- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Microscopy and Analysis || Automatic Interpretation of Melanocytic Images in Confocal Laser Scanning Microscopy
摘要： The frequency of melanoma doubles every 20 years. The early detection of malignant changes augments the therapy success. Confocal laser scanning microscopy (CLSM) enables the noninvasive examination of skin tissue. To diminish the need for training and to improve diagnostic accuracy, computer-aided diagnostic systems are required. Two approaches are presented: a multiresolution analysis and an approach based on deep layer convolutional neural networks. For the diagnosis of the CLSM views, architectural structures such as micro-anatomic structures and cell nests are used as guidelines by the dermatologists. Features based on the wavelet transform enable an exploration of architectural structures at different spatial scales. The subjective diagnostic criteria are objectively reproduced. A tree-based machine-learning algorithm captures the decision structure explicitly and the decision steps are used as diagnostic rules. Deep layer neural networks require no a priori domain knowledge. They are capable of learning their own discriminatory features through the direct analysis of image data. However, deep layer neural networks require large amounts of processing power to learn. Therefore, modern neural network training is performed using graphics cards, which typically possess many hundreds of small, modestly powerful cores that calculate massively in parallel. Readers will learn how to apply multiresolution analysis and modern deep learning neural network techniques to medical image analysis problems.
关键词： convolutional neural networks,skin lesions,multiresolution image analysis,computer-aided diagnosis,confocal laser scanning microscopy,machine learning
更新于2025-09-19 17:13:59
-
Optimization of Laser Therapy Parameters in Dependence of Spot Size
摘要： Recently, the laser therapy for a treatment of the skin lesions of the vascular origin has gained a substantial development, and progress in the technical area. The vascular lasers, particularly the CANDELA Vbeam Perfecta, which is a part of this research has been equipped by a system of the dynamical cooling, called DCD leading to a higher patient’s comfort during the examination. In the most of the vascular lasers, it was allowed for settings of the pulse length up to 40 ms. By this way, the hematomas are reduced after the treatment, and mostly the skin is only getting red. For a reason of a complexity of the CANDELA Vbeam Perfecta settings, on a demand of the physicians, the user environment has been developed serving for an automatic parameters calculation of the laser therapy, and possibilities of alternative settings for same laser energy. The software environment has been designed in the MATLAB. The SW has been tested in the clinical conditions of the University Hospital of Ostrava.
关键词： SW environment,CANDELA Vbeam Perfecta,skin lesions,MATLAB,Laser
更新于2025-09-12 10:27:22
-
Simultaneous Blood Flow Measurement and Dermoscopy of Skin Lesions Using Dual-Mode Dermascope
摘要： Dermascopes are commonly utilized for the qualitative visual inspection of skin lesions. While automated image processing techniques and varied illumination strategies have been used to aid in structural analysis of lesions, robust quantification of functional information is largely unknown. To address this knowledge gap, we have developed a compact, handheld dermascope that enables real-time blood flow measurements of skin during conventional visual inspection. In-vitro characterization demonstrated that the dermascope is capable of quantifying changes in flow across a physiologically relevant range even when used in a handheld manner with clinic lighting and dermascope LEDs on. In a small pilot clinical study, we demonstrated the dermascope’s ability to detect flow differences between two distinct lesion types.
关键词： Skin Lesions,Laser Speckle Contrast Imaging,Functional Information,Dermoscopy,Blood Flow Measurement
更新于2025-09-11 14:15:04