We present a method for automated segmentation of the vasculature in retinal images. The method produces segmentations by classifying each image pixel as vessel or nonvessel, based on the pixel's feature vector. Feature vectors are composed of the pixel's intensity and two-dimensional Gabor wavelet transform responses taken at multiple scales. The Gabor wavelet is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. We use a Bayesian classifier with class-conditional probability density functions (likelihoods) described as Gaussian mixtures, yielding a fast classification, while being able to model complex decision surfaces. The probability distributions are estimated based on a training set of labeled pixels obtained from manual segmentations. The method's performance is evaluated on publicly available DRIVE (Staal et al., 2004) and STARE (Hoover et al., 2000) databases of manually labeled images. On the DRIVE database, it achieves an area under the receiver operating characteristic curve of 0.9614, being slightly superior than that presented by state-of-the-art approaches. We are making our implementation available as open source MATLAB scripts for researchers interested in implementation details, evaluation, or development of methods.

We describe the first mobile app for identifying plant species using automatic visual recognition. The system -called Leafsnap -identifies tree species from photographs of their leaves. Key to this system are computer vision components for discarding non-leaf images, segmenting the leaf from an untextured background, extracting features representing the curvature of the leaf's contour over multiple scales, and identifying the species from a dataset of the 184 trees in the Northeastern United States. Our system obtains state-of-the-art performance on the real-world images from the new Leafsnap Dataset -the largest of its kind. Throughout the paper, we document many of the practical steps needed to produce a computer vision system such as ours, which currently has nearly a million users.

Even though TLRs modulators have been used for therapy in some GI diseases, further research, particularly in humans, is needed in order to establish the precise role of the different TLRs in the diverse GI diseases and to motivate clinical trials that consider TLRs as therapeutic targets in GI pathology.

1 Acute effects of angiotensin II (AngII) on diastolic properties of the myocardium were investigated. 2 Increasing concentrations of AngII (10 À9 to 10 À5 M) were added to rabbit papillary muscles in the absence (n ¼ 11) or presence of: (i) AT1 receptor antagonists, losartan (10 À6 M; n ¼ 7) or ZD-7155 (10 À7 M; n ¼ 8); (ii) ZD-7155 (10 À7 M) plus AT2 receptor antagonist PD-123,319 (2 Â 10 À6 M; n ¼ 6); (iii) PKC inhibitor, chelerythrine (10 À5 M; n ¼ 8); or (iv) Na þ /H þ exchanger (NHE) inhibitor, 5-(Nmethyl-N-isobutyl)-amiloride (10 À6 M; n ¼ 10). Passive length-tension relations were constructed before and after a single concentration of AngII (10 À5 M, n ¼ 6). Effects of AngII infusion (10 mg kg À1 min À1 ) were evaluated in in situ rabbit hearts. 3 AngII concentration dependently increased inotropy and resting muscle length (RL). At 10 À5 M, active tension increased 43.376.25% and RL 1.9670.4%. Correcting RL to its initial value resulted in a 4674% decrease of resting tension, indicating decreased muscle stiffness, as confirmed by the right and downward shift of the passive length-tension relation promoted by AngII. In the intact heart, at matched systolic pressures of 112 mmHg, AngII decreased end-diastolic pressures from 10.370.3 to 5.970.5 mmHg, and minimal diastolic pressures from 8.470.5 to 4.670.6 mmHg. 4 AT1 blockade inhibited AngII effects on myocardial inotropy and stiffness, while PKC or NHE inhibition only significantly attenuated its effects on resting length and tension. 5 In conclusion, AngII decreases myocardial stiffness, an effect that requires AT1 receptor activation and is mediated by PKC and NHE. This represents a novel mechanism of acute neurohumoral modulation of diastolic function, suggesting that AngII is a powerful regulator of cardiac filling.

No abstract