Abstract:
A hemorrhage edge candidate area extraction section extracts a candidate area for the outline part of a hemorrhage area, based on an image signal of a medical image constituted by multiple color signals obtained by capturing an image of a living body. A feature quantity calculation section calculates a feature quantity of the hemorrhage area based on calculation of the amount of change in the image signal in a small area including the candidate area, among multiple small areas obtained by dividing the medical image. A hemorrhage edge determination section determines whether or not the candidate areas are the outline part of the hemorrhage area based on the feature quantity.
Abstract:
A plurality of images inputted in an image signal input portion are divided into a plurality of regions by an image dividing portion, and a feature value in each of the plurality of regions is calculated by a feature value calculation portion and divided into a plurality of subsets by a subset generation portion. On the other hand, a cluster classifying portion classifies a plurality of clusters generated in a feature space into any one of a plurality of classes on the basis of the feature value and occurrence frequency of the feature value. And a classification criterion calculation portion calculates a criterion of classification for classifying images included in one subset on the basis of a distribution state of the feature value in the feature space of each of the images included in the one subset.
Abstract:
An image processing apparatus and an image processing method which can improve efficiency of observation by a user are provided. The image processing apparatus of the present invention includes an image inputting unit configured to input a medical image including a plurality of color signals; a determining unit configured to determine whether the biological mucosa is sufficiently captured in the inputted medical image or not; and a controlling unit configured to control at least either of display or storage of the medical image based on the determination result in the determining unit.
Abstract:
An endoscope inserting direction detecting system receives an endoscopic image, detects an endoscope inserting direction, in which an endoscope should be inserted, on the basis of the endoscopic image and produces information concerning the detected inserting direction. The endoscope inserting direction detecting method includes setting sampling pixels, detecting the direction of a change in brightness in the endoscopic image and evaluating the angles among a plurality of inserting-direction candidates and the direction of the change in brightness.
Abstract:
An endoscope inserting direction method includes a first step of receiving endoscopic images time-sequentially, a second step of sampling pixels representing low densities from pixels of each of the endoscopic images which are time-sequentially received in the first step and a third step of determining whether or not number of pixels representing low densities which are sampled in the second step is equal to or larger than predetermined number of pixels. In a fourth step, if the number of pixels representing low densities is determined to be equal to or larger than the predetermined number of pixels in the third step, a position of the barycenter of the pixels representing low densities is obtained, and based on a change in the position of the barycenter of the pixels representing low densities of the time-sequentially received endoscopic images, a direction of a shift in the time-sequentially received plurality of endoscopic images is detected. In a fifth step, an endoscope inserting direction, in which an endoscope should be inserted, on the basis of the result of the detection performed in the fourth step is determined.
Abstract:
An endoscope inserting direction detecting method includes receiving an endoscopic image and judging from the endoscopic image whether or not an endoscope is located too closely to an object of observation. When it is judged that the endoscope is located too closely to the object of observation, information is produced for prompting pull-back of the endoscope. When it is judged that the endoscope is not located too closely to the object of observation, a detecting algorithm is selected and applied according to the endoscopic image from among plural detecting algorithms for detecting an inserting direction of the endoscope.
Abstract:
A hemorrhage edge candidate area extraction section extracts a candidate area for the outline part of a hemorrhage area, based on an image signal of a medical image constituted by multiple color signals obtained by capturing an image of a living body. A feature quantity calculation section calculates a feature quantity of the hemorrhage area based on calculation of the amount of change in the image signal in a small area including the candidate area, among multiple small areas obtained by dividing the medical image. A hemorrhage edge determination section determines whether or not the candidate areas are the outline part of the hemorrhage area based on the feature quantity.
Abstract:
A hemorrhage edge candidate area extraction section extracts a candidate area for the outline part of a hemorrhage area, based on an image signal of a medical image constituted by multiple color signals obtained by capturing an image of a living body. A feature quantity calculation section calculates a feature quantity of the hemorrhage area based on calculation of the amount of change in the image signal in a small area including the candidate area, among multiple small areas obtained by dividing the medical image. A hemorrhage edge determination section determines whether or not the candidate areas are the outline part of the hemorrhage area based on the feature quantity.
Abstract:
The invention provides an endoscope inserting direction detecting apparatus and method with which the direction of a lumen can be determined reliably despite a simple configuration. The endoscope inserting direction detecting apparatus includes a pixel sampling unit that samples a stated pixel value from each of domains constituting an endoscopic image received by an image input/output control circuit; a shape-of-range estimating unit that estimates the shape of a range within the endoscopic image according to the continuity of the distribution of the pixels indicating the stated pixel value; and an inserting direction determining unit that determines an inserting direction within a body cavity, in which an endoscope should be further inserted, on the basis of the estimated shape. The inserting direction is displayed together with the endoscopic image.
Abstract:
An endoscope device obtains tissue information of a desired depth near the tissue surface. A xenon lamp (11) in a light source (4) emits illumination light. A diaphragm (13) controls a quantity of the light that reaches a rotating filter. The rotating filter has an outer sector with a first filter set, and an inner sector with a second filter set. The first filter set outputs frame sequence light having overlapping spectral properties suitable for color reproduction, while the second filter set outputs narrow-band frame sequence light having discrete spectral properties enabling extraction of desired deep tissue information. A condenser lens (16) collects the frame sequence light coming through the rotating filter onto the incident face of a light guide (15). The diaphragm controls the amount of the light reaching the filter depending on which filter set is selected.