Search results for "Artificial"

Letter: Image-Guided Navigation and Robotics in Spine Surgery.

2020

Ventilation through a ‘straw’: the final answer in a totally closed upper airway?

2015

Prostate Cancer Segmentation from Multiparametric MRI Based on Fuzzy Bayesian Model

2014

International audience

Photoaging evaluation by RGB images using a smartphone for photodynamic therapy assessment

2017

In this study was evaluated the photoaging of patients' skins by the processing of RGB images acquired with an optical system based on a smartphone. Two groups were approached: a younger and an older.

Pressure-Induced Growth (PIG) of Atretic Esophagus: A Contigent Management for High-Risk Esophageal Atresia

1986

The management of uncomplicated esophageal atresia is a straightforward procedure consisting of thoracotomy with anastomosis of the atretic segments and ligature of any tracheoesophageal fistula present. However, besides the rareness of isolated esophageal atresia, our observations in the past few years show increasing incidence of the anomaly in association with premature births and other malformations which are usually incompatible with life. Aspiration pneumonia resulting from reflux of gastric content through a lower tracheoesophageal fistula, rather than the overflow of saliva from an upper atretic pouch, also threatens the life of an otherwise healthy neonate with esophageal atresia.

Validation of Knee KL-classifying Deep Neural Network with Finnish Patient Data

2021

Osteoarthritis (OA) is the most common form of joint disease in the world. The diagnosis of OA is currently made by human experts and suffers from subjectivity, but recently new promising detection algorithms have been developed. We validated the current state-of-the-art KL-classifying neural network model for knee OA using knee X-rays taken from postmenopausal women suffering from knee pain attributable to OA. The performance of the model on the clinical data was considerably lower compared to the previous results on population-based test data. This suggests that the performance of the current grading methods is not yet adequate to be applied in clinical settings. The present results also …

Modelling cardiac mechanics of left ventricular noncompaction

2020

Left ventricular noncompaction (LVNC) can be defined as a cardiomyopathy characterised by a pattern of prominent trabecular structure and deep intertrabecular recesses, that is thought to be caused by an arrest of normal endomyocardial morphogenesis. Using patient-specific computational modelling, we assessed the cardiac mechanics of five patients with LVNC and compared myocardial stress and pump performance to those of healthy controls. Findings shown that patients with LVNC have impaired left ventricular (LV) function, making it possible that the lack of fibre shortening of noncompacted layer can determine poor heart function. Pronounced end-systolic wall stress on left ventricular wall o…

Role of the tear film in the optical quality of the human eye.

2007

This paper reviews recent studies of the role of the tear film in the optical quality of the eye. Recent investigations focus on the dynamics of the tear film after a blink and its important role in the optical quality of the eye. The results in this review were used in an attempt to understand the optical and visual impact of tear-film breakup in normal eyes and dry eyes. It was noted that patients with dry-eye syndrome have large optical aberrations compared with those in normal eyes, which may be the cause of blurry vision associated with the syndrome. In addition, instillation of artificial tears reduces optical aberrations and thus improves the optical quality of vision in these patien…

Tree Species Identification Using 3D Spectral Data and 3D Convolutional Neural Network

2018

In this study we apply 3D convolutional neural network (CNN) for tree species identification. Study includes the three most common Finnish tree species. Study uses a relatively large high-resolution spectral data set, which contains also a digital surface model for the trees. Data has been gathered using an unmanned aerial vehicle, a framing hyperspectral imager and a regular RGB camera. Achieved classification results are promising by with overall accuracy of 96.2 % for the classification of the validation data set. nonPeerReviewed

RGB mapping of hemoglobin distribution in skin

2011

An experimental RGB imaging system based on commercial color camera was constructed, and its potential for mapping of hemoglobin distribution in skin was studied. Two types of LEDs (RGB and white “warm” LEDs) were compared as illuminators for acquiring images of vascular and pigmented skin malformations. A novel approach for studies of skin capillary refill by RGB analysis has been proposed and discussed.