北京生物醫(yī)學工程

腦部 PET 圖像在阿爾茨海默病早期診斷中的應用

Application of brain PET images in the early diagnosis of Alzheimer's disease

作者：林萬云杜民

單位：福州大學物理與信息工程學院（福州　350108 ）福州大學福建省醫(yī)療器械和醫(yī)藥技術重點實驗室（福州　350108 ）

關鍵詞：阿爾茨海默病； ADNI數(shù)據(jù)庫； PET圖像； MR圖像； 3D CNN；早期診斷

分類號：R318

出版年·卷·期（頁碼）：2021·40·2（174-180）

摘要：

目的本研究使用腦部正電子發(fā)射型計算機斷層顯像（positron emission tomography, PET），并且設計了一個3D 卷積神經網(wǎng)絡（convolutional neural networks, CNN），以實現(xiàn)對阿爾茨海默病（Alzheimer disease, AD）的早期診斷。方法研究數(shù)據(jù)取自美國國立衛(wèi)生研究院老年研究所的ADNI (Alzheimer’s Disease Neuroimaging Initiative)數(shù)據(jù)庫，PET圖像和磁共振（magnetic resonance，MR）圖像均有收集并對數(shù)據(jù)進行相關預處理。為避免過早的下采樣給模型性能帶來不利的影響，設計了一個3D CNN模型，比較兩種不同模態(tài)的數(shù)據(jù)在AD早期診斷中各自的優(yōu)缺點。結果使用本研究組設計的3D CNN模型在基于PET圖像的AD早期診斷實驗中，預測準確率、敏感度、特異度以及曲線下面積（area under curve，AUC）分別達到71.19%、79.29%、61.35%、71.09%，各項指標均大于使用相同模型但是使用MRI圖像時的實驗結果。此外，對本研究組的模型與計算機視覺中的經典模型VGG和ResNet使用相同數(shù)據(jù)進行對比實驗，在許多評價指標上都要優(yōu)于這兩個對比模型。結論使用腦部PET圖像并結合3D CNN可以更好的利用3D圖像的空間位置信息，更有效的提取特征，能對AD早期的病變情況有更準確高效的識別，有助于及時發(fā)現(xiàn)疾病并采取措施減緩病情，降低發(fā)病概率或推遲發(fā)病時間。

Objective In this study, we used positron emission tomography (PET) of the brain and designed a 3D convolutional neural networks (CNN) to achieve early diagnosis of Alzheimer's disease (AD). Methods Data were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Both PET images and magnetic resonance (MR) images were collected and preprocessed. In order to avoid premature downsampling from affecting the model performance. We designed a 3D CNN model to compare the advantages and disadvantages of two different modal data in the early diagnosis of AD. Results Using our designed 3D CNN model in the early diagnosis experiment of AD based on PET images, the prediction accuracy, sensitivity, specificity and the area under curve (AUC) reached 71.19%, 79.29%, 61.35% and 71.09%, respectively. All indicators are greater than the experimental results when using the same model but using MRI images. Compared with VGG and ResNet, our model is better than these two models in many evaluation indicators. Conclusions Combining brain PET images and 3D CNN can make better use of the spatial position information of 3D images, extract features more effectively, and can more accurately and efficiently identify the pathological changes in the early stage of AD, which is helpful for timely detection of diseases. It can slow down the disease, reduce the probability of disease and delay the time of disease.

參考文獻：

[1]?Burns A, Iliffe S.?Alzheimer’s disease [J]. BMJ, 2009, 338:?b158.

[2]?GBD 2015 Disease and Injury Incidence and Prevalence Collaborators.?Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990-2015: A systematic analysis for the Global Burden of Disease Study 2015[J]. The Lancet, 2016, 388(10053):1545-1602.

[3]?Teipel SJ, Grothe M, Lista S, et al. Relevance of Magnetic Resonance Imaging for Early Detection and Diagnosis of Alzheimer Disease[J].?The Medical Clinics of North America, 2013, 97(3):399-424.

[4]?Dubois B, Feldman H H, Jacova C, et al. Research criteria for the diagnosis of Alzheimer's disease: revising the NINCDS–ADRDA criteria[J]. The Lancet Neurology, 2007, 6(8): 734-746.

[5]?林偉銘,袁江南,馮陳偉,等.基于極限學習機的阿爾茲海默病輔助診斷[J].中國生物醫(yī)學工程學報,2020,39(3):288-294.

Lin WM, Yuan JN, Feng CW,?et al. Computer-aided diagnosis of Alzheimer's disease based on extreme learning machine [J]. Chinese Journal of Biomedical Engineering,2020,39(3):?288-294.

[6]?陳斯鵬,高妮,田思佳,等.基于MR圖像紋理特征的阿爾茨海默病分類模型[J].北京生物醫(yī)學工程, 2017, 36(2): 134-138.

Chen SP, Gao N, Tian SJ, et?al. Classification model for Alzheimer disease based on texture features of MR images [J]. Beijing Biomedical Engineering, 2017,?36(2):?134-138.

[7]?Farooq A, Anwar S, Awais M, et al. A deep CNN based multi-class classification of Alzheimer's disease using MRI[C]//?2017 IEEE International Conference on Imaging systems and techniques (IST). Beijing: IEEE?Press, 2017: 1-6.

[8]?林偉銘, 高欽泉, 杜民. 卷積神經網(wǎng)絡診斷阿爾茲海默癥的方法[J]. 計算機應用, 2017, 37(12):3504-3508.

Lin WM, Gao QQ, Du M. Convolutional neural network based method for diagnosis of Alzheimer's disease [J].?Journal of Computer Applications,?2017,?37(12):?3504-3508.

[9]?Lin W, Tong T, Gao Q, et al. Convolutional neural networks-based MRI image analysis for the Alzheimer's disease prediction from mild cognitive impairment[J]. Frontiers in Neuroscience, 2018, 12:?777.

[10]?Tong T, Wolz R, Gao Q, et al. Multiple instance learning for classification of dementia in brain MRI[J]. Medical Image Analysis, 2014, 18(5):808-818.

[11]?Zhang J, Gao Y, Gao Y, et al. Detecting anatomical landmarks for fast Alzheimer's disease diagnosis[J]. IEEE Transactions on Medical Imaging, 2016, 35(12):?2524-2533.

[12]?Huang Y, Xu J, Zhou Y, et al. Diagnosis of Alzheimer’s disease via multi-modality 3D convolutional neural network[J]. Frontiers in Neuroscience, 2019, 13: 509.

[13]?Zu C, Jie B, Liu M, et al. Label-aligned multi-task feature learning for multimodal classification of Alzheimer's disease and mild cognitive impairment[J]. Brain Imaging and?Behavior, 2016, 10(4):1148-1159.

[14]?Zhuang X, Arridge S, Hawkes DJ, et al. A nonrigid registration framework using spatially encoded mutual information and free-form deformations[J]. IEEE Transactions on Medical Imaging, 2011, 30(10):?1819-1828.

[15]?Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks[C]// 25th International Conference on?Neural Information Processing Systems. Red Hook, NY :?Curran?Associates,?Inc. , 2012,1: 1097-1105.

[16]?Simonyan K, Zisserman A.?Very deep convolutional networks for large-scale image recognition[C/OL]//?the 3rd International Conference on Learning Representations (ICLR 2015). [2020-11-20]. https://arxiv.org/pdf/1409.1556.pdf.?????????????????

[17]?He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//?2016 IEEE Conference on Computer Vision and Pattern Recognition. ?Las Vegas, NV:?IEEE?Press, 2016: 770-778.

[18]?Kingma DP,?Ba?JL. Adam: a method for stochastic optimization[C/OL]// the 3rd International Conference on Learning Representations (ICLR 2015).?[2020-11-20]. ?https://arxiv.org/pdf/1412.6980.pdf.

[19]?Wen J, Thibeau-Sutre E, Diaz-Melo M, et al. Convolutional neural networks for classification of Alzheimer's disease: overview and reproducible evaluation[J]. Medical Image Analysis, 2020, 63: 101694.

[20]?B?ckstr?m K, Nazari M, Gu IYH, et al. An efficient 3D deep convolutional network for Alzheimer's disease diagnosis using MR images[C]//?2018 IEEE 15th International Symposium on Biomedical Imaging. Washington, DC: IEEE?Press,?2018:149-153.

[21]?Coimbra A, Williams DS, Hostetler ED. The role of MRI and PET/SPECT in Alzheimer's disease[J]. Current Topics in Medicinal Chemistry, 2006, 6(6): 629-647.

[22]?Lin W. Synthesizing Missing Data using 3D Reversible GAN for Alzheimer's Disease[C]// ?Proceedings of the 2020 International Symposium on Artificial Intelligence in Medical Sciences. 2020: 208-213.

Marcus C, Mena E, Subramaniam RM. Brain PET in the diagnosis of Alzheimer’s disease[J]. Clinical Nuclear Medicine, 2014, 39(10): e413-e422.

服務與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频