Cost-Sensitive Meta-learning for Progress Prediction of Subjective Cognitive Decline with Brain Structural MRI

Subjective cognitive decline (SCD) is a preclinical phase of Alzheimer’s disease (AD) which occurs before the deficits could be detected by cognitive tests. It is highly desired to predict the progress of SCD for possible intervention of AD-related cognitive decline. Many neuroimaging-based methods have been developed for AD diagnosis, but there are few studies devoted to automated progress prediction of SCD due to the limited number of SCD subjects. Even though some studies proposed to transfer models (trained on AD/MCI) to SCD analysis, the significant domain shift between their data distributions may degrade the prediction performance. To this end, this paper tackles the problem of learning a model from the source data for which can directly generalize to an unseen target domain for SCD prediction. We propose a cost-sensitive meta-learning scheme to simultaneously improve the model generalization and its sensitivity in MRI-based SCD detection. During training, the source domain is divided into virtual meta-train and meta-test sets to explicitly simulate the scenario for early-stage detection of AD. Considering the importance of sensitivity for progressive status detection, we further introduce cost-sensitive learning to enhance the meta-optimization process by encouraging the model to gain higher sensitivity for SCD detection with simulated domain shift. Experiments conducted on the large-scale ADNI dataset and a small-scale SCD dataset have demonstrated the effectiveness of the proposed method.

[1]  Jitendra Malik,et al.  Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection , 2018, MICCAI.

[2]  Yuanyuan Qin,et al.  Detecting Alzheimer's Disease on Small Dataset: A Knowledge Transfer Perspective , 2019, IEEE Journal of Biomedical and Health Informatics.

[3]  Parashkev Nachev,et al.  Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning , 2019, DART/MIL3ID@MICCAI.

[4]  Ayman El-Baz,et al.  Alzheimer's disease diagnostics by adaptation of 3D convolutional network , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[5]  Yongxin Yang,et al.  Learning to Generalize: Meta-Learning for Domain Generalization , 2017, AAAI.

[6]  Dinggang Shen,et al.  Identifying Autism Spectrum Disorder With Multi-Site fMRI via Low-Rank Domain Adaptation , 2020, IEEE Transactions on Medical Imaging.

[7]  C. Smart,et al.  Subjective Cognitive Decline in Preclinical Alzheimer's Disease. , 2017, Annual review of clinical psychology.

[8]  D. Shen,et al.  Prediction of 7‐year's conversion from subjective cognitive decline to mild cognitive impairment , 2020, Human brain mapping.

[9]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[10]  Reisa A. Sperling,et al.  Subjective cognitive complaints and amyloid burden in cognitively normal older individuals , 2012, Neuropsychologia.

[11]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[12]  F. Jessen,et al.  AD dementia risk in late MCI, in early MCI, and in subjective memory impairment , 2014, Alzheimer's & Dementia.

[13]  Han Zhang,et al.  Prediction of 7‐year's conversion from subjective cognitive decline to mild cognitive impairment , 2020, medRxiv.

[14]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[15]  Daoqiang Zhang,et al.  Domain Transfer Learning for MCI Conversion Prediction , 2015, IEEE Transactions on Biomedical Engineering.

[16]  Nick C Fox,et al.  The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods , 2008, Journal of magnetic resonance imaging : JMRI.

[17]  Dinggang Shen,et al.  Landmark‐based deep multi‐instance learning for brain disease diagnosis , 2018, Medical Image Anal..

[18]  Victor S. Sheng,et al.  Cost-Sensitive Learning and the Class Imbalance Problem , 2008 .

[19]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[20]  Dinggang Shen,et al.  Multi-site MRI harmonization via attention-guided deep domain adaptation for brain disorder identification , 2021, Medical Image Anal..

[21]  Ismail Ben Ayed,et al.  Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images , 2020, MICCAI.

[22]  Dinggang Shen,et al.  Joint Neuroimage Synthesis and Representation Learning for Conversion Prediction of Subjective Cognitive Decline , 2020, MICCAI.

[23]  Daoqiang Zhang,et al.  Domain Transfer Learning for MCI Conversion Prediction , 2012, MICCAI.

[24]  Yichen Wei,et al.  Self-weighted Multi-task Learning for Subjective Cognitive Decline Diagnosis , 2020, MICCAI.

[25]  Vince D. Calhoun,et al.  An ensemble learning system for a 4-way classification of Alzheimer’s disease and mild cognitive impairment , 2018, Journal of Neuroscience Methods.

[26]  Nico Karssemeijer,et al.  Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation , 2017, MICCAI.

[27]  Andrew J. Saykin,et al.  A conceptual framework for research on subjective cognitive decline in preclinical Alzheimer's disease , 2014, Alzheimer's & Dementia.

[28]  Christian Wachinger,et al.  Domain adaptation for Alzheimer's disease diagnostics , 2016, NeuroImage.

[29]  Yulia Dodonova,et al.  Residual and plain convolutional neural networks for 3D brain MRI classification , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).