Hypernasality is seen in cleft lip and palate patients who had undergone repair surgery as a consequence of velopharyngeal insufficiency. Hypernasality has been studied by evaluation of perturbation, noise measures, and cepstral analysis of speech. In this study, feature extraction and analysis were performed during running speech using six different sentences. Jitter, shimmer, Mel frequency cepstral coefficients, bionic wavelet transform entropy, and bionic wavelet transform energy were calculated. Support vector machines were employed for classification of data to normal or hypernasal. Finally, results of the automatic classification were compared with true labels to find accuracy, sensitivity, and specificity. Accuracy was higher when Mel frequency cepstral coefficients were combined with bionic wavelet transform energy feature. In the best case, accuracy of 85% with sensitivity of 82% and specificity of 85% was obtained. Results prove that acoustic analysis is a reliable method to find hypernasality in cleft lip and palate patients.

The new techniques of three-dimensional (3D)-optical coherence tomography (OCT) imaging is very useful for detecting retinal pathologic changes in various diseases and determining retinal thickness 'abnormalities'. Fundus colour images have been used for several years for detecting retinal abnormalities too. If the two image modalities were combined, the resulted image would be more informative. The first step to combine these two modalities is to register colour fundus images with an en face representation of OCT. In this study, curvelet transform is used to extract vessels for both modalities. Then the extracted vessels from two modalities are registered together in two stages. At first, images are registered using scaling and translation transformations. Then a quadratic transformation model is assumed between two pairs of images; because retina is imaged as a second-order surface. Twenty-two eyes (17 macular and 5 prepapillary), from random patients, were imaged in this study with Topcon 3D OCT1000 instrument. A new registration error is defined which averages the distance between all the corresponding points in two sets of vessels. Results show that registration error after stage one is 6.01 ± 1.82 pixels and after stage two is 1.02 ± 0.02 pixels.

Acoustic monitoring of swallow frequency has become important as the frequency of spontaneous swallowing can be an index for dysphagia and related complications. In addition, it can be employed as an objective quantification of ingestive behavior. Commonly, swallowing complications are manually detected using videofluoroscopy recordings, which require expensive equipment and exposure to radiation. In this study, a noninvasive automated technique is proposed that uses breath and swallowing recordings obtained via a microphone located over the laryngopharynx. Nonlinear diffusion filters were used in which a scale-space decomposition of recorded sound at different levels extract swallows from breath sounds and artifacts. This technique was compared to manual detection of swallows using acoustic signals on a sample of 34 subjects with Parkinson's disease. A speech language pathologist identified five subjects who showed aspiration during the videofluoroscopic swallowing study. The proposed automated method identified swallows with a sensitivity of 86.67 %, a specificity of 77.50 %, and an accuracy of 82.35 %. These results indicate the validity of automated acoustic recognition of swallowing as a fast and efficient approach to objectively estimate spontaneous swallow frequency.

No abstract

No abstract