Academic Radiology最新文献

Rationale and objectives: The study aimed to evaluate risk factors related to the vascular lake phenomenon (VLP) and its impact on prognosis in patients with large hepatocellular carcinoma (HCC) (≥5 cm) undergoing Conventional transarterial chemoembolization (cTACE).

Patients and methods: This study included 149 patients with large HCC who initially underwent cTACE from July 2021 to July 2023. The univariate and multivariate analyses were conducted to find risk factors related to VLP. The overall survival (OS), progression-free survival (PFS), objective response rate (ORR), disease control rate (DCR), and postoperative complications were compared between the VLP group and the non-VLP group. The propensity score matching (PSM) was used to reduce selection bias.

Results: Among the 149 patients (mean age 65±12 years; 120 male), 50 patients were in the VLP group. The VLP group had a significantly higher positive rate of Hepatitis B surface Antigen (HBsAg) (p=.006). After PSM, VLP was an independent factor associated with OS (p=.002, HR 0.39, 95% CI: 0.21, 0.72) and PFS (p=.002, HR 0.50, 95% CI: 0.32, 0.78). The VLP group showed significantly longer OS (19.1 months vs. 13.4 months, p=.005), longer PFS (11.2 months vs. 6.5 months, p=.006), higher ORR (34.0% vs 14.0%, p=.019), and higher DCR (62.0% vs 26.0%, p<.001) than the non-VLP group.

Conclusion: The presence of VLP in large HCC may correlate with a higher rate of HBsAg positivity. It can indicate improved survival outcomes and treatment response underwent cTACE treatment.

Summary: In hepatocellular carcinoma with a diameter greater than 5 cm, the presence of preoperative vascular lake phenomenon indicates better transarterial chemoembolization efficacy.

Background: Low-dose chest CT (LDCT) is commonly employed for the early screening of lung cancer. However, it has rarely been utilized in the assessment of volumetric bone mineral density (vBMD) and the diagnosis of osteoporosis (OP).

Purpose: This study investigated the feasibility of using deep learning to establish a system for vBMD prediction and OP classification based on LDCT scans.

Methods: This study included 551 subjects who underwent both LDCT and QCT examinations. First, the U-net was developed to automatically segment lumbar vertebrae from single 2D LDCT slices near the mid-vertebral level. Then, a prediction model was proposed to estimate vBMD, which was subsequently employed for detecting OP and osteopenia (OA). Specifically, two input modalities were constructed for the prediction model. The performance metrics of the models were calculated and evaluated.

Results: The segmentation model exhibited a strong correlation with manual segmentation, achieving a mean Dice similarity coefficient (DSC) of 0.974, sensitivity of 0.964, positive predictive value (PPV) of 0.985, and Hausdorff distance of 3.261 in the test set. Linear regression and Bland-Altman analysis demonstrated strong agreement between the predicted vBMD from two-channel inputs and QCT-derived vBMD, with a root mean square error of 8.958 mg/mm³ and an R² of 0.944. The areas under the curve for detecting OP and OA were 0.800 and 0.878, respectively, with an overall accuracy of 94.2%. The average processing time for this system was 1.5 s.

Conclusion: This prediction system could automatically estimate vBMD and detect OP and OA on LDCT scans, providing great potential for the osteoporosis screening.

Rationale and objectives: The objective of this research is to carry out a systematic review and meta-analysis to detect the diagnostic efficacy of 68Ga-FAPI Positron Emission Tomography (PET) Computed Tomography/Magnetic Resonance (CT/MR) in total of the lesions as well as different aspects of metastasis in individuals with ovarian cancers (OC).

Materials and methods: The PubMed, Embase, Cochrane library, and Web of Science databases were thoroughly searched until the cut-off date of July 23, 2024. The assessment of 68Ga-FAPI PET CT/MR of OC was presented by the included studies. Bivariate random effects models were utilized to compute the sensitivity and specificity of 68Ga-FAPI PET CT/MR in OC. The I-square index (I²) was utilized to measure heterogeneity and sensitivity analysis were employed to test it.

Results: The pooled sensitivity as well as specificity for 68Ga-FAPI PET CT/MR in OC were 0.90 (95% CI: 0.84-0.95) as well as 0.95 (95% CI: 0.91-0.97), correspondingly. In the subanalysis for metastatic lesions (lymph node [LN] metastases and peritoneal involvement), the pooled sensitivity and specificity of 68Ga-FAPI PET CT/MR were 0.94 (95% CI: 0.74-0.99) and 0.95 (95% CI: 0.84-0.99) for identifying metastatic LNs as well as 0.93 (95% CI: 0.81-0.97) and 0.96 (95% CI: 0.89-0.99) about peritoneal carcinomatosis evaluation, correspondingly. In the head-to-head comparison with 18F-FDG PET/CT, 68Ga-FAPI PET CT/MR exhibited a better sensitivity in identifying peritoneal metastases (P=.0004).

Conclusion: 68Ga-FAPI PET CT/MR displayed a high overall diagnostic effectiveness in OC. When evaluating metastatic peritoneal lesions of OC, 68Ga-FAPI PET CT/MR displayed a superior pooled sensitivity.

This article reviews the state-of-the-art applications of quantitative magnetic resonance imaging (qMRI) in predicting and evaluating response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC). HCC is a highly heterogeneous tumor, and its response to TACE varies significantly among patients. Early identification of treatment response is critical for optimizing management. Promising results have been reported using various qMRI methods, including hepatocyte-specific contrast-enhanced MRI, diffusion imaging, perfusion imaging, magnetic resonance spectroscopy (MRS), blood oxygen level-dependent functional MRI (BOLD-fMRI), magnetic resonance elastography (MRE), and artificial intelligence (AI). The coefficient of variation in the hepatobiliary phase of hepatocyte-specific contrast-enhanced MRI, which quantifies signal heterogeneity, may predict TACE outcomes. Among diffusion imaging methods, diffusion kurtosis imaging has outperformed intravoxel incoherent motion and diffusion-weighted imaging (DWI), while perfusion imaging has shown a lower area under the curve (AUC) compared to diffusion imaging. Combining MRS with DWI has achieved an AUC of 1.000 for early assessment of TACE response. However, BOLD-fMRI and MRE remain underexplored and lack established models with key quantitative parameters. AI models incorporating radiomics or deep learning with clinical factors have shown promising AUC values ranging from 0.690 to 1.000 in test sets. However, their added value requires validation through larger prospective studies.

Rationale and objectives: Accurate determination of human epidermal growth factor receptor 2 (HER2) expression is critical for guiding targeted therapy in breast cancer. This study aimed to develop and validate a deep learning (DL)-based decision-making visual biomarker system (DM-VBS) for predicting HER2 status using radiomics and DL features derived from magnetic resonance imaging (MRI) and mammography (MG).

Materials and methods: Radiomics features were extracted from MRI, and DL features were derived from MG. Four submodels were constructed: Model I (MRI-radiomics) and Model III (mammography-DL) for distinguishing HER2-zero/low from HER2-positive cases, and Model II (MRI-radiomics) and Model IV (mammography-DL) for differentiating HER2-zero from HER2-low/positive cases. These submodels were integrated into a XGBoost model for ternary classification of HER2 status. Radiologists assessed imaging features associated with HER2 expression, and model performance was validated using two independent datasets from The Cancer Image Archive.

Results: A total of 550 patients were divided into training, internal validation, and external validation cohorts. Models I and III achieved an area under the curve (AUC) of 0.800-0.850 for distinguishing HER2-zero/low from HER2-positive cases, while Models II and IV demonstrated AUC values of 0.793-0.847 for differentiating HER2-zero from HER2-low/positive cases. The DM-VBS achieved average accuracy of 85.42%, 80.4%, and 89.68% for HER2-zero, -low, and -positive patients in the validation cohorts, respectively. Imaging features such as lesion size, number of lesions, enhancement type, and microcalcifications significantly differed across HER2 statuses, except between HER2-zero and -low groups.

Conclusion: DM-VBS can predict HER2 status and assist clinicians in making treatment decisions for breast cancer.

Objectives: This study aimed to compare the diagnostic efficiency of ⁶⁸Ga-fibroblast activation protein inhibitor (FAPI) positron emission tomography (PET) and ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET in patients with head and neck cancer (HNC).

Data sources: PubMed, Embase, Web of Science, and the Cochrane Library were used to perform a systemic search through June 26, 2024.

Methods: Studies comparing the diagnostic value of ⁶⁸Ga-FAPI PET and ¹⁸F-FDG PET in patients with HNC were included. We performed a bivariate meta-analysis of diagnostic data and a meta-analysis of the quantitative parameters. The summary receiver operating characteristic curve was plotted, and publication bias was evaluated via Egger's test.

Results: The meta-analysis included 12 studies on 386 patients with HNC. ⁶⁸Ga-FAPI PET had superior pooled sensitivity to ¹⁸F-FDG PET in detecting primary/recurrent tumors and distant metastases in both lesion-based analysis and patient-based analysis. Although the sensitivity of ¹⁸F-FDG PET for detecting lymph node metastases was greater than that of ⁶⁸Ga-FAPI PET (0.93 [95% CI 0.83-0.97] vs. 0.82 [95% CI 0.63-0.93]), the specificity of ¹⁸F-FDG PET was lower than that of ⁶⁸Ga-FAPI PET (0.36 [95% CI 0.01-0.96] vs. 0.97 [95% CI 0.53-1.00]). In addition, ⁶⁸Ga-FAPI PET had a higher pooled mean maximum standardized uptake value for distant metastases (3.28 [95% CI 1.90-4.66]) and a higher pooled mean tumor-to-background ratio for primary/recurrent tumors (1.24 [95% CI 0.44-2.04]) than ¹⁸F-FDG PET.

Conclusion: Compared to ¹⁸F-FDG PET, ⁶⁸Ga-FAPI PET has superior diagnostic accuracy in HNC lesions. Thus, ⁶⁸Ga-FAPI PET may be a better tool for staging and restaging than ¹⁸F-FDG PET in patients with HNC.

Objectives: This meta-analysis aimed to systematically evaluate the diagnostic performance of artificial intelligence (AI) applied to biparametric magnetic resonance imaging (bpMRI) for identifying clinically significant prostate cancer (csPCa).

Methods: A comprehensive systematic review was conducted following PRISMA-DTA guidelines, searching PubMed, Embase, and Web of Science databases. Studies focus on AI algorithms based on bpMRI in diagnosis csPCa were included. Bivariate random-effects models synthesized sensitivity, specificity, and area under the curve (AUC). Heterogeneity was assessed using I² statistics, with subgroup analyses exploring variations across AI methodologies, AI models, study designs, and geographical regions.

Results: Nineteen studies were included, encompassing 4594 patients in internal validation sets, 795 in external validation sets, and 897 in radiologist cohorts. AI models based on bpMRI exhibited notable diagnostic performance, with internal validation revealing an average sensitivity of 0.88 (95% CI: 0.84-0.92), average specificity of 0.79 (95% CI: 0.73-0.84), and an average AUC of 0.91 (95% CI: 0.88-0.93). External validation confirmed these results with a average sensitivity of 0.85 (95% CI: 0.78-0.90), average specificity of 0.83 (95% CI: 0.69-0.91), and an average AUC of 0.91 (95% CI: 0.88-0.93). In contrast, radiologist assessments showed lower performance with an average AUC of 0.78 (95% CI: 0.74-0.81).

Conclusion: AI applied to bpMRI demonstrates excellent diagnostic performance for csPCa, representing a promising noninvasive approach that may potentially outperform traditional radiological interpretations. However, notable heterogeneity across studies and limited sample size for radiologists and external validation sets suggests the need for caution. To substantiate these findings and investigate clinical applicability, additional prospective studies are essential.

Rationale and objectives: Assess the feasibility of using a large language model (LLM) to identify valuable radiology teaching cases through report discrepancy detection.

Materials and methods: Retrospective study included after-hours head CT and musculoskeletal radiograph exams from January 2017 to December 2021. Discrepancy level between trainee's preliminary interpretation and final attending report was annotated on a 5-point scale. RadBERT, an LLM pretrained on a vast corpus of radiology text, was fine-tuned for discrepancy detection. For comparison and to ensure the robustness of the approach, Mixstral 8×7B, Mistral 7B, and Llama2 were also evaluated. The model's performance in detecting discrepancies was evaluated using a randomly selected hold-out test set. A subset of discrepant cases identified by the LLM was compared to a random case set by recording clinical parameters, discrepant pathology, and evaluating possible educational value. F1 statistic was used for model comparison. Pearson's chi-squared test was employed to assess discrepancy prevalence and score between groups (significance set at p<0.05).

Results: The fine-tuned LLM model achieved an overall accuracy of 90.5% with a specificity of 95.5% and a sensitivity of 66.3% for discrepancy detection. The model sensitivity significantly improved with higher discrepancy scores, 49% (34/70) for score 2 versus 67% (47/62) for score 3, and 81% (35/43) for score 4/5 (p<0.05 compared to score 2). LLM-curated set showed a significant increase in the prevalence of all discrepancies and major discrepancies (scores 4 or 5) compared to a random case set (P<0.05 for both). Evaluation of the clinical characteristics from both the random and discrepant case sets demonstrated a broad mix of pathologies and discrepancy types.

Conclusion: An LLM can detect trainee report discrepancies, including both higher and lower-scoring discrepancies, and may improve case set curation for resident education as well as serve as a trainee oversight tool.