Automating Medical Image Analysis
نویسنده
چکیده
By image analysis we mean the operation of extracting a relativeiy small amount of quantitative information from a two-dimensional image. Typically, a two-dimensional image, in digital form, consists of an array of 512 x 512 eight-bit digital words. The quantitative information to be extracted consists of a few thousand digital words. These words may describe, for example, the contours of cell cross sections as seen in optical or electron microscope pictures, or contours of the heart wall as seen with a two-dimensional echocardiographic system. A system for interactively extracting the quantitative data has been developed at APL. A duplicate version has been in operation at the Johns Hopkins Medical Institutions for the past year in support of cardiology research programs. The design of the system has been strongly influenced by the fact that we are concentrating on the class of image analysis problems that requires the processing of a few hundred to a few thousand images for a meaningful medical study. This imposes a requirement for rapid entry of pictures into the system and computerized handling of the data extracted from the pictures. Pictures can be entered from 35-mm film, hard copy, video tape, or digital tape. Except for digital tape entry, the picture is entered in standard (analog) video format and is digitized and stored for display and processing in a commercial video image processor interfaced with a minicomputer. Digitizing a picture requires one frame time (1/30 second). The system also provides means for identifying the data by a character header and placing it on disk file in a central computer (IBM 3033). This approach permits ready access to the data for analysis by use of a highlevel interactive language called APL. The input picture is displayed on a cathode ray tube (CRT) and the user controls the system by means of a digitizing tablet that has a 16-button cursor. The operating modes of the system are selected by the push buttons. Moving the cursor over the surface of the digitizing tablet causes an electronic cursor, which appears superimposed on the picture displayed on the CRT, to move a corresponding amount. This provides a convenient and flexible means for the user
منابع مشابه
Incorporating prior knowledge in medical image segmentation: a survey
Medical image segmentation, the task of partitioning an image into meaningful parts, is an important step toward automating medical image analysis and is at the crux of a variety of medical imaging applications, such as computer aided diagnosis, therapy planning and delivery, and computer aided interventions. However, the existence of noise, low contrast and objects’ complexity in medical image...
متن کاملRiemannian Manifolds for Brain Extraction on Multi-modal Resonance Magnetic Images
In this paper, we present an application of Riemannian geometry for processing non-Euclidean image data. We consider the image as residing in a Riemannian manifold, for developing a new method to brain edge detection and brain extraction. Automating this process is a challenge due to the high diversity in appearance brain tissue, among different patients and sequences. The main contribution, in...
متن کاملCurrent Methods in Medical Image Segmentation1
■ Abstract Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. We present a critical appraisal of the current status of semiautomated and automated methods for the segmentation of anatomical medical images. Terminology and important issues in image segmentation are fir...
متن کاملA Survey of Current Methods in Medical Image Segmentation
Image segmentation plays a crucial role in many medical imaging applications by automating or facilitating the delineation of anatomical structures and other regions of interest. We present herein a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Current segmentation approaches are reviewed with an emphasis plac...
متن کاملRough Set based MRI Medical image segmentation using optimized initial centroids
Medical image segmentation plays a vital role in image processing due to the catering needs of the medical images in automating, delineating anatomical structures and diagnosis. Very often the medical images contain uncertain, vague, and incomplete data definition. The concepts of lower and upper approximations of rough sets effectively handle this data. In this paper, rough sets based clusteri...
متن کاملAutomated Analysis of the Mitotic Phases of Human Cells in 3D Fluorescence Microscopy Image Sequences
The evaluation of fluorescence microscopy images acquired in high-throughput cell phenotype screens constitutes a substantial bottleneck and motivates the development of automated image analysis methods. Here we introduce a computational scheme to process 3D multi-cell time-lapse images as they are produced in large-scale RNAi experiments. We describe an approach to automatically segment, track...
متن کامل