Predicting diagnosis 4 years prior to Alzheimer's disease incident

Deep learning combining FDG-PET and neurocognitive data accurately predicts MCI conversion to Alzheimer's dementia 3-year post MCI diagnosis

INTRODUCTION

This study reports a novel deep learning approach to predict mild cognitive impairment (MCI) conversion to Alzheimer's dementia (AD) within three years using whole-brain fluorodeoxyglucose (FDG) positron emission tomography (PET) and cognitive scores (CS).

METHODS

This analysis consisted of 150 normal controls (CN), 257 MCI, and 205  AD subjects from ADNI. FDG-PET and CS were obtained at MCI diagnosis to predict AD conversion within three years of MCI diagnosis using convolutional neural networks.

RESULTS

Neurocognitive scores predicted better than FDG-PET per se, but the best model was a combination of FDG-PET, age, and neurocognitive data, yielding an AUC of 0.785 ± 0.096 and a balanced accuracy of 0.733 ± 0.098. Saliency maps highlighted putamen, thalamus, inferior frontal gyrus, parietal operculum, precuneus cortices, calcarine cortices, temporal gyrus, and planum temporale to be important for prediction.

DISCUSSION

Deep learning accurately predicts MCI conversion to AD and provides neural correlates of brain regions associated with AD conversion.

Prediction of MCI-to-AD progression with atrophy-weighted standard uptake value ratios of 18 F-Florbetapir PET

Accurate prediction of MCI-to-AD progression is an important yet challenging task. We introduce a new quantitative parameter: the atrophy-weighted standard uptake value ratio (awSUVR), defined as the PET SUVR divided by the hippocampal volume measured with MR, and evaluate whether it may provide better prediction of the MCI-to-AD progression.

MATERIALS AND METHODS

We used ADNI data to evaluate the prediction performances of the awSUVR against SUVR. 571, 363 and 252 18-F-Florbetaipir scans were selected based on criteria of conversion at the third, fifth and seventh year after the PET scans, respectively. Corresponding MR scans were segmented with Freesurfer and applied on PET for SUVR and awSUVR computation. We also searched for the optimal combination of target and reference regions. In addition to evaluating the overall prediction performances, we also evaluated the prediction for APOE4 carriers and non-carriers. For the scans with false predictions, we used 18-F-Flortaucipir scans to investigate the potential source of error.

RESULTS

awSUVR provides more accurate prediction than the SUVR in all three progression criteria. The 5-year prediction accuracy/sensitivity/specificity is 90/81/93% for awSUVR and 86/81/88% for SUV. awSUVR also yields good 3- and 7-year prediction accuracy/sensitivity/specificity of 91/57/96 and 92/89/93, respectively. APOE4 carriers generally are slightly more difficult to predict for the progression. False negative prediction is found to either due to a near-cutoff mis-classification or potentially non-AD dementia pathology. False positive prediction is mainly due to the slightly delayed progression than the expected progression time.

CONCLUSION

We demonstrated with ADNI data that 18-F-Florbetapir SUVR weighted with hippocampus volume may provide good prediction power with over 90% accuracy in MCI-to-AD progression.

A review of the application of three-dimensional convolutional neural networks for the diagnosis of Alzheimer's disease using neuroimaging

Alzheimer's disease (AD) is a degenerative disorder that leads to progressive, irreversible cognitive decline. To obtain an accurate and timely diagnosis and detect AD at an early stage, numerous approaches based on convolutional neural networks (CNNs) using neuroimaging data have been proposed. Because 3D CNNs can extract more spatial discrimination information than 2D CNNs, they have emerged as a promising research direction in the diagnosis of AD. The aim of this article is to present the current state of the art in the diagnosis of AD using 3D CNN models and neuroimaging modalities, focusing on the 3D CNN architectures and classification methods used, and to highlight potential future research topics. To give the reader a better overview of the content mentioned in this review, we briefly introduce the commonly used imaging datasets and the fundamentals of CNN architectures. Then we carefully analyzed the existing studies on AD diagnosis, which are divided into two levels according to their inputs: 3D subject-level CNNs and 3D patch-level CNNs, highlighting their contributions and significance in the field. In addition, this review discusses the key findings and challenges from the studies and highlights the lessons learned as a roadmap for future research. Finally, we summarize the paper by presenting some major findings, identifying open research challenges, and pointing out future research directions.

Handgrip Strength Is Related to Hippocampal and Lobar Brain Volumes in a Cohort of Cognitively Impaired Older Adults with Confirmed Amyloid Burden

BACKGROUND

Strength and mobility are essential for activities of daily living. With aging, weaker handgrip strength, mobility, and asymmetry predict poorer cognition. We therefore sought to quantify the relationship between handgrip metrics and volumes quantified on brain magnetic resonance imaging (MRI).

OBJECTIVE

To model the relationships between handgrip strength, mobility, and MRI volumetry.

METHODS

We selected 38 participants with Alzheimer's disease dementia: biomarker evidence of amyloidosis and impaired cognition. Handgrip strength on dominant and non-dominant hands was measured with a hand dynamometer. Handgrip asymmetry was calculated. Two-minute walk test (2MWT) mobility evaluation was combined with handgrip strength to identify non-frail versus frail persons. Brain MRI volumes were quantified with Neuroreader. Multiple regression adjusting for age, sex, education, handedness, body mass index, and head size modeled handgrip strength, asymmetry and 2MWT with brain volumes. We modeled non-frail versus frail status relationships with brain structures by analysis of covariance.

RESULTS

Higher non-dominant handgrip strength was associated with larger volumes in the hippocampus (p = 0.02). Dominant handgrip strength was related to higher frontal lobe volumes (p = 0.02). Higher 2MWT scores were associated with larger hippocampal (p = 0.04), frontal (p = 0.01), temporal (p = 0.03), parietal (p = 0.009), and occipital lobe (p = 0.005) volumes. Frailty was associated with reduced frontal, temporal, and parietal lobe volumes.

CONCLUSION

Greater handgrip strength and mobility were related to larger hippocampal and lobar brain volumes. Interventions focused on improving handgrip strength and mobility may seek to include quantified brain volumes on MR imaging as endpoints.

Breaking bad news in the era of artificial intelligence and algorithmic medicine: an exploration of disclosure and its ethical justification using the hedonic calculus

An appropriate ethical framework around the use of Artificial Intelligence (AI) in healthcare has become a key desirable with the increasingly widespread deployment of this technology. Advances in AI hold the promise of improving the precision of outcome prediction at the level of the individual. However, the addition of these technologies to patient-clinician interactions, as with any complex human interaction, has potential pitfalls. While physicians have always had to carefully consider the ethical background and implications of their actions, detailed deliberations around fast-moving technological progress may not have kept up. We use a common but key challenge in healthcare interactions, the disclosure of bad news (likely imminent death), to illustrate how the philosophical framework of the 'Felicific Calculus' developed in the eighteenth century by Jeremy Bentham, may have a timely quasi-quantitative application in the age of AI. We show how this ethical algorithm can be used to assess, across seven mutually exclusive and exhaustive domains, whether an AI-supported action can be morally justified.

A Precise Computational Method for Hippocampus Segmentation from MRI of Brain to Assist Physicians in the Diagnosis of Alzheimer’s Disease

Hippocampus segmentation on magnetic resonance imaging is more significant for diagnosis, treatment and analyzing of neuropsychiatric disorders. Automatic segmentation is an active research field. Previous state-of-the-art hippocampus segmentation methods train their methods on healthy or Alzheimer’s disease patients from public datasets. It arises the question whether these methods are capable for recognizing the hippocampus in a different domain. Therefore, this study proposes a precise computational method for hippocampus segmentation from MRI of brain to assist physicians in the diagnosis of Alzheimer’s disease (HCS-MRI-DAD-LBP). Initially, the input images are pre-processed by Trimmed mean filter for image quality enhancement. Then the pre-processed images are given to ROI detection, ROI detection utilizes Weber’s law which determines the luminance factor of the image. In the region extraction process, Chan–Vese active contour model (ACM) and level sets are used (UACM). Finally, local binary pattern (LBP) is utilized to remove the erroneous pixel that maximizes the segmentation accuracy. The proposed model is implemented in MATLAB, and its performance is analyzed with performance metrics, like precision, recall, mean, variance, standard deviation and disc similarity coefficient. The proposed HCS-MRI-DAD-LBP method attains in OASIS dataset provides high disc similarity coefficient of 12.64%, 10.11% and 1.03% compared with the existing methods, like HCS-DAS-MLT, HCS-DAS-RNN and HCS-DAS-GMM and in ADNI dataset provides high precision of 20%, 9.09% and 1.05% compared with existing methods like HCS-MRI-DAD-CNN-ADNI, HCS-MRI-DAD-MCNN-ADNI and HCS-MRI-DAD-CNN-RNN-ADNI, respectively.

An MRI Scans-Based Alzheimer's Disease Detection via Convolutional Neural Network and Transfer Learning

Alzheimer’s disease (AD) is the most common type (>60%) of dementia and can wreak havoc on the psychological and physiological development of sufferers and their carers, as well as the economic and social development. Attributed to the shortage of medical staff, automatic diagnosis of AD has become more important to relieve the workload of medical staff and increase the accuracy of medical diagnoses. Using the common MRI scans as inputs, an AD detection model has been designed using convolutional neural network (CNN). To enhance the fine-tuning of hyperparameters and, thus, the detection accuracy, transfer learning (TL) is introduced, which brings the domain knowledge from heterogeneous datasets. Generative adversarial network (GAN) is applied to generate additional training data in the minority classes of the benchmark datasets. Performance evaluation and analysis using three benchmark (OASIS-series) datasets revealed the effectiveness of the proposed method, which increases the accuracy of the detection model by 2.85−3.88%, 2.43−2.66%, and 1.8−40.1% in the ablation study of GAN and TL, as well as the comparison with existing works, respectively.