Characterization of microvascular disease in pediatric sickle cell disease using nailfold capillaroscopy.

Sickle cell disease (SCD) is a disorder with repetitive vaso-occlusive crises resulting in microvascular obstruction and tissue ischemia that may lead to multi-organ ischemia and dysfunction. Nailfold videocapillaroscopy (NFC) is an imaging technique utilized in clinical rheumatology to visualize capillaries located near the fingertip. To characterize NFC abnormalities in the setting of pediatric SCD, we performed NFC using a video capillaroscope on 8 digits in 44 stable SCD patients and 65 age matched healthy controls. Mean capillary number was lower (6.4 ± 1.3 vs 7.5 ± 1.8, p = 0.001) in the SCD group compared to controls. The percentage of dilated capillaries was similar (7.1 ± 8.3 vs. 5.9 ± 8.2, p = 0.4). The large majority of capillaries visualized in the SCD and control groups were normal capillary types per the EULAR definition, with a similar percentage of normal, nonspecific capillary morphologies and abnormal types. Regarding normal capillary sub-types, the SCD group and controls exhibited similar percentages of stereotype hairpin shapes, and tortuous or once or twice crossing type capillaries. On multivariate analyses, mean capillary number was independently associated with SCD after adjusting for age, body mass index, systolic blood pressure and gender. In conclusion, pediatric SCD is associated with lower capillary number but similar percentage of dilated capillaries and morphology on NFC. In our SCD cohort, capillary number was unrelated to our available markers of disease severity, including history of sickle crises, previous hospitalization for crises or Hemoglobin F levels.

Characterization of microvascular disease in patients with sickle cell disease using nailfold capillaroscopy.

Sickle cell disease (SCD) is a disorder characterized by repetitive vaso-occlusive crises causing microvascular obstruction, tissue ischemia and pain that may lead to chronic multi-organ ischemic sequelae. Nailfold videocapillaroscopy (NFC) is a non-invasive imaging technique used in clinical rheumatology to directly visualize capillaries located near the fingertip. To characterize NFC abnormalities in the setting of SCD, we performed NFC on 71 SCD patients and 70 age matched controls using a video capillaroscope on 8 digits. As compared to controls, mean capillary number was lower and the final capillary score (measure of capillary dropout inversely related to capillary density) was higher in the SCD group. The SCD group had a lower percentage of stereotype hairpin shapes and a higher percentage of crossing type capillaries. On multivariate linear analyses, both mean capillary number and final capillary score were independently associated with SCD after adjusting for age, body mass index, and gender. SCD was associated with more dilated capillaries but similar numbers of hemorrhages. In conclusion, SCD is associated with lower capillary density and more dilated capillaries on NFC. These changes appear unrelated to markers of disease severity including frequency of sickle crises, number of transfusions, and HbS levels. The relation between NFC and target organ involvement merits further study.

A Comparative Study of Land Cover Classification by Using Multispectral and Texture Data.

The main objective of this study is to find out the importance of machine vision approach for the classification of five types of land cover data such as bare land, desert rangeland, green pasture, fertile cultivated land, and Sutlej river land. A novel spectra-statistical framework is designed to classify the subjective land cover data types accurately. Multispectral data of these land covers were acquired by using a handheld device named multispectral radiometer in the form of five spectral bands (blue, green, red, near infrared, and shortwave infrared) while texture data were acquired with a digital camera by the transformation of acquired images into 229 texture features for each image. The most discriminant 30 features of each image were obtained by integrating the three statistical features selection techniques such as Fisher, Probability of Error plus Average Correlation, and Mutual Information (F + PA + MI). Selected texture data clustering was verified by nonlinear discriminant analysis while linear discriminant analysis approach was applied for multispectral data. For classification, the texture and multispectral data were deployed to artificial neural network (ANN: n-class). By implementing a cross validation method (80-20), we received an accuracy of 91.332% for texture data and 96.40% for multispectral data, respectively.