US 12,073,559 B2
Methods for automated detection of cervical pre-cancers with a low-cost, point-of-care, pocket colposcope
Mercy Asiedu, Durham, NC (US); Nirmala Ramanujam, Durham, NC (US); and Guillermo Sapiro, Durham, NC (US)
Assigned to Duke University, Durham, NC (US)
Appl. No. 17/282,093
Filed by Duke University, Durham, NC (US)
PCT Filed Oct. 4, 2019, PCT No. PCT/US2019/054773
§ 371(c)(1), (2) Date Apr. 1, 2021,
PCT Pub. No. WO2020/076644, PCT Pub. Date Apr. 16, 2020.
Prior Publication US 2021/0374953 A1, Dec. 2, 2021
Int. Cl. G06T 7/136 (2017.01); A61B 1/00 (2006.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/168 (2017.01)
CPC G06T 7/0012 (2013.01) [A61B 1/000094 (2022.02); G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06T 7/168 (2017.01); G06T 2207/20024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/30096 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A method for automated detection of cervical pre-cancer, the method comprising:
providing at least one cervigram;
pre-processing the at least one cervigram including automatically segmenting a region from the cervix for further analysis;
extracting texture-based features from the segmented region of the at least one pre-processed cervigram; and
classifying the at least one cervigram as negative or positive for cervical pre-cancer based on the extracted features.
 
13. A method for developing an algorithm for automated cervical cancer diagnosis, the method comprising:
providing a plurality of cervigrams;
pre-processing each cervigram including automatically segmenting a region from the cervix for further analysis;
extracting texture-based features from the segmented region of each pre-processed cervigram; and
establishing a classification model based on the extracted features for each cervigram,
wherein the classification model is configured to classify additional cervigrams as negative or positive for cervical pre-cancer.