Comparison of CINtec PLUS cytology and cobas HPV test for triaging Canadian patients with LSIL cytology referred to colposcopy: A two-year prospective study

OBJECTIVES & METHODS: CINtec PLUS and cobas HPV tests were compared for triaging patients referred to colposcopy with a history of LSIL cytology in a 2-year prospective study. Cervical specimens were tested once at enrollment, and test positivity rates determined. Test performance was ascertained with cervical intraepithelial neoplasia grade 2 or worse (CIN2+) and CIN3 or worse (CIN3+) serving as clinical endpoints. RESULTS: In all ages, (19–76 years, n= 598), 44.3% tested CINtec PLUS positive vs. 55.4% HPV positive (p< 0.001). To detect CIN2+ (n= 99) CINtec PLUS was 81.8% sensitive vs. 93.9% for HPV testing (p= 0.009); genotype 16/18-specific sensitivity was 46.5%. Specificity was 52.9% vs. 36.6%, respectively (p< 0.001). In all ages, to detect CIN3+ (n= 44), sensitivity was 93.2% for both tests; genotype 16/18-specific sensitivity was 52.3%. Specificity was 48.4% for CINtec PLUS vs. 31.1% for HPV testing (p< 0.001). In patients < 30 years, CINtec was 91.7% sensitive vs 95.8% for HPV testing (p= 0.549). CONCLUSIONS: CINtec PLUS or cobas HPV test could serve as a predictor of CIN3+ with high sensitivity in patients referred to colposcopy with a history of LSIL regardless of age while significantly reducing the number of LSIL referral patients requiring further investigations and follow-up in colposcopy clinics.

Diagnostic Performance of Deep LearnIng AlgoriThm for Analysis of Computed Tomography Myocardial PerfusION

Purpose: Artificial intelligence could play a key role in cardiac imaging analysis. To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation. Methods: One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30% and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DLrest) and stress dataset (CTP-DLstress) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA+CTPStress, CCTA+CTP-DLrest, and CCTA+CTP-DLstress were measured and compared. The time of analysis for CTPStress, CTP-DLrest and CTP-DLStress were recorded. Results: Patient-specific sensitivity, specificity, NPV, PPV, accuracy and area under the curve (AUC) of CCTA alone and CCTA+CTPStress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy and AUC of CCTA+DLrest and CCTA+DLstress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%,88%,98%, respectively. All CCTA+CTPStress, CCTA+CTP-DLRest and CCTA+CTP-DLStress significantly improved detection of hemodynamically significant CAD (p<0.01).Time of CTP-DL was significantly lower as compared to human analysis (39.2±3.2 vs. 379.6±68.0 seconds, p<0.001).Conclusion: Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTPStress.

Spatial Agreement among Vegetation Disturbance Maps in Tropical Domains Using Landsat Time Series

Detecting disturbances in native vegetation is a crucial component of many environmental management strategies, and remote sensing-based methods are the most efficient way to collect multi-temporal disturbance data over large areas. Given that there is a large range of datasets for monitoring, analyzing, and detecting disturbances, many methods have been well-studied and successfully implemented. However, factors such as the vegetation type, input data, and change detection method can significantly alter the outcomes of a disturbance-detection study. We evaluated the spatial agreement of disturbance maps provided by the Breaks For Additive Season and Trend (BFAST) algorithm, evaluating seven spectral indices in three distinct vegetation domains in Brazil: Atlantic forest, savanna, and semi-arid woodland, by assessing levels of agreement between the outputs. We computed individual map accuracies based on a reference dataset, then ranked their performance, while also observing their relationships with specific vegetation domains. Our results indicated a low rate of spatial agreement among index-based disturbance maps, which itself was minimally influenced by vegetation domain. Wetness indices produced greater detection accuracies in comparison to greenness-related indices free of saturation. The normalized difference moisture index performed best in the Atlantic forest domains, yet performed poorest in semi-arid woodland, reflecting its specific sensitivity to vegetation and its water content. The normalized difference vegetation index led to high disturbance detection accuracies in the savanna and semi-arid woodland domains. This study offered novel insight into vegetation disturbance maps, their relationship to different ecosystem types, and corresponding accuracies. Distinct input data can produce non-spatially correlated disturbance maps and reflect site-specific sensitivity. Future research should explore algorithm limitations presented in this study, as well as the expansion to other techniques and vegetation domains across the globe.