Semi-automatic segmentation and classification of Pap smear cells.

Cytologic screening has been widely used for detecting the cervical cancers. In this study, a semiautomatic PC-based cellular image analysis system was developed for segmenting nuclear and cytoplasmic contours and for computing morphometric and textual features to train support vector machine (SVM) classifiers to classify four different types of cells and to discriminate dysplastic from normal cells. A software program incorporating function, including image reviewing and standardized denomination of file names, was also designed to facilitate and standardize the workflow of cell analyses. Two experiments were conducted to verify the classification performance. The cross-validation results of the first experiment showed that average accuracies of 97.16% and 98.83%, respectively, for differentiating four different types of cells and in discriminating dysplastic from normal cells have been achieved using salient features (8 for four-cluster and 7 for two-cluster classifiers) selected with SVM recursive feature addition. In the second experiment, 70% (837) of the cell images were used for training and 30% (361) for testing, achieving an accuracy of 96.12% and 98.61% for four-cluster and two-cluster classifiers, respectively. The proposed system provides a feasible and effective tool in evaluating cytologic specimens.

Pseudo three-dimensional vision-based nail-fold morphological and hemodynamic analysis.

In this study, a Pseudo three-dimensional Vision-based Nail-fold Morphological and Hemodynamic Analysis (PTVNMHA) is proposed to automatically extract morphological/hemodynamic features from a microscopic nail-fold image sequence, reconstruct the corresponding pseudo three-dimensional microvascular models, and visualize the dynamic blood flow in the model constructed. The morphological features extracted include the number, width/height, density, arteriolar limb caliber, curved segment caliber, venular limb caliber, blood color, tortuosity, and width of the curved segment of capillaries. The hemodynamic features identified are blood flow velocity and blood flow rate. All are significant pathological indicators with a spatial precision up to 1.6 µm. The diameters of cross-sections along the centerlines of capillaries are identified and employed to reconstruct the pseudo three-dimensional microvascular surface meshes. The microscopic image sequence acquired is mapped to the corresponding microvascular model constructed to perform dynamic blood flow visualization. Compared with laser Doppler velocimetry, PTVNMHA can derive blood flow velocities for each capillary across the microscopic range separately in much higher precision and obtain diversified morphological and hemodynamic features of capillaries with a low-cost equipment setup. In addition to the blood flow velocity, blood flow rate, which keeps almost constant no matter where the measuring position is in a capillary, has also been measured and proposed as a useful feature to discriminate patients with hypertension from the normal with great significance (p<0.001). In the future, large scale experiments will be conducted to diagnose patients with anemia as well as patients with essential and secondary hypertension to verify effectiveness of the PTVNMHA system.

Prevalence of prehypertension and associated risk factors in a rural Taiwanese adult population.

BACKGROUND: The Joint National Committee on the Prevention, Detection, Evaluation, and Treatment of High Blood Pressure has recently introduced the prehypertension category of blood pressure status that needs monitoring and intervention. This study aimed to assess the prevalence of prehypertension and its associated risks in rural Taiwan. METHODS: From community-based cross-sectional data of 6204 adults (2650 men and 3554 women) who received general health examination in the Chi-Shan district in rural Taiwan, collected between 2002 and 2007, we analyzed and compared the blood pressure and demographic, metabolic, and behavior characteristics of prehypertensive and normotensive subjects. Multiple logistic regression methods were used to identify risk factors for prehypertension. RESULTS: Within the study population, 3354 had hypertension, 1875 had prehypertension, and 975 had normal blood pressure. The prehypertensive subjects were older, had higher body mass index (BMI), and had higher blood glucose, total cholesterol, triglycerides, and uric acid levels than did the normotensive group. Multivariate logistic regression analysis revealed that BMI was the strongest predictor of prehypertension in both men and women (OR=1.102, 95% CI=1.054-1.152, P<0.001; and OR=1.121, 95% CI=1.085-1.159, P<0.001, respectively). CONCLUSIONS: The prevalence of prehypertension is high among adults in rural Taiwan and it was associated with many risk factors for further hypertension and cardiovascular disease. Early lifestyle modifications, such as healthy diet, optimal weight control, and exercise are recommended interventions.