Identification and quantitative evaluation of symptomatic cerebral venous thrombosis using 3D variable flip angle turbo spin echo.

PURPOSE: To explore the feasibility of MR 3D T1w Sampling Perfection with Application optimized Contrasts by using different flip angle Evolutions (SPACE) sequence imaging in symptomatic CVT diagnose, extracting the imaging features with quantitative analysis. METHODS: Fifty-nine patients with suspected CVT with neurological symptoms were retrospectively included in this study. Of them, 35 patients were enrolled in the comparation of diagnostic accuracy between the contrast-enhanced magnetic resonance venograms (CE-MRV) and 3D T1w SPACE imaging. Forty-five patients with 101 involved segments were identified for the quantitative analysis. All MR images were acquired on a 3.0 T MR scanner. The reference standard used in this study was a comprehensive combination of the imaging techniques and clinical information. CVT patients were grouped as acute (≤48 h), subacute (>48 h and ≤30d), and chronic (>30d) clinical phase. CVT segments were grouped based on pre-contrast T1WI, as type A: hypo intense signal; B: heterogeneously hyper intense signal; C: iso intense signal. The feasibility of 3D T1w SPACE imaging for diagnosing CVT was explored. Diagnostic accuracy of T1w SPACE imaging was analyzed and compared with the CE-MRV. The signal intensity of pre-contrast images (SpreCE), signal intensity of post-contrast images (SpostCE), and contrast enhancement (CE) rate, CE rate relative to that of pituitary gland (PG), white matter (WM), gray matter (GM), and normal vein vessel wall (nVVW) were compared based on both patients and segments. The CE rate grade of CVT segments of different imaging types was compared. RESULTS: The MR 3D T1w SPACE imaging achieved a higher sensitivity and specificity (100%/94.1% and 100%/100% based on patients/segments separately) than that of the CE-MRV (73.9%/56.9% and 83.3%/98.9% based on patients/segments separately). No statistical correlation was found between the imaging types of CVT segments and onset time of clinical symptoms (χ2 = 6.649, P = 0.171). Quantitative analysis showed that the CE rate relative to PG and that to WM were higher in the chronic CVT patients than that in the other two groups (H = 10.330 and P = 0.006, H = 9.898 and P = 0.007, separately). CE rate relative to GM in the chronic group was higher than that in the subacute group (H = 7.143 and P = 0.028). All of the quantitative parameters were statistically different across CVT segments of three imaging types (all P≤0.001). CONCLUSION: MR 3D T1w SPACE imaging has the advantage to accurately diagnose CVT of different clinical stages, and identify the involved thrombus segments.

Overall diagnostic accuracy of different MR imaging sequences for detection of dysplastic nodules: a systematic review and meta-analysis.

OBJECTIVE: To assess the overall diagnostic accuracy of different MR imaging sequences in the detection of the dysplastic nodule (DN). METHODS: PubMed, Cochrane Library, and Web of Science were systematically searched. Study selection and data extraction were conducted by two authors independently. Quality assessment of diagnostic accuracy studies (QUADAS) 2 in RevMan software was used to score the included studies and assess their methodological quality. A random-effects model was used for statistical pooling by Meta-Disc. Subgroup analysis and sensitivity analysis were used to explore potential sources of heterogeneity. RESULTS: Fourteen studies (335 DN lesions in total) were included in our meta-analysis. The area under the curve (AUC) of summary receiver operating characteristic (SROC) of T2WI was 0.87. Pooled sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) of DWI were 0.81 (95%CI, 0.73-0.87), 0.90 (95%CI, 0.86-0.93), 7.04 (95%CI, 4.49-11.04), and 0.24 (95%CI, 0.17-0.33) respectively. In the arterial phase, pooled sensitivity, specificity, PLR, and NLR were 0.89 (0.84-0.93), 0.75 (0.72-0.79), 3.72 (2.51-5.51), and 0.17 (0.12-0.25), respectively. Pooled sensitivity, specificity, PLR, and NLR of the delayed phase were 0.78 (0.72-0.83), 0.60 (0.55-0.65), 2.19 (1.55-3.10), and 0.36 (0.23-0.55) separately. Pooled sensitivity, specificity, PLR, and NLR of the hepatobiliary phase were 0.77 (0.71-0.82), 0.92 (0.89-0.94), 8.74 (5.91-12.92), and 0.24 (0.14-0.41) respectively. Pooled sensitivity, specificity, and PLR were higher on DWI and hepatobiliary phase in diagnosing LGDN than HGDN. CONCLUSION: MR sequences, particularly DWI, arterial phase, and hepatobiliary phase imaging demonstrate high diagnostic accuracy for DN. KEY POINTS: • MRI has dramatically improved the detection and accurate diagnosis of DNs and their differentiation from hepatocellular carcinoma. • Overall diagnostic accuracy of different MRI sequences in the detection of DN has not been studied before. • Our meta-analysis demonstrates that MRI achieves a high diagnostic value for DN, especially when using DWI, arterial phase imaging, and hepatobiliary phase imaging.

Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study.

Background Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Purpose To develop and to validate radiomic signatures diagnosing invasive lung adenocarcinoma in PSNs compared with the Brock, clinical-semantic features, and volumetric models. Materials and Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range, 55-65 years; 191 women) from January 2013 to October 2017 with 297 PSN lung adenocarcinomas split into training (n = 229) and test (n = 68) data sets. Radiomic features were extracted from the different regions (gross tumor volume [GTV], solid, ground-glass, and perinodular). Random-forest models were trained using clinical-semantic, volumetric, and radiomic features, and an online nodule calculator was used to compute the Brock model. Performances of models were evaluated using standard metrics such as area under the curve (AUC), accuracy, and calibration. The integrated discrimination improvement was applied to assess model performance changes after the addition of perinodular features. Results The radiomics model based on ground-glass and solid features yielded an AUC of 0.98 (95% confidence interval [CI]: 0.96, 1.00) on the test data set, which was significantly higher than the Brock (AUC, 0.83 [95% CI: 0.72, 0.94]; P = .007), clinical-semantic (AUC, 0.90 [95% CI: 0.83, 0.98]; P = .03), volumetric GTV (AUC, 0.87 [95% CI: 0.78, 0.96]; P = .008), and radiomics GTV (AUC, 0.88 [95% CI: 0.80, 0.96]; P = .01) models. It also achieved the best accuracy (93% [95% CI: 84%, 98%]). Both this model and the model with added perinodular features showed good calibration, whereas adding perinodular features did not improve the performance (integrated discrimination improvement, -0.02; P = .56). Conclusion Separating ground-glass and solid CT radiomic features of part-solid nodules was useful in diagnosing the invasiveness of lung adenocarcinoma, yielding a better predictive performance than the Brock, clinical-semantic, volumetric, and radiomics gross tumor volume models. Online supplemental material is available for this article. See also the editorial by Nishino in this issue. Published under a CC BY 4.0 license.

Identification of benign and malignant pulmonary nodules on chest CT using improved 3D U-Net deep learning framework.

PURPOSE: To accurately distinguish benign from malignant pulmonary nodules with CT based on partial structures of 3D U-Net integrated with Capsule Networks (CapNets) and provide a reference for the early diagnosis of lung cancer. METHOD: The dataset consisted of 1177 samples (benign/malignant: 414/763) from 997 patients provided by collaborating hospital. All nodules were biopsy or surgery proven, and pathologic results were regarded as the "golden standard". This study utilized partial U-Net to capture the low-level (edge, corner, etc.) information and CapNets to preserve high-level (semantic information) information of nodules. For CapNets, each capsule had a 4 × 4 matrix representing the pose and an activation probability representing the presence of an object. Furthermore, we chose accuracy (ACC), area under the curve (AUC), sensitivity (SE) and specificity (SP) to evaluate the generalization of the proposed architecture and compared its identification performance with 3D U-Net and experienced radiologists. RESULTS: The AUC of our architecture (0.84) was superior to that (0.81) of the original 3D U-Net (p = 0.04, DeLong's test). Moreover, ACC (84.5 %) and SE (92.9 %) of our model were clearly higher than radiologists' ACC (81.0 %) and SE (84.3 %) at the optimal operating point. However, SP (70 %) of our model was slightly lower than radiologists' SP (75 %), which might be the result of class imbalance with limited benign samples involved for algorithm training. CONCLUSIONS: Our architecture showed a high performance for identifying benign and malignant pulmonary nodules, indicating the improved model has a promising application in clinic.

Preoperative CT-based radiomics combined with intraoperative frozen section is predictive of invasive adenocarcinoma in pulmonary nodules: a multicenter study.

OBJECTIVES: Develop a CT-based radiomics model and combine it with frozen section (FS) and clinical data to distinguish invasive adenocarcinomas (IA) from preinvasive lesions/minimally invasive adenocarcinomas (PM). METHODS: This multicenter study cohort of 623 lung adenocarcinomas was split into training (n = 331), testing (n = 143), and external validation dataset (n = 149). Random forest models were built using selected radiomics features, results from FS, lesion volume, clinical and semantic features, and combinations thereof. The area under the receiver operator characteristic curves (AUC) was used to evaluate model performances. The diagnosis accuracy, calibration, and decision curves of models were tested. RESULTS: The radiomics-based model shows good predictive performance and diagnostic accuracy for distinguishing IA from PM, with AUCs of 0.89, 0.89, and 0.88, in the training, testing, and validation datasets, respectively, and with corresponding accuracies of 0.82, 0.79, and 0.85. Adding lesion volume and FS significantly increases the performance of the model with AUCs of 0.96, 0.97, and 0.96, and with accuracies of 0.91, 0.94, and 0.93 in the three datasets. There is no significant difference in AUC between the FS model enriched with radiomics and volume against an FS model enriched with volume alone, while the former has higher accuracy. The model combining all available information shows minor non-significant improvements in AUC and accuracy compared with an FS model enriched with radiomics and volume. CONCLUSIONS: Radiomics signatures are potential biomarkers for the risk of IA, especially in combination with FS, and could help guide surgical strategy for pulmonary nodules patients. KEY POINTS: • A CT-based radiomics model may be a valuable tool for preoperative prediction of invasive adenocarcinoma for patients with pulmonary nodules. • Radiomics combined with frozen sections could help in guiding surgery strategy for patients with pulmonary nodules.