磁共振脑结构成像大数据迁移学习在脑疾病中的应用
文献类型：学位论文
| 作者 | 鲁 彬; 鲁彬
|
| 答辩日期 | 2022-06 |
| 文献子类 | 博士 |
| 授予单位 | 中国科学院大学 |
| 授予地点 | 中国科学院心理研究所 |
| 其他责任者 | 严超赣 |
| 关键词 | 阿尔茨海默症 卷积神经网络 迁移学习 磁共振脑成像 性别差异 |
| 学位名称 | 理学博士 |
| 学位专业 | 认知神经科学 |
| 其他题名 | The application of transfer learning on brain illnesses using structural MRI |
| 中文摘要 | Magnetic resonance imaging (MRI) is a non-invasive radiation-free imagingtechnology. But beyond detecting brain lesions or tumors, comparatively little successhas been attained in identifying brain disorders such as Alzheimer’s disease (AD).Many machine learning algorithms to detect AD have been trained using limitedtraining data, meaning they often generalize poorly when applied to scans frompreviously unseen populations. While deep convolutional networks have shownexcellent performance on image-based classification tasks, their application to brainimaging is limited by the restricted sample size. As more and more MRI brain imagingdatabases become publicly available and deep learning excels in image classification,brain imaging big data combined with deep learning becomes a viable path for MRIbrain imaging to move further toward clinical applications. In the current study, a retrospective MRI dataset pooled from more than 217sites/scanners constituted the largest brain MRI sample to date (85,721 scans from50,876 participants) between January 2017 and August 2021. Next, a state-of-the-artdeep convolutional neural network, Inception-ResNet-V2, was built as a sex classifierwith high generalization capability. The sex classifier achieved 94.9% accuracy andserved as a base model in transfer learning for the objective diagnosis of AD. Theocclusion map showed that hypothalamus, superior vermis and pituitary played criticalroles in predicting sex. To explore the clinical implications of the brain gender classifier,we tested brain gender directly on a homosexual sample, in which 40% of homosexualfemales would be discriminated as brain males. It was a much higher misclassificationrate than the other samples, possibly reflecting some correlation between subjects'sexual orientation and structural brain variation. We then explored the potential of CNNs for the objective diagnosis of braindiseases. After transfer learning, the model fine-tuned for AD classification achieved91.3% accuracy in leave-sites-out cross-validation on the Alzheimer's DiseaseNeuroimaging Initiative (ADNI, 6,857 samples) dataset and 94.2%/93.6%/90.5%accuracy for direct tests on three unseen independent datasets (The Australian Imaging,Biomarkers & Lifestyle, AIBL, 669 samples / the Minimal Interval Resonance Imagingin Alzheimer's Disease cohort, MIRIAD, 644 samples / Open Access Series of ImagingStudies, OASIS, 1,123 samples). When this AD classifier was tested on brain imagesfrom unseen mild cognitive impairment (MCI) patients, MCI patients who finallyconverted to AD were 3 times more likely to be predicted as AD than MCI patients whodid not convert (65.2% vs 20.6%). Predicted scores from the AD classifier showedsignificant correlations with illness severity. The occlusion map for the AD classifierhighlighted that the hippocampus and parahippocampal gyrus - especially in the lefthemisphere - played unique roles in predicting AD. In sum, the proposed AD classifiercould offer a medical-grade marker that have potential to be integrated into ADdiagnostic practice. In addition, positron emission tomography (PET) with nuclearradiation is commonly used in the diagnosis of AD to assess cerebral metabolism. Theoutput score of our MRI-based AD classifier correlated with the 18F-AV45 PET SUVRvalue of 0.359 (p<0.001), which to some extent suggests the use of non-invasive,radiation-free MRI instead of PET for the assessment of AD. This offers the possibilityof using non-invasive and radiation-free MRI instead of PET scan with radiation in theassessment of AD. However, the pathology of psychiatric disorders such as MDD, ASD and SCZ isless clear than that of neurological disorder such as AD, the disease causes smallerstructural changes in the brain, and the disease is more heterogeneous, making it moredifficult to establish a disease prediction model based on magnetic resonance images.In addition, the brain disease database's other than AD are generally retrospective indesign, with relatively small data volume, more acquisition sites, and inconsistencies inmodels, sequences, and quality control. These factors lead to greater challenges in thegeneralizability of brain imaging-based classifiers for MDD, ASD, and SCZ. We usedhyperparameters obtained in AD transfer learning to attempt to construct diseaseclassifiers for MDD, ASD, and SCZ using transfer learning, in conjunction with datanormalization methods. For the MDD classifier, we used retrospectively designedshared data from the REST-meta-MDD data consortium of more than ten hospitalscontaining 1,300 MDD patients and 1,128 normal control subjects (NC). For the ASDand SCZ classifiers, we used prospectively designed study data from five hospitals andresearch units that were pre-serialized and harmonized, containing 234 ASD patients,186 SCZ patients, and 128 NC subjects. The results showed that MDD-NC, ASD-NC,SCZ-NC, and ASD-SCZ reached an average accuracy of 55.6%, 39.9%, 55.7%, and48.3% on cross-site validation, with AUCs of 0.562, 0.293, 0.553, and 0.527. We foundthat: 1. Disease classifiers for MDD, ASD, and SCZ performed inferiorly to ADclassifiers, which may reflect the influence of multiple factors such as sample size,disease heterogeneity, and different structural changes caused by disease; 2. Modelsusing random cross-validation performed much better than those using cross-site-validation (MDD-NC, ASD-NC, SCZ-NC, and ASD-SCZ achieved average accuracyof 69.3%, 68.8%, 77.8%, and 74.1% on random cross-validation, with AUCs of 0.770,0.670, 0.842, and 0.805), reflecting the importance of site-effects for classifiers basedon magnetic resonance brain imaging. And a truly clinically useful diagnostic aid mustrequire good generalizability, i.e., stable high-level performance across differentmodels and sequences. In addition, data standardization has a very important impact onimproving the cross-site prediction ability of models, but the common standardizationmethods in the field do not effectively improve the accuracy, although they can makethe brain imaging feature maps more satisfy the machine learning assumption ofindependent homogeneous distribution. These results raise new methodological issuesfor objective assisted diagnosis based on MR brain imaging, and the solution of theseissues in the future is expected to further promote the clinical application of MR brainimaging. In summary, this study applied and pooled almost all MRI brain imaging publicdatasets to construct a convolutional neural network brain image gender classifier withideal accuracy and generalizability; subsequently, the convolutional neural networkgender classifier was transferred to AD samples using transfer learning to achieve thepractical performance of AD prediction with the feasibility of objective brain imaging-based diagnosis of neurological diseases. The obtained hyperparameters were then used for further transferred to examine the possibility of their application in psychiatricdiseases, but the objective prediction of brain images of psychiatric diseases was notsuccessfully achieved, and further exploration was needed. |
| 英文摘要 | 磁共振成像 (Magnetic Resonance Imaging, MRI) 是一种非侵入性的、无辐射的成像技术，被广泛的应用于脑肿瘤等疾病的临床诊断上。然而，MRI 的临床应用在近年来进入了瓶颈期，MRI 在对脑肿瘤之外的如阿尔茨海默症 (Alzheimer’s Disease, AD) 、重性抑郁障碍 (Major Depression Disorder, MDD) 、孤独症谱系障碍 (Autism Spectrum Disorder, ASD) 、精神分裂症 (Schizophrenia, SCZ) 等脑疾病的临床辅助诊断上进展甚微。虽然深度卷积网络 (Convolutional NeuralNetwork, CNN) 在基于图像的分类任务上表现出卓越的性能，但是其在脑影像上的应用却受制于样本量上的不足。随着越来越多的磁共振脑成像数据库的公开和深度学习在图像分类上的卓越表现，结合深度学习的脑影像大数据成为了磁共振脑成像进一步走向临床应用的一条可行路径。 首先，我们汇集了 34 个数据集，构成了迄今为止最大的人脑结构磁共振图像样本 (来自 50,876 名参与者的 85,721 个样本) ，然后应用深度卷积神经网络Inception-ResNet-V2，构建了一个工业级的性别分类器。重要的是，我们使用了跨数据集交叉验证 (leave-dataset-out cross-validation) 而不是随机交叉验证。跨数据集交叉验证比随机交叉验证更加严格，可以完全避免测试集的站点信息泄露到训练集中，而大部分研究使用的随机交叉验证方法很可能夸大了结果的表现。使用跨站点交叉验证在站点效应非常强的基于磁共振成像分类器研究中非常必要。最终，我们的性别分类器在跨数据集的交叉验证中达到了 94.9%的准确率，即该模型可以用任何人从任何扫描仪得到的 MRI 结构脑成像数据对参与者的性别进行分类，准确率约为 95%。遮盖测试表明，下丘脑 (hypothalamus) 、小脑上蚓部(superior vermis) 和垂体 (pituitary)对性别分类器进行分类提供了最为重要的特征。为了探讨大脑性别分类器的临床意义，我们直接在同性恋样本上测试大脑性别，其中 40%的同性恋女性会被判别为大脑男性，误判率远高于其他样本，反映了被试性取向和脑结构变异之间存在一定的相关。然后，我们探索了 CNN 在客观诊断脑疾病方面的潜力。利用迁移学习，在AD 数据集进行了参数微调，在 Alzheimer's Disease Neuroimaging Initiative (ADNI)数据集上的跨站点五折交叉验证 (Leave-site-out five-fold cross-validation) 中，达到了 91.3%的准确率，在独立数据集 The Australian Imaging, Biomarkers & Lifestyle (AIBL)、the Minimal Interval Resonance Imaging in Alzheimer's Disease cohort(MIRIAD)、Open Access Series of Imaging Studies (OASIS) 上直接测试的准确率为 94.2%、93.6%和 90.5%。AD 分类器的输出分数同疾病严重程度存在显著的相关。AD 分类器可以一定程度上预测轻度认知障碍 (Mild Cognitive Impairment,MCI) 患者是否进展为AD，在MCI患者的大脑图像上直接测试该AD分类器时，65.2%进展为 AD 的 MCI 患者被预测为 AD，而只有 20.6%没有进展为 AD 的MCI 患者被预测为 AD。遮盖测试表明，双侧海马 (hippocampus) 和旁海马皮层(parahippocampal gyrus) 尤其是左半球部分对 AD 分类器进行分类提供了最为重要的特征。此外，AD 的诊断中常用有核辐射的正电子发射断层扫描 (positronemission tomography, PET) 评定大脑代谢，基于磁共振影像的 AD 分类器的输出分数与 18F-AV45 PET SUVR 值相关值为 0.359 (p < 0.001) ，这一定程度上为采用无创无辐射的磁共振影像代替有辐射的 PET 扫描在评定 AD 中的应用提供了可能。 但是，MDD、ASD 和 SCZ 等精神疾病的病理不如 AD 这样的神经疾病明确，疾病导致的脑结构变化更小，且疾病异质性更强，使得基于磁共振图像的疾病预测模型建立难度更大。我们使用在 AD 迁移学习中获得的超参数，使用迁移学习，配合数据标准化方法，尝试构造 MDD、ASD 和 SCZ 的疾病分类器。对于 MDD分类器，我们使用了来自十余家医院的 REST-meta-MDD 数据联盟的回顾性设计共享数据，包含 1300 名 MDD 患者和 1128 名正常对照被试 (normal control, NC) 。对于 ASD 和 SCZ 分类器，我们使用了来自五家医院和研究单位的预先进行过序列统一化处理的前瞻性设计研究数据，包含 234 名 ASD 患者、186 名 SCZ 患者和 128 名 NC 被试。结果显示，MDD-NC、ASD-NC、SCZ-NC 和 ASD-SCZ 跨站点交叉验证上平均正确率达到了 55.6%、39.9%、55.7%和 48.3%，AUC 达到了0.562、0.293、0.553 和 0.527。总体来说：1. MDD、ASD 和 SCZ 的疾病分类器表现逊于 AD 分类器，这可能反映了样本量、疾病异质性和疾病造成的结构改变等多种因素的影响；2. 使用随机交叉验证的模型表现要远远高于使用跨站点交叉验证 (MDD-NC、ASD-NC、SCZ-NC 和 ASD-SCZ 随机交叉验证上平均正确率达到了69.3%、68.8%、77.8%和74.1%，AUC达到了0.770、0.670、0.842和0.805) ，用于临床的辅助诊断工具必定是需要很好的可推广性，即在不同的机型和序列上都能有稳定的高水平表现。此外，数据标准化对于提升模型的跨站点预测能力具有非常重要的影响，但领域内常用标准化方法虽然可以使脑成像特征图更加满足独立同分布的机器学习假设，但并不能有效提高预测正确率。现有脑疾病数据库的一般为回顾型设计，数据量相对较小，采集站点较多，机型、序列、质控不一致。这些因素导致基于脑成像分类器的推广性受到非常严重的挑战。这些结果为基于磁共振脑成像的客观辅助诊断提出了新的的方法学问题，未来这些问题的解决有望进一步推动磁共振脑成像的临床应用。 综上，本研究申请和汇集了几乎所有磁共振脑成像公开数据集，构建了基于大数据的卷积神经网络脑影像性别分类器，具有理想的正确率和可推广性；随后利用迁移学习将卷积神经网络性别分类器迁移到 AD 样本上面，达到了 AD 预测的实用性效果，具有了神经疾病脑影像客观诊断的可行性；随后利用得到的超参数进行进一步迁移，考察其在精神疾病应用的可能性，但未能顺利解决精神疾病脑影像客观预测的目标，未来研究需要进一步探索。 |
| 语种 | 中文 |
| 源URL | [http://ir.psych.ac.cn/handle/311026/43162]  |
| 专题 | 心理研究所_认知与发展心理学研究室 |
| 推荐引用方式 GB/T 7714 | 鲁 彬,鲁彬. 磁共振脑结构成像大数据迁移学习在脑疾病中的应用[D]. 中国科学院心理研究所. 中国科学院大学. 2022. |
入库方式： OAI收割
来源：心理研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。