슬라이스 선택 방식에 따른 딥러닝 알츠하이머 진단 분류 성능 분석
Performance analysis of deep learning-based Alzheimer disease classifiers with different slice selection methods
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
뇌 구조 자기공명영상 데이터로부터 알츠하이머 환자인지 아닌지 분류하는 작업은 알츠하이머 질환의 조기 발견을 위해 도움이 되는 진단 기법이고, 최근 들어 딥러닝을 이용하여 진단의 정확도를 높이는 연구가 많이 진행되고 있다. 3차원 영상으로부터 일부 슬라이스를 추출한 후 예측 모델 학습 및 검증을 진행하는 연구가 보고되고 있다. 본 논문에서는 슬라이스 선택 방식에 따른 차이가 뇌영상 알츠하이머 질환 딥러닝 분류의 성능에 어떤 영향을 주는지 비교 분석한다. Coronal 방향의 영상에서 세가지 방식을 비교한다. 엔트로피 순으로 선택하되 슬라이스 덩어리 별로 선택하지 않는 방식과 덩어리 별로 선택하는 방식, 그리고 그룹간 L2-norm 값이 큰 순으로 선택하되 덩어리 단위로 선택하는 방식을 비교한다. 5-fold 교차검증을 이용하여 모델 학습 및 검증을 수행한다. 딥러닝 모델로는 이미지넷 데이터로 사전 학습한 가중치를 갖는 4가지 딥러닝 모델과 사전 학습하지 않은 딥러닝 모델을 이용하여 학습한다. 검증 결과 엔트로피 기반 방식이 L2-norm 차이 기반의 방식에 비해 구현이 간단하면서도, 비슷한 예측 성능을 보여주고 있다.
Abstract
The classification of Alzheimer patients vs. normals based on brain structural MRI data is helpful for early diagnosis of Alzheimer’s disease. Recently, numerous research studies investigated deep learning to improve diagnostic accuracy. Several research groups proposed methods for selecting slices from the 3D MRI data and utilized the selected slices as input to model training and validation. This paper addresses the effect of slice selection methods on deep learning classifiers’ performances in predicting Alzheimer’s disease. From the coronal slice orientation, we compared three slice selection methods: Entropy-based method without chunk selection and with chunk selection, and L2-norm-based method with chuck selection. Model development and validation were performed with a five-fold cross validation. We considered four deep convolutional neural network (CNN) models pretrained with ImageNet database as well as one deep CNN model without pretraining. Our results indicate that the entropy-based slice selection method is simpler than the L2-norm-based method in its implementation, and it produces performance similar to the L2-norm-based method.
참고문헌 (24)
- G. Livingston et al., "Dementia prevention, intervention, and care : 2020 report of the Lancet Commission", Lancet, 396, pp.413~446 (2020)
- D. Lee, "The prevalence of dementia in older people in an urban population of Korea : the Seoul study", J Am Geriatr Soc, 50(7), pp.1233~1239 (2002)
- M. DeTure, "The neuropathological diagnosis of Alzheimer's disease", Molecular Neurodegeneration, 14, pp.32~ (2019)
- J. Park, "Burden of disease due to dementia in the elderly population of Korea : present and future", BMC Public Health, 13, pp.293~ (2013)
- 김보민, "휴대용 fNIRS를 이용한 머신러닝 기반의 알츠하이머병 진단 기술 연구", 한국통신학회논문지, 46(7), pp.1185~1198 (2021), 한국통신학회[DOI]
- H. Yu, "Supervised Network-Based Fuzzy Learning of EEG Signals for Alzheimer's Disease Identification", IEEE T Fuzzy Syst, 28(1), pp.60~71 (2020)
- S. Suppiah, "The Who. When. Why. and How of PET Amyloid Imaging in Management of Alzheimer's Disease-Review of Literature and Interesting Images", Diagnostics., 9(2), pp.65~ (2019)
- 최린, "알츠하이머병 환자의 전반적 피질 위축, 내측두엽 위축, 백질 고강도 신호와 인지기능의 연관성", 생물정신의학, 22(3), pp.140~148 (2015), 대한생물정신의학회
- W. Henneman, "Hippocampal atrophy rates in Alzheimer disease: added value over whole brain volume measures", Neurology, 72(11), pp.999~1007 (2009)
- 알람 사루알, "Alzheimer disease classification by combination of SRAN, Linear SVM, PCA, and VBM", 한국차세대컴퓨팅학회 논문지, 11(4), pp.37~46 (2015), 한국차세대컴퓨팅학회
- D. Jha, "Diagnosis of Alzheimer's Disease Using Dual-Tree Complex Wavelet Transform. PCA. and Feed-Forward Neural Network", J. Healthc. Eng., pp.9060124~ (2017)
- Y. Zhang, "Detection of subjects and brain regions related to Alzheimer's disease using 3D MRI scans based on eigenbrain and machine learning", Front. Comput. Neurosci., 9, pp.66~ (2015)
- B. Lee, "Using deep CNN with data permutation scheme for classification of Alzheimer's disease in structural magnetic resonance imaging (sMRI)", IEICE TRANSACTIONS on Information and Systems, 102(7), pp.1384~1395 (2019)
- M. Raza, "Diagnosis and monitoring of Alzheimer's patients using classical and deep learning techniques", Expert. Syst. Appl., 136, pp.353~364 (2019)
- L. Fulton, "Classification of Alzheimer's Disease with and without Imagery using Gradient Boosted Machines and ResNet-50", Brain Sci, 9(9), pp.212~ (2019)
- J. Islam, "Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks", Brain Informatics, 5, pp.2~ (2018)
- D. Marcus, "Open access series of imaging studies : longitudinal MRI data in nondemented and demented older adults", J Cogn Neurosci, 22(12), pp.2677~2684 (2010)
- M. Tan. Q. Le, "EfficientNet : Rethinking Model Scaling for Convolutional Neural Networks", Pr Mach Learn Res, 97 (2019)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv : 1409. 1556, ~ (2014)
- K. He, "Identity Mappings in Deep Residual Networks", Lect Notes Comput Sc, 998, pp.630~645 (2016)
- A Howard, "Mobilenets : Efficient convolutional neural networks for mobile vision applications", arXiv preprint arXiv : 1704. 04861, ~ (2017)
- J. Deng, "ImageNet : A Large-Scale Hierarchical Image Database", Proc CVPR IEEE, pp.248~255 (2009)
- S. Basaia, "Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks", Neuroimage Clin, 21, pp.101645~ (2019)
- C. R Jack Jr et al., "The Alzheimer's Disease Neuroimaging Initiative (ADNI): MRI methods", J Magn Reson Imaging, 27(4), pp.685~691 (2008)