Search

Background: The clinical utility of radiomics is hampered by a high correlation between the large number of features analysed which may result in the "bouncing beta" phenomenon which could in part explain why in a similar patient population texture features identified and/or cut-off values of prognostic significance differ from one study to another. Principal component analysis (PCA) is a technique for reducing the dimensionality of large datasets containing highly correlated variables, such as texture feature datasets derived from FDG PET images, increasing data interpretability whilst at the same time minimizing information loss by creating new uncorrelated variables that successively maximize variance. Here, we report on PCA of a texture feature dataset derived from 123 malignant melanoma lesions with a significant range in lesion size using the freely available LIFEx software., Results: Thirty-eight features were derived from all lesions. All features were standardized. The statistical assumptions for carrying out PCA analysis were met. Seven principal components with an eigenvalue > 1 were identified. Based on the "elbow sign" of the Scree plot, only the first five were retained. The contribution to the total variance of these components derived using Varimax rotation was, respectively, 30.6%, 23.6%, 16.1%, 7.4% and 4.1%. The components provided summarized information on the locoregional FDG distribution with an emphasis on high FDG uptake regions, contrast in FDG uptake values (steepness), tumour volume, locoregional FDG distribution with an emphasis on low FDG uptake regions and on the rapidity of changes in SUV intensity between different regions., Conclusions: PCA allowed to reduce the dataset of 38 features to a set of 5 uncorrelated new variables explaining approximately 82% of the total variance contained within the dataset. These principal components may prove more useful for multiple regression analysis considering the relatively low numbers of patients usually included in clinical trials on FDG PET texture analysis. Studies assessing the superior differential diagnostic, predictive or prognostic value of principal components derived using PCA as opposed to the initial texture features in clinical relevant settings are warranted., (© 2022. The Author(s).)

A single-center, prospective double-blind randomized trial was conducted to compare the efficacy and safety of the calcium channel blocker nisoldipine in a sustained release coat-core formulation (CC), titrated from 10 mg to 40 mg daily, with the angiotensin converting enzyme inhibitor enalapril, titrated from 10 to 40 mg daily, in the treatment of black South African patients with severe hypertension (sitting diastolic blood pressure [DBP] between 115 and 140 mm Hg, confirmed by 24-h ambulatory blood pressure monitoring). Treatment target was a sitting DBP < 95 mm Hg by the 9th week of treatment. This was followed by a 4-month open phase using nisoldipine CC 10 to 60 mg daily. Ninety-six patients had complete data at baseline, and at the end of the double-blind and open phases, and were included in this analysis. In both groups, all patients required titration up to the maximal dose of double-blind medication. Monotherapy with nisoldipine CC, but not enalapril, significantly reduced both sitting and 24-h ambulatory blood pressure (BP). Twenty-four-hour BP in the nisoldipine CC group decreased from 179+/-14 / 118+/-7 to 144+/-16 / 94+/-10 mm Hg (P < .0001) versus 181+/-13 / 117+/-5 to 171+/-17 / 110+/-11 mm Hg in the enalapril group (P = ns). The profound decrease in blood pressure achieved with nisoldipine CC was accompanied by a significant reduction in left ventricular [LV] mass index, observed after only 2 months of treatment (from 146+/-40 to 129+/-35 g/m2, P = .05). In contrast, enalapril had no effect on LV mass (from 139+/-36 to 142+/-50 g/m2, P = NS). The antihypertensive effect of nisoldipine CC was further demonstrated in the open phase, during which 24-h BP decreased from 180+/-14 / 118+/-6 mm Hg (at baseline) to 142+/-16 / 92+/-10 mm Hg at the end of the 16-week open phase (P < .0001). This effect was sustained with trough-to-peak ratio of 74% for systolic and 67% for diastolic BP, with further regression in LV mass. Reduction in 24-h systolic BP to < 135 mm Hg was associated with a greater degree of regression of LV mass index in patients treated with nisoldipine CC. The incidence of adverse events in both groups was low and both nisoldipine CC and enalapril were well tolerated. The incidence of significant ventricular arrhythmia was also low and did not change with treatment. In conclusion, our findings suggest that nisoldipine CC administered once daily could be considered as a suitable first-line antihypertensive agent in black patients with severe hypertension, based on its profound and sustained blood-pressure-lowering effect, associated with significant regression of left ventricular mass and its low side effect profile.