International Journal of Computer and Applications

Texture features for image classification and retrieval.

Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization.

/pdf/machine-learning-for-medical-ultrasound-status-methods-and-2jqbj31nfj.pdf

Machine learning for medical ultrasound: status, methods, and future opportunities.

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one - SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its twobranch architecture and attention scheme. While the second one - UPA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model- PAN could achieve similar performance as the lightweight networks - SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at this https URL.

Efficient Image Super-Resolution Using Pixel Attention

This paper reviewed the 3rd NTIRE challenge on single-image super-resolution (restoration of rich details in a low-resolution image) with a focus on proposed solutions and results. The challenge had 1 track, which was aimed at the real-world single image super-resolution problem with an unknown scaling factor. Participants were mapping low-resolution images captured by a DSLR camera with a shorter focal length to their high-resolution images captured at a longer focal length. With this challenge, we introduced a novel real-world super-resolution dataset (RealSR). The track had 403 registered participants, and 36 teams competed in the final testing phase. They gauge the state-of-the-art in real-world single image super-resolution.

/pdf/ntire-2019-challenge-on-real-image-super-resolution-methods-3qgjnvehdu.pdf

NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results

Ultrasound imaging has several advantages over other medical imaging modalities (e.g., X-rays, computed tomography, and magnetic resonance). It is safe, relatively low cost, and allows real-time imaging. Tissue characterization with ultrasound has become important topic since computer facilities have been available for the analysis of ultrasound signals. In this paper, an unsupervised neural network learning technique-Hybrid Kohonen Self Organising Map (SOM) is proposed for the recognition of liver diseases from ultrasound images. Three kinds of liver diseases cyst, hepatoma and hemangioma are identified as the most critical liver diseases. The diagnosis scheme includes three steps: Speckle reduction, feature extraction and classification. A speckle is removed from ultrasound images by Laplacian pyramid nonlinear diffusion method and also preserves prominent edge information for classification. For nonlinear diffusion in each pyramid layer, a gradient threshold is automatically determined by a variation of Median Absolute Deviation (MAD) estimator. Then the features are extracted from mean gray level, entropy, local variance, co-occurrence matrix, first order statistics, gradient features and fractal dimensions are collected from the normal and abnormal ultrasound images. The unsupervised neural network learning technique called Hybrid Kohonen Self organizing map is proposed to classify normal and abnormal liver diseases from ultrasound images.

Classification of liver diseases from ultrasound images using a hybrid kohonen SOM and LPND speckle reduction method

The field of medical imaging seen rapid development over the last two decades and has consequently revolutionized the way in which modern medicine is practiced. Diseases and their symptoms are constantly changing therefore continuous updating is necessary for the data to be relevant. Diseases fall into different categories, even a small difference in symptoms may result in categorising it in a different group altogether. Thus analysing data accurately is of critical importance. This book concentrates on diagnosing diseases like cancer or tumor from different modalities of images. 

This book is divided into the following domains: Importance of big data in medical imaging, pre-processing, image registration, feature extraction, classification and retrieval. It is further supplemented by the medical analyst for a continuous treatment process. The book provides an automated system that could retrieve images based on user’s interest to a point of providing decision support. It will help medical analysts to take informed decisions before planning treatment and surgery. It will also be useful to researchers who are working in problems involved in medical imaging.

Big Data in Medical Image Processing

Accurate categorization of cirrhosis liver image in ultrasound modality is of great importance in medical diagnosis and treatment. Health informatics is important as it provides quick predictions on diseases based on nearness of symptoms. Modelling solutions for the same on cloud using deep learning is the motivation of this paper. Here, we propose a deep learning model associated with correlation based feature selection method for cirrhosis image classification. We compare the results with three other conventional classifiers algorithms to improve the better classification accuracy. First in pre-processing stage, noises are eliminated from pathological scan images by using modified laplacian pyramid non-linear diffusion filter. From the pre-processed scan images, each cirrhosis region is obtained under the guidance of radiology or physicians. Then, after extracting the complete features of each patch by gray level, local binary pattern and scale invariant feature, a feature selection technique is applied to choice the predominant texture features for each classifier. Finally a convolution neural network is implemented to improve the performance of classifiers in terms of sensitivity, specificity and accuracy. Convolution neural network algorithm with two hidden layers gives more accuracy in classifying cirrhosis image with 98% sensitivity. Experiments are carried out with 990 cirrhosis image patches which demonstrates that our proposed deep learning classifier perform 100% well than original classifiers in terms of accuracy.

An efficient categorization of liver cirrhosis using convolution neural networks for health informatics

Segmentation of 3D Point Cloud Data Based on Supervoxel Technique

Registration of intraoperative fluoroscopy images with preoperative two-dimensional and/or three-dimensional MRI images can be used for several purposes in image-guided surgery. Registration is an important problem and a fundamental task in image processing technique. In the medical image processing fields, some techniques are proposed to find a geometrical transformation that relates the points of an image to their corresponding points of another image. In recent years, multimodality image registration techniques are proposed in the medical imaging field. Especially, Mutual information (MI) is currently one of the most effective similarities metric in medical image registration. It is an automatic measure, and suitable for multimodal medical image registration. In radiotherapy planning manual registration techniques performed on MR image and CT images of the brain. Now-a-days, physicians segment the volume of interest (VOIs) from each set of slices manually. However, manual segmentation of the object area may require several hours for analysis. Furthermore, MDCT images and MR images contain more than 100 slices. Therefore, manual segmentation and registration method cannot apply for clinical application in the head CT and MR images. Mutual information (MI) is an automatic measure, and suitable for multimodal medical image registration. The genetic algorithm has been used to predict the deformation due to inclination of object considering mutual information. In this paper, image registration is coupled with mutual information and genetic algorithm. The primary objective of this paper is to increase accuracy of the registration. Experiments show our algorithm is a robust and efficient method which can yield accurate registration results.

R. Suganya

Papers

Classification of liver diseases from ultrasound images using a hybrid kohonen SOM and LPND speckle reduction method

Big Data in Medical Image Processing

An efficient categorization of liver cirrhosis using convolution neural networks for health informatics

Segmentation of 3D Point Cloud Data Based on Supervoxel Technique

Mutual information and genetic algorithm based registration of mri brain images