[논문]전산화 단층 촬영(Computed tomography, CT) 이미지에 대한 EfficientNet 기반 두개내출혈 진단 및 가시화 모델 개발

윤예빈; 김민건; 김지호; 강봉근; 김구태

doi:10.9718/jber.2021.42.4.150

전산화 단층 촬영(Computed tomography, CT) 이미지에 대한 EfficientNet 기반 두개내출혈 진단 및 가시화 모델 개발
Diagnosis and Visualization of Intracranial Hemorrhage on Computed Tomography Images Using EfficientNet-based Model 원문보기

Journal of biomedical engineering research : the official journal of the Korean Society of Medical & Biological Engineering, v.42 no.4, 2021년, pp.150 - 158

윤예빈 (한국뇌연구원) , 김민건 (지멘스헬시니어스) , 김지호 (한국뇌연구원) , 강봉근 (대구경북첨단의료산업진흥재단) , 김구태 (한국뇌연구원)

Abstract ▼ AI-Helper

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

주제어

표/그림 (8)

그림 그림 1. 데이터 분석 파이프라인 Fig. 1. Data analysis pipeline
그림 그림 2. 두개내출혈 CT 이미지 Fig. 2. CT images of ICH subtypes
표 표 1. 뇌 부위별 추천 window 값 Table 1. Recommended window values for the brain regions
그림 그림 3. 뇌 부위별 윈도우 값을 적용한 3 채널 데이터 세트 생성 과정 Fig. 3. Generating a 3-channel training dataset applying brain region-specific window levels
그림 그림 4. A. 두개내출혈 하위 유형별 모델의 진단 민감도(녹색)와 특이도(회색). B. 각 하위 유형 안에서 라벨 0(파란색), 1(주황색)의 비율 Fig. 4. A. Model sensitivity (green) and specificity (grey) for each of ICH subtypes. B. Label 0 (blue) and 1 (orange) ratio for each of ICH subtypes
표 표 2. 인공지능 학습 모델별 정확도 Table 2. Classification accuracy
표 표 3. 혼돈행렬 Table 3. Confusion matrix
그림 그림 5. Grad-CAM을 활용한 두개내출혈 병변 위치 시각화 Fig. 5. Visualization of ICH lesions using the Grad-CAM

참고문헌 (18)

Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthcare Journal, 2019;6(2):94-98.

상세보기
Liu GD, Li YC, Zhang W, Zhang L. A Brief Review of Artificial Intelligence Applications and Algorithms for Psychiatric Disorders. Engineering, 2020;6(4):462-467.

상세보기
Marietta M, Pedrazzi P, Girardis M, Torelli G. Intracerebral haemorrhage: An often neglected medical emergency. Internal and Emergency Medicine, 2007;2(1):38-45.

상세보기
Caceres JA, Goldstein JN. Intracranial Hemorrhage. Emergency Medicine Clinics of North America, 2012;30(3):771-794.

상세보기
Ye H, Gao F, Yin Y, Guo D, Zhao P, Lu Y, Wang X, Bai J, Cao K, Song Q, Zhang H, Chen W, Guo X, Xia J. Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network. European Radiology, 2019;29(11):6191-6201.

상세보기
Alfaro D, Levitt MA, English DK, Williams V, Eisenberg R. Accuracy of interpretation of cranial computed tomography scans in an emergency medicine residency program. Annals of Emergency Medicine, 1995;25(2):169-174.

상세보기
Lal NR, Murray UM, Eldevik OP, Desmond JS. Clinical consequences of misinterpretations of neuroradiologic CT scans by on-call radiology residents. AJNR. American Journal of Neuroradiology, 2000;21(1):124-129.
Strub WM, Leach JL, Tomsick T, Vagal A. Overnight Preliminary Head CT Interpretations Provided by Residents: Locations of Misidentified Intracranial Hemorrhage. American Journal of Neuroradiology, 2007;28(9):1679-1682.

상세보기
Arbabshirani MR, Plis S, Sui J, Calhoun VD. Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls. NeuroImage, 2017;145:137-165.

상세보기
He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. 2015;ArXiv:1512.03385 [Cs].
Tan M, Le QV. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. 2020;ArXiv:1905.11946 [Cs, Stat].
Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, Mahajan V, Rao P, Warier P. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet, 2018;392:2388-96.

상세보기
Alfidi RJ, Haaga J, Meaney TF, MacIntyre WJ, Gonzalez L, Tarar R, Zelch MG, Boller M, Cook SA, Jelden G. Computed tomography of the thorax and abdomen: a preliminary report. Radiology, 1975;117:257-264.

상세보기
Kim CH, Jung JI. Study for hounsfield units in computed tomogram with jaw lesion. J Korean Assoc Oral Maxillofac Surg, 2006;32:391-396.
Lin T, Goyal P, Girshick R, He K, Dollar P. Focal Loss for Dense Object Detection. 2017;arXiv:1708.02002.
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. International Journal of Computer Vision, 2020;128(2):336-359.

상세보기
Pope PE, Kolouri S, Rostami M, Martin CE, Hoffmann H. Explainability Methods for Graph Convolutional Neural Networks. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019;10764-10773.
Xie Q, Luong M, Hovy E, Le QV. Self-Training with Noisy Student Improves ImageNet Classification. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020;10687-10698.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증