컨볼루션 뉴럴 네트워크 기반의 딥러닝을 이용한 흉부 X-ray 영상의 분류 및 정확도 평가
본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5, 873장의 흉부 X-ray 영상에서 Normal 1, 583장, Pneumonia 4, 289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(ll%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2x2, Flatten layer, Image Data Generator로 구성하...
Saved in:
| Published in | 한국방사선학회 논문지 Vol. 14; no. 1; pp. 39 - 44 |
|---|---|
| Main Authors | , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | Korean |
| Published |
한국방사선학회
28.02.2020
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1976-0620 2384-0633 |
| DOI | 10.7742/jksr.2020.14.1.39 |
Cover
| Abstract | 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5, 873장의 흉부 X-ray 영상에서 Normal 1, 583장, Pneumonia 4, 289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(ll%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2x2, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 3x3, drop out 0.25, epoch 5, batch size 15, 손실함수 RMSprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다.
The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with Convolution Neural Network. Normal 1,583 and Pneumonia 4,289 were used in chest X-ray images. The data were classified as train (88.8%), validation (0.2%) and test (11%). Constructed as Convolution Layer, Max pooling layer size 2x2, Flatten layer, and Image Data Generator. The number of filters, filter size, drop out, epoch, batch size, and loss function values were set when the Convolution layer were 3 and 4 respectively. The test data verification results showed that the predicted accuracy was 94.67% when the number of filters was 64-128-128-128, filter size 3x3, drop out 0.25, epoch 5, batch size 15, and loss function RMSprop was 4. In this study, the classification of chest X-ray Normal and Pneumonia was predictable with high accuracy, and it is believed to be of great help not only to chest X-ray images but also to other medical images. |
|---|---|
| AbstractList | 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5, 873장의 흉부 X-ray 영상에서 Normal 1, 583장, Pneumonia 4, 289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(ll%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2x2, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 3x3, drop out 0.25, epoch 5, batch size 15, 손실함수 RMSprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다.
The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with Convolution Neural Network. Normal 1,583 and Pneumonia 4,289 were used in chest X-ray images. The data were classified as train (88.8%), validation (0.2%) and test (11%). Constructed as Convolution Layer, Max pooling layer size 2x2, Flatten layer, and Image Data Generator. The number of filters, filter size, drop out, epoch, batch size, and loss function values were set when the Convolution layer were 3 and 4 respectively. The test data verification results showed that the predicted accuracy was 94.67% when the number of filters was 64-128-128-128, filter size 3x3, drop out 0.25, epoch 5, batch size 15, and loss function RMSprop was 4. In this study, the classification of chest X-ray Normal and Pneumonia was predictable with high accuracy, and it is believed to be of great help not only to chest X-ray images but also to other medical images. 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5,873장의 흉부 X-ray 영상에서 Normal 1,583장, Pneumonia 4,289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(11%)로 분류하였다. Convolution Layer, Max pooling layer pool size 22, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 33, drop out 0.25, epoch 5, batch size 15, 손실함수 rmsprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상 뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다. The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with Convolution Neural Network. Normal 1,583 and Pneumonia 4,289 were used in chest X-ray images. The data were classified as train(88.8%), validation(0.2%) and test(11%). Constructed as Convolution Layer, Max pooling layer size 22, Flatten layer, and Image Data Generator. The number of filters, filter size, drop out, epoch, batch size, and loss function values were set when the Convolution layer were 3 and 4 respectively. The test data verification results showed that the predicted accuracy was 94.67% when the number of filters was 64-128-128-128, filter size 33, drop out 0.25, epoch 5, batch size 15, and loss function rmsprop was 4. In this study, the classification of chest X-ray Normal and Pneumonia was predictable with high accuracy, and it is believed to be of great help not only to chest X-ray images but also to other medical images. KCI Citation Count: 0 The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with Convolution Neural Network. Normal 1,583 and Pneumonia 4,289 were used in chest X-ray images. The data were classified as train (88.8%), validation (0.2%) and test (11%). Constructed as Convolution Layer, Max pooling layer size 2×2, Flatten layer, and Image Data Generator. The number of filters, filter size, drop out, epoch, batch size, and loss function values were set when the Convolution layer were 3 and 4 respectively. The test data verification results showed that the predicted accuracy was 94.67% when the number of filters was 64-128-128-128, filter size 3×3, drop out 0.25, epoch 5, batch size 15, and loss function RMSprop was 4. In this study, the classification of chest X-ray Normal and Pneumonia was predictable with high accuracy, and it is believed to be of great help not only to chest X-ray images but also to other medical images. 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5,873장의 흉부 X-ray 영상에서 Normal 1,583장, Pneumonia 4,289장을 사용하였다. 데이터 분류는 train(88.8%), validation(0.2%), test(11%)로 분류하였다. Convolution Layer, Max pooling layer pool size 2×2, Flatten layer, Image Data Generator로 구성하였다. Convolution layer가 3일 때와 4일 때 각각 filter 수, filter size, drop out, epoch, batch size, 손실함수 값을 설정하였다. test 데이터로 Convolution layer가 4일 때, filter 수 64-128-128-128, filter size 3×3, drop out 0.25, epoch 5, batch size 15, 손실함수 RMSprop으로 설정 시 정확도가 94.67%였다. 본 연구를 통해 높은 정확성으로 분류가 가능하였으며, 흉부 X-ray 영상뿐만 아니라 다른 의료영상에서도 많은 도움이 될 것으로 사료된다. |
| Author | 조흥준 Hyeon-jeong Kim 박세영 Se-young Park Heung-joon Jo 흥주완 김소영 송호준 Eun-byeol Lee So-young Kim 김현정 Joo-wan Hong 이은별 Ho-jun Song |
| Author_xml | – sequence: 1 fullname: 송호준 – sequence: 2 fullname: Ho-jun Song – sequence: 3 fullname: 이은별 – sequence: 4 fullname: Eun-byeol Lee – sequence: 5 fullname: 조흥준 – sequence: 6 fullname: Heung-joon Jo – sequence: 7 fullname: 박세영 – sequence: 8 fullname: Se-young Park – sequence: 9 fullname: 김소영 – sequence: 10 fullname: So-young Kim – sequence: 11 fullname: 김현정 – sequence: 12 fullname: Hyeon-jeong Kim – sequence: 13 fullname: 흥주완 – sequence: 14 fullname: Joo-wan Hong |
| BackLink | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002564436$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNo9kMtKI0EYhQtRMKM-gMymNi5m0W3duqp6GcTRqCBIFu6KTl-kbScZut24M0xcRIVsDMRLo6CCgouAQQR9Iqv6HWx1cPUd-D8Oh_8HGG-2miEAsxjZQjAyv51kqU0QQTZmNrapOwYqhEpmIU7pOKhgV_AyEzQJZrIsbiDKGedCsgrYNS93-vFVX9-ZgwHU3ZG-HEHduSkOn835cdF-gG_PQz0cmLy8ntzqywd9lJu8A00-Mmf3Rf8CFnlXP-3DTSv19qAZtM2_9qf91NG3JYY9aK76xWlf9zqw6HXfhvvTYCLydrJw5j-nQP33Yn1h2VpbX6otVNesRDJpBVL4LkENGmLfIQHHjsMl833Xc73AD0m53xVBhIUMiMdlJBgKuQxc3JBYNiJJp8Cvr9pmGqnEj1XLiz-51VJJqqob9ZriLqWUfbhzX24SZ7uxagbZjlqprq5_fBUJyYnDKeFO6f389jL1N43_eOmeokIgRhh9B7mXle0 |
| ContentType | Journal Article |
| DBID | HZB Q5X JDI ACYCR |
| DEWEY | 610 |
| DOI | 10.7742/jksr.2020.14.1.39 |
| DatabaseName | 한국학술정보 KISS Korean Studies Information Service System (KISS) B-Type KoreaScience Korean Citation Index |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| DocumentTitleAlternate | 컨볼루션 뉴럴 네트워크 기반의 딥러닝을 이용한 흉부 X-ray 영상의 분류 및 정확도 평가 Evaluation of Classification and Accuracy in Chest X-ray Images using Deep Learning with Convolution Neural Network |
| EISSN | 2384-0633 |
| EndPage | 44 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_6933348 JAKO202007862563265 3770424 |
| GroupedDBID | ALMA_UNASSIGNED_HOLDINGS HZB Q5X .UV JDI P5Y ACYCR KROLR |
| ID | FETCH-LOGICAL-k848-d87c920b3e1c52d6155684cc9a9adce278497df178d2a68f740e68d91b818bf83 |
| ISSN | 1976-0620 |
| IngestDate | Tue Nov 21 21:35:12 EST 2023 Fri Dec 22 12:03:55 EST 2023 Wed Feb 19 02:12:32 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Issue | 1 |
| Keywords | X-ray |
| Language | Korean |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-k848-d87c920b3e1c52d6155684cc9a9adce278497df178d2a68f740e68d91b818bf83 |
| Notes | The Korean Society of Radiology KISTI1.1003/JNL.JAKO202007862563265 http://data.doi.or.kr/10.7742/jksr.2020.14.1.39 |
| OpenAccessLink | http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202007862563265&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01 |
| PageCount | 6 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_6933348 kisti_ndsl_JAKO202007862563265 kiss_primary_3770424 |
| PublicationCentury | 2000 |
| PublicationDate | 20200228 |
| PublicationDateYYYYMMDD | 2020-02-28 |
| PublicationDate_xml | – month: 02 year: 2020 text: 20200228 day: 28 |
| PublicationDecade | 2020 |
| PublicationTitle | 한국방사선학회 논문지 |
| PublicationTitleAlternate | 한국방사선학회논문지 |
| PublicationYear | 2020 |
| Publisher | 한국방사선학회 |
| Publisher_xml | – name: 한국방사선학회 |
| SSID | ssib036466784 ssib010494110 ssib051116959 ssib012146256 ssib036279067 ssib039546180 |
| Score | 1.7271353 |
| Snippet | 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5, 873장의 흉부 X-ray 영상에서... The purpose of this study was learning about chest X-ray image classification and accuracy research through Deep Learning using big data technology with... 본 연구에서는 CNN과 빅데이터 기술을 이용한 Deep Learning을 통해 흉부 X-ray 영상 분류 및 정확성 연구에 대하여 알아보고자 한다. 총 5,873장의 흉부 X-ray 영상에서... |
| SourceID | nrf kisti kiss |
| SourceType | Open Website Open Access Repository Publisher |
| StartPage | 39 |
| SubjectTerms | Chest X-Ray CNN Deep Learning Pneumonia 딥러닝 원자력공학 폐렴 합성곱 신경망 네트워크 흉부 X-ray |
| Title | 컨볼루션 뉴럴 네트워크 기반의 딥러닝을 이용한 흉부 X-ray 영상의 분류 및 정확도 평가 |
| URI | https://kiss.kstudy.com/ExternalLink/Ar?key=3770424 http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202007862563265&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01 https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002564436 |
| Volume | 14 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | 한국방사선학회논문지, 2020, 14(1), 77, pp.39-44 |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2384-0633 dateEnd: 99991231 omitProxy: true ssIdentifier: ssib010494110 issn: 1976-0620 databaseCode: M~E dateStart: 20090101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1daxNBcKkVxBdRq1g_yiHuU0m979t93Lsk1Er1pULfjrtcIjWSSpo-6IO0GB-qQl8s1I9QQQsV-hCwlII--Ht6l__gzN4lOduCHy-5YXZ2dnbm7mbmsjtLyC0WajZE0U7BCjX8WsV5IcD_XC0rAP-EDtLAvcOz9-zpB-bMvDU_cupnbtXSciucqjw7cV_J_1gVcGBX3CX7D5YdMAUEwGBf-AULw-9f2ZiWPOq6VDBacqlrUNdDQBgS41FmUc4mEcU4dU0EeBmAFGVSAagiZYK6kpwD0pMYjQoPiGSDq0rmKrCSRMU-Tw4MrIynkAMzF5tTIoajSAgHBkBQwZE5B6GQeVFSccncpkydnC80g6dpJ4Yi4ASMDBiOirRyJmIwOZCNlWVHoSJ7ZM0lACKVU0mKEuJyTkCu5mPygVSy1aKimHFFgUEIXU7PkxpT-8TpXARoLNWm1Ve-l2lTOP1h4HaW3W0qNNmL9UnMIyRDbRVxBUpqVGbmSYCFq2baQ_Uf45LaysoEziyLCs1_34FkfrhfPnVJEDAWVFtXf_NZ5rFnM3VAaWWoLJRJK2sedZIQ8GPR3Uf1JayHq4PXNKe0qX7HfEHyI4HCYPnmjLh7H3tCeAnpsw0ZgHWKnNbBr-LhKbPPS_03uobVh3IBpobHyOvD6k0QPTk8d36AYZvw3hjunDa4Zdra0MNAdgCvFnkC4kAt6VIFnNTtY1OCOAvSsCVIPDEbW4D4sdGs5eLHufPkXJb4KSJ9ii-QkfriRXJmNlvaMkZayfed-NuP-PNO8nJTidf24q09JW5_6b06SD686a3uKocH3bi7mXSg9e12vLUbv-4knbaSdPaS9197Gx-VXmct3l9R5IOkJJuryYtVSb3fjrfh0l1Xkk8bvXcb8Xpb6a2vHXZXLpG5cmnOmy5kR6IU6sxkhYg5Fa6roVHVKpYe4ZoCm5mVCg94EFWquIiAO1FNc1ikBzarOaZatVnEtRDi8rDGjMtktLHYqF4hihUZeg0sEvJAM3moBoHJnGpkhTXd0UM9GCdjqDr_SVr0xjccB1dJjJMJqUq_ES099k-4EcbJTdCxX68s-Fi5Hq8PF_1604f8_I5vcwO3_l_9E5dr5OzwWbhORlvN5eoNiP5b4YS8wX4BvWnSYw |
| linkProvider | ISSN International Centre |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%EC%BB%A8%EB%B3%BC%EB%A3%A8%EC%85%98+%EB%89%B4%EB%9F%B4+%EB%84%A4%ED%8A%B8%EC%9B%8C%ED%81%AC+%EA%B8%B0%EB%B0%98%EC%9D%98+%EB%94%A5%EB%9F%AC%EB%8B%9D%EC%9D%84+%EC%9D%B4%EC%9A%A9%ED%95%9C+%ED%9D%89%EB%B6%80+X-ray+%EC%98%81%EC%83%81%EC%9D%98+%EB%B6%84%EB%A5%98+%EB%B0%8F+%EC%A0%95%ED%99%95%EB%8F%84+%ED%8F%89%EA%B0%80&rft.jtitle=%ED%95%9C%EA%B5%AD%EB%B0%A9%EC%82%AC%EC%84%A0%ED%95%99%ED%9A%8C+%EB%85%BC%EB%AC%B8%EC%A7%80&rft.au=%EC%86%A1%ED%98%B8%EC%A4%80&rft.au=%EC%9D%B4%EC%9D%80%EB%B3%84&rft.au=%EC%A1%B0%ED%9D%A5%EC%A4%80&rft.au=%EB%B0%95%EC%84%B8%EC%98%81&rft.date=2020-02-28&rft.issn=1976-0620&rft.volume=14&rft.issue=1&rft.spage=39&rft.epage=44&rft_id=info:doi/10.7742%2Fjksr.2020.14.1.39&rft.externalDBID=n%2Fa&rft.externalDocID=JAKO202007862563265 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1976-0620&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1976-0620&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1976-0620&client=summon |