Despite the ever-increasing amount and complexity of annotated medical image data, the development of large-scale medical image analysis algorithms has not kept pace with the need for methods that bridge the semantic gap between images and diagnoses. The goal of this position paper is to discuss and explore innovative and large-scale data science techniques in medical image analytics, which wil...

Accurate registration is crucial for medical image analysis. In this letter, we proposed an improved Demons technique (IDT) for medical image registration. The IDT improves registration quality using orthogonal gradient information. The advantage of the proposed IDT is assessed using 14 medical image pairs. Experimental results show that the proposed technique provides about 8% improvement over...

—All medical image processing techniques need to extract meaningful information from medical images. However, the noise generated during image acquisition and transmission degrades the human interpretation, or computer-aided analysis of these images. Therefore, denoising should be performed to improve the image quality for more accurate analysis and diagnosis. In this paper we propose a medical...

This review paper is based on medical image compression using various image compression techniques. In this paper comparative analysis of different compression techniques and their applications in the rising fields of medical science such as e-health, telemedicine, teleradiology has been carried out. There has been abundant research work carried on medical image compression. Even though, the me...

To develop any autonomous computerized algorithm for abnormality detection based on medical image analysis essentially requires a robust segmentation algorithm. To achieve this goal of accurate segmentation of medical image it requires an effective edge detection algorithm. Generalized edge detection algorithms like Sobel, Canny, though effective in normal images but often fails in case of medi...

Segmentation is an important part of image processing, which often has a large impact on quantitative image analysis results. Fully automated operator independent segmentation procedures that successfully work in a population with a larger biological variation are extremely difficult to design and usually some kind of operator intervention is required, at least in pathological cases. We develop...

A new fully automated shape learning method is presented. It is based on clustering a shape training set in the original shape space and performing a Procrustes analysis on each cluster to obtain a cluster prototype and information about shape variation. As a direct application of our shape learning method, a 17-structure shape model of brain substructures was computed from MR image data, an ei...

Three-dimensional (3D) and four-dimensional (4D) imaging plays an increasingly important role in computer-assisted diagnosis, intervention and therapy. However, in many cases the interpretation of these images is heavily dependent on the subjective assessment of the imaging data by clinicians. Over the last decades image registration has transformed the clinical workflow in many areas of medica...