37.32% of the patients suffered fragility fractures post-follow-up. The FRCT model, integrating age, cancellous bone volume, average cancellous bone density, high-density lipoprotein levels, and prior fracture incidence, demonstrated superior predictive accuracy over the conventional fracture risk assessment tool (FRAX), with a C-index of 0.773 in the training group and 0.797 in the validation group. Calibration assessments via the Hosmer-Lemeshow test confirmed the model's excellent fit, and decision curve analysis underscored the FRCT model's substantial positive net benefit.

Conclusion: The FRCT model, leveraging opportunistic CT screening, offers a highly accurate and personalized approach to fracture risk prediction in COPD patients, surpassing the capabilities of existing tools. This model is poised to become an indispensable asset for clinicians in managing osteoporotic fracture risks within the COPD population.

Rationale and objectives: To predict the muscular invasion status of bladder urothelial carcinoma (UCB) using quantitative parameters from multi-directional high b-value diffusion-weighted imaging (MDHB-DWI), and compare these parameters with the Vesical Imaging Reporting and Data System (VI-RADS).

Methods: In this prospective study, patients with pathologically confirmed UCB were enrolled between May 2023 and May 2024. All participants underwent preoperative MRI, including MDHB-DWI and conventional MRI. The average quantitative parameter values of MDHB-DWI (diffusion kurtosis imaging [DKI], diffusion tensor imaging [DTI], mean apparent propagator [MAP] and neurite orientation dispersion and density imaging [NODDI]) and apparent diffusion coefficient (ADC) values were compared between non-muscle invasive (NMIBC) and muscle-invasive (MIBC) groups using the T-test or rank sum test. Quantitative MRI models were developed using multivariate logistic regression analyses based on significant diffusion parameters obtained from MDHB-DWI. Receiver operating characteristic (ROC) curves were plotted, and DeLong's test was applied to compare the area under the curve (AUC) of the model with that of VI-RADS.

Results: A total of 76 patients with UCB (56 males; NMIBC/MIBC=51/25) were included. Axial diffusivity (AD) from DKI and mean diffusivity (MD) from DTI were identified as independent predictors for constructing a quantitative MRI model. The AUC of the model was 0.936, significantly outperforming VI-RADS (AUC=0.831) (p = 0.007).

Conclusion: DKI-AD and DTI-MD from MDHB-DWI demonstrate a robust ability to differentiate muscular invasion in UCB. Their combination significantly improves diagnostic efficiency compared to VI-RADS.

Rationale and objectives: Coronary CT angiography (CCTA) is mandatory before transcatheter aortic valve replacement (TAVR). Our objective was to evaluate the efficacy of artificial intelligence (AI)-powered software in automatically analyzing cardiac parameters from pre-procedural CCTA to predict major adverse cardiovascular events (MACE) in TAVR patients.

Materials and methods: Patients undergoing pre-TAVR CCTA were retrospectively included. AI software automatically extracted 34 morphologic and volumetric cardiac parameters characterizing the ventricles, atria, myocardium, and epicardial adipose tissue. Clinical information and outcomes were recorded from institutional database. Cox regression analysis identified predictors of MACE, including non-fatal myocardial infarction, heart failure hospitalization, unstable angina, and cardiac death. Model performance was evaluated with Harrell's C-index, and nested models were compared using the likelihood ratio test. Manual analysis of 170 patients assessed agreement with automated measurements.

Results: Among the 648 enrolled patients (77 ± 9.3 years, 58.9% men), 116 (17.9%) experienced MACE within a median follow-up of 24 months (interquartile range 10-40). After adjusting for clinical parameters, only left ventricle long axis shortening (LV-LAS) was an independent predictor of MACE (hazard ratio [HR], 1.05 [95% confidence interval, 1.05-1.11]; p = 0.04), with significantly improved C-index (0.620 vs. 0.633; p < 0.001). When adjusted for the Society of Thoracic Surgeons Predicted Risk of Mortality score, LV-LAS was also predictive of MACE (HR, 1.08 [95%CI, 1.03-1.13]; p = 0.002), while improving model performance (C-index: 0.557 vs. 0.598; p < 0.001). All parameters showed good or excellent agreement with manual measurements.

Conclusion: Automated AI-based comprehensive cardiac assessment enables pre-TAVR MACE prediction, with LV-LAS outperforming all other parameters.

Pulmonary embolism (PE) is a common emergency presentation that can lead to death if left untreated. While catheter pulmonary angiography was the gold standard, ventilation/perfusion studies were the preferred non-invasive diagnostic test for PE. Lawsuits from this era focused on the diagnostic uncertainty created by V/Q scan reports, which are graded by probability of PE. After multidetector computed tomography (MDCT) became widespread, the focus of lawsuits shifted away from the content of the report and towards implying negligence for not ordering imaging. Due to a confluence of factors, including the evolving medicolegal environment, clinicians chose CT as the modality of choice.

Lawsuits for spending too little time interpreting each radiological image are a vexatious charge to level against a radiologist in medical malpractice court. In this article, we recount two medicolegal cases where the defendant radiologists were accused of missing a life-threatening diagnosis due to not spending enough time reviewing each image. We consider the literature in vision sciences, visual perception in radiology and interpretive biases to demonstrate that using reading speed as evidence of negligence in a malpractice court represents in incorrect understanding of how radiologists perceive images, including three-dimensional volumetric studies.