Abstract:
The position of an antenna incorporated in a capsule-type endoscope 3 that moves in a body is estimated using a plurality of antennae, and where the distance dij between two positions Pti and P(t−1)j estimated at adjacent times falls within a predetermined value, pieces of information for these positions are related to each other and stored in a memory as connection information. Subsequently, processing for searching for a route from the connection information stored in the memory and calculating a track is performed.
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:
An endoscope inserting direction detecting method includes receiving an endoscopic image, sampling pixels, which represent high densities, from data of the endoscopic image, defining an approximate expression for providing an approximate state of a distribution of sampling-pixels, evaluating a difference between a state of distribution of the sampling-pixels and a result of an approximation based on the approximate expression, and determining an endoscope inserting direction, in which an endoscope should be inserted, on the basis of a result of and evaluation of the fourth step.
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:
The present invention comprises: 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, whereby the direction of a lumen can be determined reliably despite a simple configuration.
Abstract:
An endoscopic system comprises an endoscope system, an endoscopic position detecting apparatus, and an image processing apparatus. The endoscope system enables endoscopic examinations. The endoscopic position detecting apparatus detects the three-dimensional positions of the distal part of the endoscope in a body cavity. The image processing apparatus estimates the shape of an object entity visualized by the endoscope. The image processing apparatus is used as a means for grasping the shape of an object entity in a body cavity. For this purpose, the insertion unit of an electronic endoscope is inserted into the body cavity of a patient lying down on a patient couch. Specifically, a main unit of the image processing apparatus is connected to a video processor over a cable, and receives an image signal (R, G, and B signals and a sync signal) sent from the video processor. The main unit of the image processing apparatus estimates relative shapes according to successive image signals representing the object entity and being sent from the video processor. The main unit of the image processing apparatus then calculates the absolute shape of the object entity according to the position data of the distal part of the electronic endoscope sent from a main unit of the endoscopic position detecting apparatus.
Abstract:
A fluorescence endoscopy and an endoscopic device therefor, wherein, to an object to be examined containing a fluorescent substance, light rays in a plurality of wavelength ranges whose degrees of exciting the fluorescent substance are different from one another and which can constitute a color images are sequentially irradiated; images of the object are obtained by the respective wavelength ranges; a color image of the object is constituted using the images obtained by the respective wavelength ranges and information based on fluorescence emitted by the fluorescent substance, is obtained using at least an image obtained by a wavelength whose degree of exciting the fluorescent substance is largest out of the images obtained by the respective wavelength ranges.
Abstract:
An endoscope video apparatus has an endoscope including a solid-state image sensor, for outputting an endoscopic image signal, a video processor for processing the image signal supplied from the solid-state image sensor and outputting a video signal, an image file unit for recording the video signal, and an input section for inputting retrieval data corresponding to the video signal recorded in the image file unit. A control section discriminates the presence/absence of retrieval data input from the input section. A control circuit operates an alarm unit by discrimination data representing the absence of retrieval data.
Abstract:
A medical image processing apparatus includes a selection portion that selects a pixel of interest from an image composed of a plurality of pixels and obtained by picking up an image of a living tissue, a first feature value calculation portion that calculates a first feature value on the basis of color tone of the pixel of interest and color tones of surrounding pixels, a second feature value calculation portion that calculates a second feature value on the basis of the color tone of the pixel of interest and the color tones of surrounding pixels, an evaluation value calculation portion that calculates an evaluation value on the basis of the first feature value and the second feature value, and an evaluation value judgment portion that judges whether the pixel of interest is a pixel constituting the linear structure, on the basis of the evaluation value.
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.