The problems of installation and integration of complex suite of software for processing medical images. Based analysis of the situation is realized in an easier integration of an automated system using the latest inf...The problems of installation and integration of complex suite of software for processing medical images. Based analysis of the situation is realized in an easier integration of an automated system using the latest information technologies using the web - environment for analysis and segmentation of DICOM - images.展开更多
Automatic interpretation of the images of colon cell biopsies requires automatic segmentation of these cells in the image obtained. The active contour method for image segmentation is a well known method for automatic...Automatic interpretation of the images of colon cell biopsies requires automatic segmentation of these cells in the image obtained. The active contour method for image segmentation is a well known method for automatic detection of the cell contour. However, the application of this method on colon cell images was not effective. In this paper, the authors have proposed a new technique to reduce the analysis time needed to detect cells in a given image. This technique is based on the active contour method but now using a progressive division of the dimensions of the image to achieve convergence. The model proposed succeeded in detecting cells whose boundaries are not necessarily defined by a gradient. The initial curve can be anywhere in the image, and interior contours can be automatically detected. The developed algorithm was successfully applied on textured multispectral images of three types of cells, including benign hyperplasia （BH）, intraepithelial neoplasia （IN）, and carcinoma （Ca） cells.展开更多
Oceanic eddies may cause local sea surface temperature （SST）, height, and salinity anomalies in remote sensing （RS） images. Remote sensed SST imagery has proven to be an effective technique in oceanic eddy detecti...Oceanic eddies may cause local sea surface temperature （SST）, height, and salinity anomalies in remote sensing （RS） images. Remote sensed SST imagery has proven to be an effective technique in oceanic eddy detection, because of its high temporal and spatial resolution. Various techniques have been used to identify eddies from SST images. However, mainly owing to the strong morphological variation of oceanic eddies, there is arguably no uniquely correct eddy detection method. A scheme of algorithm based on quasi-contour tracing and clustering of eddy detection from SST dataset is presented. The method does not impose fixed restrictions or limitations during the course of ＂suspected＂ eddy detection, and any eddy-like structures can be detected as ＂suspected＂ eddies. Then, ＂true＂ eddies can be identified based on the combination of intensity and spatial/temporal scale criteria. This approach has been applied to detect eddies in the East China Sea by using Operational SST ＆ Sea Ice Analysis （OSTIA） dataset. Experiments proved that oceanic eddies ranging in diameter from tens to hundreds of kilometers can be detected. Through investigation of the 2007-2011 OSTIA daily SST dataset from the Kuroshio region in the East China Sea, we found that the most active regions for oceanic eddies are those along the Kuroshio path, northeast of Taiwan Island, the Yangtze Estuary and the Ryukyu Islands. About 86% of the cyclonic eddies and 87% of the anticyclonic eddies have the size of 50-100 km in diameter. Only 25% of the anticyclonic eddy and 26% of the cyclonic eddy have the strength more than 0.4℃ in the sea surface layer.展开更多
We present a computerized method for the semi-automatic detection of contours in ultrasound images. The novelty of our study is the introduction of a fast and efficient image function relating to parametric active con...We present a computerized method for the semi-automatic detection of contours in ultrasound images. The novelty of our study is the introduction of a fast and efficient image function relating to parametric active contour models. This new function is a combination of the gray-level information and first-order statistical features, called standard deviation parameters. In a comprehensive study, the developed algorithm and the efficiency of segmentation were first tested for synthetic images. Tests were also performed on breast and liver ultrasound images. The proposed method was compared with the watershed approach to show its efficiency. The performance of the segmentation was estimated using the area error rate. Using the standard devia- tion textural feature and a 5x5 kernel, our curve evolution was able to produce results close to the minimal area error rate （namely 8.88% for breast images and 10.82% for liver images）. The image resolution was evaluated using the con- trast-to-gradient method. The experiments showed promising segmentation results.展开更多
文摘The problems of installation and integration of complex suite of software for processing medical images. Based analysis of the situation is realized in an easier integration of an automated system using the latest information technologies using the web - environment for analysis and segmentation of DICOM - images.
文摘Automatic interpretation of the images of colon cell biopsies requires automatic segmentation of these cells in the image obtained. The active contour method for image segmentation is a well known method for automatic detection of the cell contour. However, the application of this method on colon cell images was not effective. In this paper, the authors have proposed a new technique to reduce the analysis time needed to detect cells in a given image. This technique is based on the active contour method but now using a progressive division of the dimensions of the image to achieve convergence. The model proposed succeeded in detecting cells whose boundaries are not necessarily defined by a gradient. The initial curve can be anywhere in the image, and interior contours can be automatically detected. The developed algorithm was successfully applied on textured multispectral images of three types of cells, including benign hyperplasia （BH）, intraepithelial neoplasia （IN）, and carcinoma （Ca） cells.
文摘Oceanic eddies may cause local sea surface temperature （SST）, height, and salinity anomalies in remote sensing （RS） images. Remote sensed SST imagery has proven to be an effective technique in oceanic eddy detection, because of its high temporal and spatial resolution. Various techniques have been used to identify eddies from SST images. However, mainly owing to the strong morphological variation of oceanic eddies, there is arguably no uniquely correct eddy detection method. A scheme of algorithm based on quasi-contour tracing and clustering of eddy detection from SST dataset is presented. The method does not impose fixed restrictions or limitations during the course of ＂suspected＂ eddy detection, and any eddy-like structures can be detected as ＂suspected＂ eddies. Then, ＂true＂ eddies can be identified based on the combination of intensity and spatial/temporal scale criteria. This approach has been applied to detect eddies in the East China Sea by using Operational SST ＆ Sea Ice Analysis （OSTIA） dataset. Experiments proved that oceanic eddies ranging in diameter from tens to hundreds of kilometers can be detected. Through investigation of the 2007-2011 OSTIA daily SST dataset from the Kuroshio region in the East China Sea, we found that the most active regions for oceanic eddies are those along the Kuroshio path, northeast of Taiwan Island, the Yangtze Estuary and the Ryukyu Islands. About 86% of the cyclonic eddies and 87% of the anticyclonic eddies have the size of 50-100 km in diameter. Only 25% of the anticyclonic eddy and 26% of the cyclonic eddy have the strength more than 0.4℃ in the sea surface layer.
基金supported by the Project SOP HRD-EFICIENT 61445/2009 of University Dunarea de Jos of Galati,Romania
文摘We present a computerized method for the semi-automatic detection of contours in ultrasound images. The novelty of our study is the introduction of a fast and efficient image function relating to parametric active contour models. This new function is a combination of the gray-level information and first-order statistical features, called standard deviation parameters. In a comprehensive study, the developed algorithm and the efficiency of segmentation were first tested for synthetic images. Tests were also performed on breast and liver ultrasound images. The proposed method was compared with the watershed approach to show its efficiency. The performance of the segmentation was estimated using the area error rate. Using the standard devia- tion textural feature and a 5x5 kernel, our curve evolution was able to produce results close to the minimal area error rate （namely 8.88% for breast images and 10.82% for liver images）. The image resolution was evaluated using the con- trast-to-gradient method. The experiments showed promising segmentation results.
