Non-Subsampled Contourlet Transform-Based Effective Denoising of Medical Images

Noise removal in medical images remains a challenge for the researchers because noise removal introduces artifacts and blurring of the image. Developing medical image denoising algorithm is a difficult operation because a tradeoff between noise reduction and the preservation of actual features of image has to be made in a way that enhances and preserves the diagnostically relevant image content. A special member of the emerging family of multiscale geometric transforms is the contourlet transform which effectively captures the image edges and contours. This overcomes the limitations of the existing method of denoising using wavelet and curvelet. But due to down sampling and up sampling, the contourlet transform is shift-variant. However, shift-invariance is desirable in image analysis applications such as edge detection, contour characterization, and image enhancement. In this chapter, nonsubsampled contourlet transform (shift-invariance transform)-based denoising is presented which more effectively represents edges than contourlet transform.

Optimal Feature Selection and Extraction for Eye Disease Diagnosis

Ophthalmologists utilize retinal fundus images of humans for the detection, diagnosis, and prediction of many eye diseases. Automatic scrutiny of fundus images are foremost apprehension for ophthalmologists and investigators. The manual recognition of blood vessels is most deceptive because the blood vessels in a fundus image are multifaceted and with low contrast. Unearthing of blood vessels proffers information on pathological transformation and can smooth the progress of rating diseases severity or mechanically diagnosing the diseases. The manual recognition method turns out to be annoying. Consequently, the automatic recognition of blood vessels is also more significant. For extracting the vessel in fundus images unswerving and habitual methods are obligatory. The proposed methodology is designed to effectively diagnose the eye disease by performing feature extraction succeeded by feature selection and to improve the performance factors such as feature extraction ratio, feature selection time, sensitivity, and specificity when compared to the state-of-art methods.

The Fundamentals of Medical Image Restoration

This chapter simply encapsulates the basics of image restoration, various noise models, and degradation model including some blur and image restoration filters. The mining of high resolution information from the low-resolution images is a very vital task in several applications of digital image processing. In recent times, a lot of research work has been carried out in this field in order to improve the resolution of real medical images especially when the given images are corrupted with some kind of noise. The displayed images are the result of the various stages that might cause imperfections in the digital images, for instance the so-called imaging and capturing process can itself degrade the original scene. The imperfections present in the image need to be studied and analyzed if the noise present in the images is not modelled properly. There are different types of degradations which are considered such as noise, geometrical degradations, imperfections (due to improper illumination and color), and blur. Blurring in the images is generally caused by the relative motion between the camera and the original object being captured or due to poor focusing of an optical system. In the production of aerial photographs for remote sensing purposes, blurs are introduced by the atmospheric turbulence, aberrations in the optical system, and relative motion between the camera and the ground. Apart from the blurring effect, noise also creates imperfections in the images that corrupt the images under analysis. The noise may be introduced by several factors (e.g., medium, recording or capturing system, or by the quantization process). Due to this noise or blur present in the images, resolution needs to be improved and the image is to be restored from the geometrically warped, blurred, and noisy images.

Biomedical Image Processing Software Development for Shoulder Arthroplasty

Shoulder arthroplasty is an important operation for the treatment of shoulder joints, with an increasing rate of operations per year around the world. Although this operation is generally achieved successfully, there are a number of complications which increase the risks in the operation. Preoperative planning for a surgery can help reduce the amount of risks resulting from complications and increase the success rate of the operation. Three-dimensional visualization software can be helpful in preoperative planning. This chapter aims to provide such software to help reduce the risks of the operation by visualizing 3D joint anatomy of the specific patient for the surgeon, and letting surgeons observe the geometrical properties of the joint.

The Fundamentals of Biomedical Image Processing

This chapter provides a brief introduction to the various fundamentals and concepts related to the basics of the biomedical image processing. Medical imaging processing comprises various techniques and processes that are used to create images of human body for clinical purposes and medical procedures for the purpose of diagnosis or examination of disease. Digital image processing along with its suitable components and computer-simulated algorithms are implemented using computers to perform the image analysis of digital images. The study of normal anatomy and physiology of human body is made as a part of diagnosis process. Though medical imaging of various organs and tissues can be performed for medical examination purposes, the impact of digital images on modern society is tremendous and image processing has become a critical component of science and technology related to the biomedical image processing.

Certain Investigation Titles on the Segmentation of Colon and Removal of Opacified Fluid for Virtual Colonoscopy

Colorectal cancer (CRC) is a most important type of cancer that can be detected by virtual colonoscopy (VC) in the colon or rectum, and it is the major cause of death prevailing in the world. The CAD technique requires the segmentation of the colon to be accurate and can be implemented by two approaches. The first approach focuses on the segmentation of lungs in the computed tomography (CT) images downloaded from The Cancer Imaging Archive (TCIA) using clustering approach. The second method focused on the automatic segmentation of colon, removal of opacified fluid and bowels for all the slices in a dataset in a sequential order using MATLAB. The second approach requires more computational time, and hence, in order to reduce, the semiautomatic segmentation of colon was implemented in 3D seeded region growing and fuzzy clustering approach in MEVISLAB software. The approaches were implemented in multiple datasets and the accuracy were verified with manual segmentation by radiologist, and the importance of removing opacified fluid were shown for improving the accuracy of colon segments.

Medical Image Registration in Clinical Diagnosis

The term medical image covers a wide variety of types of images (modality), especially in medical image registration with very different perspective. In this chapter, spatial technique is approached and analyzed for providing effective clinical diagnosis. The effective conventional methods are chosen for this registration. Researchers have developed and focused this research using proven conventional methods in the respective fields of registration Affine, Demons, and Affine with B-spline. From the overall analysis, it is clear that Affine with B-Spline performs better in registration of medical images than Affine and Demons.

Medical Image Classification

Diagnosis of diseases at the right stage with optimal accuracy is a significant requirement in the medical field. Apart from diagnosis from clinical symptoms, diagnosis based on scanned images of both internal and external organs is playing a vital role in understanding the severity of the disease. Classification is a field of study derived from artificial intelligence, and today it is widely used in medical image classification. These techniques are used to classify the different stages of a disease or different variant diseases possible in an organ from different types of input images such as magnetic resonance imaging (MRI), computed tomography (CT), x-ray, fundus images, iris images, etc. Various preprocessing techniques are used to select the relevant features from the input image to form the feature set. The classifiers are trained using the feature set to generate models. The generated models can be optimized to improve the performance. Various metrics such as accuracy, coverage, precision, recall, and FMeasure are used to measure the accuracy.

A Comparative Study of Medical Image Retrieval Using Distance, Transform, Texture, and Shape

Content-based medical image retrieval (CBMIR) is the application of computer vision techniques to the problem of medical image search in large databases. Three main techniques are applied to check the applicability. The first technique implemented is distance metrics-based retrieval. The second technique implemented is transform-based retrieval. The transform which has lesser performance is combined with higher performance, to check the applicability of the results. The third technique implemented is content-based medical image retrieval. Texture and shape-based retrieval techniques are also applied. Shape-based retrieval is processed using canny edge with the Otsu method. The multifeature-based technique is also applied and analyzed. The best retrieval rate is achieved by multifeature-based retrieval with 100/50%. Based on more relevant retrieved images all the three, brain, liver, and knee, images are found to be retrieved more with 100/50%.

A Survey on Female Breast Cancer

The mortality rate of breast cancer can be effectively reduced by early diagnosis. Imaging modalities are used to diagnose through computer for women breast cancer. Digital mammography is the best imaging model for breast cancer screening technique and diagnosis. Digital breast tomosynthesis (DBT), a three-dimensional (3-D) mammography, is an advanced form of breast imaging where multiple images of the breast from different angles are captured and reconstructed (synthesized) into a three-dimensional image set. This chapter discusses the research work carried out on the computer diagnosis of women breast cancer through digital breast tomosynthesis and concludes with further improvement in the computer-aided diagnosis.