摘要:
The detection accuracy of poorly differentiated cancers in adenocarcinoma is improved by restricting false detection. Cell nucleus detection means 1 receives a digitized pathological image as an input and extracts the region of a cell nucleus therefrom. Gland duct detection means 2 detects a gland duct structure in the image. Poorly differentiated cancer detection means 4 detects poorly differentiated cancers only in the region other than the gland duct region. False detection rejection means 7 compares the detection density of poorly differentiated cancer in the vicinity of a detection point with a threshold that is predetermined depending on gland duct density in the vicinity of the detection point, at each detection point detected by poorly differentiated cancer detection means 4 and rejects the detection point as a false detection if the detection density of a poorly differentiated cancer is smaller than the threshold.
摘要:
The detection accuracy of poorly differentiated cancers in adenocarcinoma is improved by restricting false detection. Cell nucleus detection means 1 receives a digitized pathological image as an input and extracts the region of a cell nucleus therefrom. Gland duct detection means 2 detects a gland duct structure in the image. Poorly differentiated cancer detection means 4 detects poorly differentiated cancers only in the region other than the gland duct region. False detection rejection means 7 compares the detection density of poorly differentiated cancer in the vicinity of a detection point with a threshold that is predetermined depending on gland duct density in the vicinity of the detection point, at each detection point detected by poorly differentiated cancer detection means 4 and rejects the detection point as a false detection if the detection density of a poorly differentiated cancer is smaller than the threshold.
摘要:
An evaluation system includes a capture unit for capturing an image of a living tissue in which HER2 protein and cell nucleuses are dyed, a discrimination unit for identifying a cell membrane from the image of the living tissue based on dyed cell nucleuses within the image of the living tissue captured by the capture unit to discriminate a dyed state of the cell membrane, and an evaluation unit for evaluating development of the HER2 protein based on a discrimination result by the discrimination unit.
摘要:
An evaluation system includes a capture unit for capturing an image of a living tissue in which HER2 protein and cell nucleuses are dyed, a discrimination unit for identifying a cell membrane from the image of the living tissue based on dyed cell nucleuses within the image of the living tissue captured by the capture unit to discriminate a dyed state of the cell membrane, and an evaluation unit for evaluating development of the HER2 protein based on a discrimination result by the discrimination unit.
摘要:
A breast cancer pathological image diagnosis support system for supporting a diagnosis of breast cancer based on a pathological image is provided. The breast cancer pathological image diagnosis support system includes an image obtaining unit which obtains an HE-stained image and an IHC image as pathological images to be diagnosed; an information obtaining unit which obtains information of a tumor area in the HE-stained image; a matching unit which calculates a matching position of the HE-stained image and the IHC image obtained by the image obtaining unit; a specifying unit which specifies a tumor area in the IHC image based on the information of the tumor area in the HE-stained image obtained by the information obtaining unit and information of the matching position calculated by the matching unit; and a calculating unit which calculates a staining positive cell content rate in the tumor area based on information of the tumor area in the IHC image specified by the specifying unit.
摘要:
A breast cancer pathological image diagnosis support system for supporting a diagnosis of breast cancer based on a pathological image is provided. The breast cancer pathological image diagnosis support system includes an image obtaining unit which obtains an HE-stained image and an IHC image as pathological images to be diagnosed; an information obtaining unit which obtains information of a tumor area in the HE-stained image; a matching unit which calculates a matching position of the HE-stained image and the IHC image obtained by the image obtaining unit; a specifying unit which specifies a tumor area in the IHC image based on the information of the tumor area in the HE-stained image obtained by the information obtaining unit and information of the matching position calculated by the matching unit; and a calculating unit which calculates a staining positive cell content rate in the tumor area based on information of the tumor area in the IHC image specified by the specifying unit.
摘要:
A parallel sorting apparatus is provided whose sorting processing is speeded up. A reference value calculation section calculates a plurality of reference values serving as boundaries of intervals used for allocating input data depending on the magnitude of a value. An input data aggregation section partitions the input data into a plurality of input data regions, and calculates, by parallel processing, mapping information used for allocating data in each of the partitioned input data regions to the plurality of intervals that have boundaries on the reference values calculated by the reference value calculation section. A data allocation section allocates, by parallel processing, data in each of the input data regions to the plurality of intervals in accordance with the mapping information calculated by the input data aggregation section. An interval sorting section individually sorts, by parallel processing, data in the plurality of intervals allocated by the data allocation section.
摘要:
A parallel sorting apparatus is provided whose sorting processing is speeded up. A reference value calculation section calculates a plurality of reference values serving as boundaries of intervals used for allocating input data depending on the magnitude of a value. An input data aggregation section partitions the input data into a plurality of input data regions, and calculates, by parallel processing, mapping information used for allocating data in each of the partitioned input data regions to the plurality of intervals that have boundaries on the reference values calculated by the reference value calculation section. A data allocation section allocates, by parallel processing, data in each of the input data regions to the plurality of intervals in accordance with the mapping information calculated by the input data aggregation section. An interval sorting section individually sorts, by parallel processing, data in the plurality of intervals allocated by the data allocation section.
摘要:
An active learning system samples known data, and learns the known data independently in a plurality of learning machines, and selects data to be next learned for unknown data. The active learning system comprises a sampling weighting device for weighting the known data when they are sampled, a prediction weighting device for weighting the learning results of the learning machines when they are integrated, and a data weighting device for weighting the learning results when the data to be next learned is selected. When an extreme deviation is present in the count of data, each of the weighting devices more heavily weights a larger count of data.
摘要:
An active learning system samples known data, and learns the known data independently in a plurality of learning machines, and selects data to be next learned for unknown data. The active learning system comprises a sampling weighting device for weighting the known data when they are sampled, a prediction weighting device for weighting the learning results of the learning machines when they are integrated, and a data weighting device for weighting the learning results when the data to be next learned is selected. When an extreme deviation is present in the count of data, each of the weighting devices more heavily weights a larger count of data.