Wound intensity correction and segmentation with convolutional neural networks

Abstract

Wound area changes over multiple weeks are highly predictive of the wound healing process. A big data eHealth system would be very helpful in evaluating these changes. We usually analyze images of the wound bed for diagnosing injury. Unfortunately, accurate measurements of wound region changes from images are difficult. Many factors affect the quality of images, such as intensity inhomogeneity and color distortion. To this end, we propose a fast level set model-based method for intensity inhomogeneity correction and a spectral properties-based color correction method to overcome these obstacles. State-of-the-art level set methods can segment objects well. However, such methods are time-consuming and inefficient. In contrast to conventional approaches, the proposed model integrates a new signed energy force function that can detect contours at weak or blurred edges efficiently. It ensures the smoothness of the level set function and reduces the computational complexity of re-initialization. To increase the speed of the algorithm further, we also include an additive operator-splitting algorithm in our fast level set model. In addition, we consider using a camera, lighting, and spectral properties to recover the actual color. Numerical synthetic and real-world images demonstrate the advantages of the proposed method over state-of-the-art methods. Experimental results also show that the proposed model is at least twice as fast as methods used widely.Recently, millions of patients are suffering from chronic wounds. The time-consuming wound assessments are not always feasible because of the high volume of patients. Consequently, accurate diagnosis and careful treatment will highly rely on expertise and experience. Advances in computer vision and artificial intelligence enable the analysis of wound images by big data and cloud computing. Big data is popular information and communication technologies paradigms. The big data-based approaches can be combined for directing the next generation of eHealth systems. However, because the imaging systems are difficult, the captured images have low quality, which

A Practical Low-Cost Machine Vision Sensor System for Defect Classification on Air Bearing Surfaces

“…In Fig. 6, the results of the corresponding ROIs on the ABS using the level set method based on the Chan-Vese model (34)(35)(36) are presented. The specific values used herein for Eq.…”

“…We tried to apply the level set method with our system, but it was not satisfactory owing to not only its low speed and high CPU load for the high-resolution image used in this work but also to the imperfect extraction. The fast level set method, proposed by Y. Li et al (34) and H. Lu and colleagues, (35,36) improved the performance of the level set method and increased the speed of the algorithm. We tried to use this algorithm with our system, but choosing and tuning parameters to satisfy our case were not easy to implement in due time.…”

Deep Learning for Financial Time Series Forecasting in A-Trader System

“…CNNs are variations of MLP designed to use minimal amounts of preprocessing [29]. CNNs constitute a type of feed-forward artificial neural networks in which connectivity pattern between its neurons mimics animal visual cortex connection structure.…”

Semi-supervised classification framework of hyperspectral images based on the fusion evidence entropy

“…Current research with respect to the image and signal processing of supervised classification methods focuses on deep learning and support vector machine algorithms [14,18,31,33,35]. The core of the supervised classification model framework is the use of previous knowledge of specialists or real measured data to mark unknown states in the data, which is called training the samples.…”