Back to results
US 10,872,411 B2Granted
Diagnostic imaging assistance apparatus and system, and diagnostic imaging assistance method
AssigneeHitachi High-Tech Corporation
InventorsHideharu Hattori, Kenko Uchida, Sadamitsu Aso, Toshinari Sakurai, Yasuki Kakishita
Life of this patent
Estimating the term…
Abstract
A diagnostic imaging assistance apparatus according to the present invention performs a process of inputting images of a tissue and a cell, a process of extracting feature amounts of a wide view and a narrow view from a target image to be processed, a process of classifying whether the target images having different views are normal or abnormal from the feature amounts, and a process of classifying a lesion likelihood using a classification result.
Claims17
A diagnostic imaging assistance apparatus comprising:
- an input unit configured to receive wide view image data and narrow view image data in a same image as image data obtained by capturing a slice of a tissue or a cell of a diagnostic object;
- a feature extraction unit configured to process the image data input to the input unit to extract a feature amount on an image of the tissue from the wide view image data and extract a feature amount on an image of the cell from the narrow view image data;
- a single view determination unit configured to classify whether the tissue is normal or abnormal from the feature amount of the wide view image data extracted by the feature extraction unit, and classify whether the cell is normal or abnormal from the feature amount of the narrow view image data;
- a multiple view determination unit configured to classify a lesion likelihood of the diagnostic object from a classification result of the wide view image data and a classification result of the narrow view image data classified by the single view determination unit;
- a drawing unit configured to actualize a region containing the tissue or the cell classified as abnormal by the multiple view determination unit on the image data;
- and
- a recording unit configured to store an image of which the region containing the tissue or the cell classified as abnormal is actualized by the drawing unit.
4 more elements
A diagnostic imaging assistance method comprising:
- inputting wide view image data obtained by capturing a tissue of a diagnostic object to an input unit;
- processing the wide view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the tissue;
- classifying whether the tissue is normal or abnormal by a single view determination unit from the feature amount of the wide view image data extracted by the feature extraction unit;
- inputting narrow view image data in a same image as the wide view containing a cell captured from the tissue classified as abnormal by the single view determination unit to the input unit, the narrow view image data and the wide view image data comprising image data;
- processing the narrow view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the cell;
- classifying whether the cell is normal or abnormal by the single view determination unit from the feature amount of the narrow view image data extracted by the feature extraction unit;
- classifying a lesion likelihood of the diagnostic object by a multiple view determination unit from a classification result of the wide view image data and a classification result of the narrow view image data classified by the single view determination unit;
- actualizing a region containing the tissue or the cell classified as abnormal by the single view determination unit on the image data in a drawing unit;
- and
- storing the image data obtained by actualizing the region containing the tissue or the cell classified as abnormal in a recording unit.
7 more elements
A diagnostic imaging assistance method comprising:
- inputting narrow view image data obtained by capturing a cell of a diagnostic object to an input unit;
- processing the narrow view image data input to the input unit by a feature extraction unit to extract a feature amount on an image of the cell;
- classifying whether the cell is normal or abnormal by a single view determination unit from the feature amount of the narrow view image data extracted by the feature extraction unit;
- capturing an image of a tissue containing a cell classified as abnormal by the single view determination unit to input wide view image data of the tissue to the input unit, the narrow view image data and the wide view image data comprising image data;
- processing the wide view image data input to the input unit by a feature extraction unit to extract a feature amount on the image of the tissue;
- classifying whether the tissue is normal or abnormal by the single view determination unit from the feature amount of the wide view image data extracted by the feature extraction unit;
- classifying a lesion likelihood of the diagnostic object by a multiple view determination unit from a classification result of the narrow view image data and a classification result of the wide view image data classified by the single view determination unit;
- actualizing a region containing the cell or the tissue classified as abnormal by the single view determination unit on the image data in a drawing unit;
- and
- storing the image data obtained by actualizing the region containing the cell or the tissue classified as abnormal in a recording unit.
7 more elements
Dependencies are inferred from the claim text.