Diagnostic value of the dual-modal imaging radiomics model for subpleural pulmonary lesions.

PURPOSE: To investigate the clinical value of the radiomics model of grayscale ultrasound (GUS) and contrast-enhanced ultrasound (CEUS) to diagnosis subpleural pulmonary tuberculosis and nonpulmonary tuberculosis based on GUS and CEUS images. METHODS: This study included 221 patients with 228 lesions diagnosed using the composite reference standard. The patients were randomly divided into training (n = 183) and test (n = 45) cohorts in an 8:2 ratio. The regions of interest of the GUS and CEUS images were manually segmented to extract the radiomic features. The GUS, CEUS and GUS+CEUS radiomics models were constructed via the multistep selection of highly correlated features. Receiver operating characteristic curves of the different models were plotted, and the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value and negative predictive value (NPV) of the different models were compared. RESULTS: Following Least Absolute Shrinkage and Selection Operator dimension reduction we selected 4, 9, and 11 features to construct the GUS, CEUS, and GUS+CEUS radiomics models, respectively. The AUC values of the three groups in the test cohort were 0.689, 0.748 and 0.779, respectively, and they did not differ significantly. In the test cohort, the GUS+CEUS radiomics model exhibited the highest AUC (0.779), accuracy (75.56%), and NPV (68.7%) of the three models. CONCLUSIONS: The GUS+CEUS radiomics model possesses good clinical value in diagnosing pulmonary tuberculosis.

The diagnostic value of contrast-enhanced ultrasound for cervical tuberculous lymphadenitis.

OBJECTIVE: To investigate the value of contrast-enhanced ultrasound (CEUS) for the diagnosis of cervical tuberculous lymphadenitis (CTL). METHODS: The cohort study included 203 consecutive patients diagnosed with cervical lymph node. Before pathological or laboratory confirmation, all patients underwent CEUS examination, and the imaging findings were analyzed afterward. The diagnostic efficiency of the CEUS imaging findings of CTL was evaluated. RESULTS: Nighty-seven patients of the 203 (47.8%) were pathologically or laboratory confirmed with a CTL diagnosis while the remainder (52.2%) were diagnosed with non-tuberculous lymphadenitis. Regarding the imaging findings of CEUS, it was more common in CTL patients to find a pattern of heterogeneous enhancement inside the lymph nodes relative to non-tuberculous patients [81.44% (79/97) vs 15.09% (16/106), P < 0.01]. The sensitivity of the feature in diagnosis for CTL was 81.44% and the specificity was 84.91%, resepectively. Furthermore, a pattern of peripheral rim-like enhancement had been notable in CTL patients compared with non-tuberculous patients [86.60% (84/97) vs 12.26% (13/106), P < 0.01], associating with a diagnostic sensitivity of 86.60% and a specificity of 87.74%. When it came to the combination of both imaging findings mentioned above, the features were more prominent in CTL patients than compared with non-tuberculous patients [74.23% (72/97) vs 5.66% (6/106), P < 0.01], with a diagnostic sensitivity of 74.23% and a high specificity of 94.34%. Regarding area under curve (AUC) for the ROC analysis, the feature of internal heterogeneous enhancement, peripheral rim-like enhancement, and both features were 0.832, 0.872, and 0.843. CONCLUSIONS: CEUS patterns of heterogeneous enhancement and peripheral rim-like enhancement of lymph nodes are helpful characteristics for the diagnosis of CTL.