Title:
IMAGE ANALYSIS METHOD, IMAGE ANALYSIS DEVICE, IMAGE ANALYSIS SYSTEM, IMAGE ANALYSIS PROGRAM, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2019/102829
Kind Code:
A1
Abstract:
In order to accurately evaluate the degree of change that has occurred in a tissue, the present invention is provided with: a Betti number calculation unit (42) which generates, for one captured image of the tissue, a plurality of binarized images having different reference values used for binarization, and calculates, for each of the plurality of binarized images, a first feature number indicating the number of connected regions in which pixels having one of the binarized pixel values are connected; and a prediction score determination unit (44) for determining information relating to a change that has occurred in the tissue on the basis of the result of comparison between a pattern indicating a correlation between the reference value for binarization and the first feature number and a predetermined reference pattern.
More Like This:
Inventors:
NAKANE KAZUAKI (JP)
NISHIO MIZUHO (JP)
NISHIO MIZUHO (JP)
Application Number:
PCT/JP2018/040977
Publication Date:
May 31, 2019
Filing Date:
November 05, 2018
Export Citation:
Assignee:
UNIV OSAKA (JP)
International Classes:
A61B6/03; G06T7/00; G06T7/136; G06T7/187; G06T7/60
Domestic Patent References:
| WO2010087112A1 | 2010-08-05 |
Other References:
NISHIO, MIZUHO ET AL.: "Regarding Relationship between Quantitative and Visual Evaluation of Emphysema by Homology and Visual Evaluation and Prediction of Visual Evaluation by Machine Learning", PREPRINTS OF 9TH JAPANESE SOCIETY OF PULMONARY FUNCTIONAL IMAGING, 28 January 2017 (2017-01-28), pages 66
NAKANE, KAZUAKI ET AL.: "(non-official translation) 4. Tissue image analysis method using the concept of homology", EXPERIMENTAL MEDICINE EXTRA ISSUE, vol. 35, no. 5, 6 March 2017 (2017-03-06)
QAISER, TALHA ET AL.: "Persistent Homology for Fast Tumor Segmentation in Whole Slide Histology Images", PROCEDIA COMPUTER SCIENCE, vol. 90, 2016, pages 119 - 124, XP029654609, DOI: 10.1016/j.procs.2016.07.033
NAKANE, KAZUAKI ET AL.: "Homology-based method for detecting regions of interest in colonic digital images", DIAGNOSTIC PATHOLOGY, vol. 10, 2015, pages 36, XP021223131, DOI: 10.1186/s13000-015-0244-x
NAKANE, KAZUAKI ET AL.: "Research performance report on Grants-in-Aid for Scientific Research of Ministry of Education, Culture, Sports , Science and Technology", THE IMAGE ANALYZING METHOD BASED ON THE HOMOLOGY CONCEPT, 31 May 2017 (2017-05-31), XP055616645, Retrieved from the Internet [retrieved on 20190115]
NAKANE, KAZUAKI: "(non-official translation) About Automation of Cancer Pathological Image Diagnosis (10th Theory of Biomathematics and its Application)", RIMS KOKYUROKU, vol. 1917, 2014, pages 37 - 42
NISHIO, MIZUHO ET AL.: "Application of the homology method for quantification of low- attenuation lung region in patients with and without COPD", INTERNATIONAL JOURNAL OF COPD, vol. 2016, no. 11, 6 September 2016 (2016-09-06), pages 2125 - 2137, XP055616651, DOI: 10.2147/COPD.S110504
NISHIO, MIZUHO ET AL.: "Automated prediction of emphysema visual score using homology-based quantification of low-attenuation lung region", PLOS ONE, vol. 12, no. 5, e0178217, 25 May 2017 (2017-05-25), XP055616653, DOI: 10.1371/journal.pone.0178217
NAKANE, KAZUAKI ET AL.: "(non-official translation) 4. Tissue image analysis method using the concept of homology", EXPERIMENTAL MEDICINE EXTRA ISSUE, vol. 35, no. 5, 6 March 2017 (2017-03-06)
QAISER, TALHA ET AL.: "Persistent Homology for Fast Tumor Segmentation in Whole Slide Histology Images", PROCEDIA COMPUTER SCIENCE, vol. 90, 2016, pages 119 - 124, XP029654609, DOI: 10.1016/j.procs.2016.07.033
NAKANE, KAZUAKI ET AL.: "Homology-based method for detecting regions of interest in colonic digital images", DIAGNOSTIC PATHOLOGY, vol. 10, 2015, pages 36, XP021223131, DOI: 10.1186/s13000-015-0244-x
NAKANE, KAZUAKI ET AL.: "Research performance report on Grants-in-Aid for Scientific Research of Ministry of Education, Culture, Sports , Science and Technology", THE IMAGE ANALYZING METHOD BASED ON THE HOMOLOGY CONCEPT, 31 May 2017 (2017-05-31), XP055616645, Retrieved from the Internet
NAKANE, KAZUAKI: "(non-official translation) About Automation of Cancer Pathological Image Diagnosis (10th Theory of Biomathematics and its Application)", RIMS KOKYUROKU, vol. 1917, 2014, pages 37 - 42
NISHIO, MIZUHO ET AL.: "Application of the homology method for quantification of low- attenuation lung region in patients with and without COPD", INTERNATIONAL JOURNAL OF COPD, vol. 2016, no. 11, 6 September 2016 (2016-09-06), pages 2125 - 2137, XP055616651, DOI: 10.2147/COPD.S110504
NISHIO, MIZUHO ET AL.: "Automated prediction of emphysema visual score using homology-based quantification of low-attenuation lung region", PLOS ONE, vol. 12, no. 5, e0178217, 25 May 2017 (2017-05-25), XP055616653, DOI: 10.1371/journal.pone.0178217
Attorney, Agent or Firm:
HARAKENZO WORLD PATENT & TRADEMARK (JP)
Download PDF:
Previous Patent: CONVERSION INFORMATION ACQUISITION DEVICE, PROGRAM DEVELOPMENT ASSISTANCE DEVICE, CONVERSION INFORMA...
Next Patent: BAND-PASS FILTER
Next Patent: BAND-PASS FILTER