Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019045480) TUBERCULOSIS DIAGNOSIS METHOD BASED ON DEEP-LEARNING
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/045480 International Application No.: PCT/KR2018/010053
Publication Date: 07.03.2019 International Filing Date: 30.08.2018
IPC:
G16H 50/20 (2018.01) ,G16H 50/50 (2018.01) ,G06N 3/08 (2006.01)
[IPC code unknown for G16H 50/20][IPC code unknown for G16H 50/50]
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
08
Learning methods
Applicants:
(주)인스페이스 INSPACE CO., LTD. [KR/KR]; 대전시 유성구 가정북로 96 501호 501, 96, Gajeongbuk-ro Yuseong-gu Daejeon 34111, KR
Inventors:
최명진 CHOI, Myung Jin; KR
김태영 KIM, Tae Young; KR
김문기 KIM, Moon Gi; KR
박현우 PARK, Hyun Woo; KR
박준호 PARK, Jun Ho; KR
신소연 SHIN, So Youn; KR
정해영 JEONG, Hea Young; KR
Agent:
정회환 CHUNG, Hwoi Hwan; KR
Priority Data:
10-2017-010976630.08.2017KR
Title (EN) TUBERCULOSIS DIAGNOSIS METHOD BASED ON DEEP-LEARNING
(FR) MÉTHODE DE DIAGNOSTIC DE LA TUBERCULOSE BASÉE SUR UN APPRENTISSAGE EN PROFONDEUR
(KO) 딥러닝 기반 결핵 검사 방법
Abstract:
(EN) A tuberculosis diagnosis method based on deep-learning of the present invention comprises: a step of acquiring an image from a sputum smear slide made for training by using image capturing equipment; a learning step of learning a deep-learning model to be used to determine tuberculosis by using the acquired image; a verification step of verifying accuracy in the deep-learning model learned through the learning step; a step of determining negative or positive for tuberculosis by using a weighted value of the deep-learning model learned through the learning step and the verification step; and a displaying step of providing, to a user, a test result made through the tuberculosis determination step by displaying the test result on a monitor.
(FR) Une méthode de diagnostic de la tuberculose basée sur un apprentissage en profondeur de la présente invention comprend : une étape d'acquisition d'une image à partir d'une microplaquette de frottis d'expectoration fabriquée pour la formation à l'aide d'un équipement de capture d'image ; une étape d'apprentissage consistant en l'apprentissage d'un modèle d'apprentissage en profondeur à utiliser pour déterminer la présence de tuberculose à l'aide de l'image acquise ; une étape de vérification consistant en la vérification de la précision du modèle d'apprentissage en profondeur appris par l'intermédiaire de l'étape d'apprentissage ; une étape de détermination de l'absence ou de la présence de la tuberculose à l'aide d'une valeur pondérée du modèle d'apprentissage en profondeur appris par l'intermédiaire de l'étape d'apprentissage et de l'étape de vérification ; et une étape d'affichage consistant en la fourniture, à un utilisateur, d'un résultat de test effectué par l'intermédiaire de l'étape de détermination de la présence de tuberculose par l'affichage du résultat de test sur un moniteur.
(KO) 본 발명의 딥러닝 기반 결핵검사방법은 영상 촬영 장비를 이용하여 훈련용으로 제작된 객담도말 슬라이드로부터 영상을 획득하는 단계; 상기 획득한 영상으로 결핵 판정에 사용될 딥러닝 모델을 학습하기 위한 학습 단계; 상기 학습단계를 통해 학습된 딥러닝 모델의 정확도를 검증하기 위한 검증단계; 상기 학습 단계와 상기 검증 단계를 통해 학습된 딥러닝 모델의 가중치 값을 이용하여 결핵 음성 또는 양성 여부를 판정하는 단계;및 상기 결핵 판정단계를 통해 나온 검사 결과를 모니터에 표출함으로써 사용자에게 제공하는 표출단계;를 포함하는 것을 특징으로 한다.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Korean (KO)
Filing Language: Korean (KO)