Extraction of sulcal medial surface and classification of Alzheimer's disease using sulcal features

Deep Learning for Alzheimer's Disease Prediction: A Comprehensive Review

Alzheimer's disease (AD) is a neurological disorder that significantly impairs cognitive function, leading to memory loss and eventually death. AD progresses through three stages: early stage, mild cognitive impairment (MCI) (middle stage), and dementia. Early diagnosis of Alzheimer's disease is crucial and can improve survival rates among patients. Traditional methods for diagnosing AD through regular checkups and manual examinations are challenging. Advances in computer-aided diagnosis systems (CADs) have led to the development of various artificial intelligence and deep learning-based methods for rapid AD detection. This survey aims to explore the different modalities, feature extraction methods, datasets, machine learning techniques, and validation methods used in AD detection. We reviewed 116 relevant papers from repositories including Elsevier (45), IEEE (25), Springer (19), Wiley (6), PLOS One (5), MDPI (3), World Scientific (3), Frontiers (3), PeerJ (2), Hindawi (2), IO Press (1), and other multiple sources (2). The review is presented in tables for ease of reference, allowing readers to quickly grasp the key findings of each study. Additionally, this review addresses the challenges in the current literature and emphasizes the importance of interpretability and explainability in understanding deep learning model predictions. The primary goal is to assess existing techniques for AD identification and highlight obstacles to guide future research.

An MRI Study of Morphology, Asymmetry, and Sex Differences of Inferior Precentral Sulcus

Numerous studies utilizing magnetic resonance imaging (MRI) have observed sex and interhemispheric disparities in sulcal morphology, which could potentially underpin certain functional disparities in the human brain. Most of the existing research examines the precentral sulcus comprehensively, with a rare focus on its subsections. To explore the morphology, asymmetry, and sex disparities within the inferior precentral sulcus (IPCS), we acquired 3.0T magnetic resonance images from 92 right-handed Chinese adolescents. Brainvisa was used to reconstruct the IPCS structure and calculate its mean depth (MD). Based on the morphological patterns of IPCS, it was categorized into five distinct types. Additionally, we analyzed four different types of spatial relationships between IPCS and inferior frontal sulcus (IFS). There was a statistically significant sex disparity in the MD of IPCS, primarily observed in the right hemisphere. Females exhibited significantly greater asymmetry in the MD of IPCS compared to males. No statistically significant sex or hemispheric variations were identified in sulcal patterns. Our findings expand the comprehension of inconsistencies in sulcal structure, while also delivering an anatomical foundation for the study of related regions' function.

Depth- and curvature-based quantitative susceptibility mapping analyses of cortical iron in Alzheimer's disease

In addition to amyloid beta plaques and neurofibrillary tangles, Alzheimer's disease (AD) has been associated with elevated iron in deep gray matter nuclei using quantitative susceptibility mapping (QSM). However, only a few studies have examined cortical iron, using more macroscopic approaches that cannot assess layer-specific differences. Here, we conducted column-based QSM analyses to assess whether AD-related increases in cortical iron vary in relation to layer-specific differences in the type and density of neurons. We obtained global and regional measures of positive (iron) and negative (myelin, protein aggregation) susceptibility from 22 adults with AD and 22 demographically matched healthy controls. Depth-wise analyses indicated that global susceptibility increased from the pial surface to the gray/white matter boundary, with a larger slope for positive susceptibility in the left hemisphere for adults with AD than controls. Curvature-based analyses indicated larger global susceptibility for adults with AD versus controls; the right hemisphere versus left; and gyri versus sulci. Region-of-interest analyses identified similar depth- and curvature-specific group differences, especially for temporo-parietal regions. Finding that iron accumulates in a topographically heterogenous manner across the cortical mantle may help explain the profound cognitive deterioration that differentiates AD from the slowing of general motor processes in healthy aging.

PPAD: a deep learning architecture to predict progression of Alzheimer's disease

MOTIVATION

Alzheimer's disease (AD) is a neurodegenerative disease that affects millions of people worldwide. Mild cognitive impairment (MCI) is an intermediary stage between cognitively normal state and AD. Not all people who have MCI convert to AD. The diagnosis of AD is made after significant symptoms of dementia such as short-term memory loss are already present. Since AD is currently an irreversible disease, diagnosis at the onset of the disease brings a huge burden on patients, their caregivers, and the healthcare sector. Thus, there is a crucial need to develop methods for the early prediction AD for patients who have MCI. Recurrent neural networks (RNN) have been successfully used to handle electronic health records (EHR) for predicting conversion from MCI to AD. However, RNN ignores irregular time intervals between successive events which occurs common in electronic health record data. In this study, we propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimer's Disease (PPAD) and PPAD-Autoencoder. PPAD and PPAD-Autoencoder are designed for early predicting conversion from MCI to AD at the next visit and multiple visits ahead for patients, respectively. To minimize the effect of the irregular time intervals between visits, we propose using age in each visit as an indicator of time change between successive visits.

RESULTS

Our experimental results conducted on Alzheimer's Disease Neuroimaging Initiative and National Alzheimer's Coordinating Center datasets showed that our proposed models outperformed all baseline models for most prediction scenarios in terms of F2 and sensitivity. We also observed that the age feature was one of top features and was able to address irregular time interval problem.

AVAILABILITY AND IMPLEMENTATION

https://github.com/bozdaglab/PPAD.

Longitudinal mapping of cortical surface changes in Huntington's Disease

This paper investigated cortical folding in Huntington's disease to understand how disease progression impacts the surface of the cortex. Cortical morphometry changes in eight gyral based regions of interest (i.e. the left and right hemispheres of the lateral occipital, precentral, superior frontal and rostral middle gyri) were examined. We used existing neuroimaging data from IMAGE-HD, comprising 26 pre-symptomatic, 26 symptomatic and 24 healthy control individuals at three separate time points (baseline, 18-month, 30-month). Local gyrification index and cortical thickness were derived as the measures of cortical morphometry using FreeSurfer 6.0's longitudinal pipeline. The gyral based regions of interest were identified using the Desikan-Killiany Atlas. A Group by Time repeated measures ANCOVA was conducted for each region of interest. We found significantly lower LGI at a group level in the right hemisphere lateral occipital region and both hemispheres of the precentral region; as well as significantly reduced cortical thickness at a group level in both hemispheres of the lateral occipital and precentral regions and the right hemisphere of the superior frontal region. We also found a Group by Time interaction for Local gyrification index in the right hemisphere lateral occipital region. This change was largely driven by a significant decrease in the symptomatic group between baseline and 18-months. Additionally, lower local gyrification index and cortical thickness were associated with higher disease burden score. These findings demonstrate that significant longitudinal decline in right hemisphere local gyrification index is evident during manifest disease in lateral occipital cortex and that these changes are more profound in individuals with greater disease burden score.

Hippocampus segmentation and classification for dementia analysis using pre-trained neural network models

The diagnostic and clinical overlap of early mild cognitive impairment (EMCI), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and Alzheimer disease (AD) is a vital oncological issue in dementia disorder. This study is designed to examine Whole brain (WB), grey matter (GM) and Hippocampus (HC) morphological variation and identify the prominent biomarkers in MR brain images of demented subjects to understand the severity progression. Curve evolution based on shape constraint is carried out to segment the complex brain structure such as HC and GM. Pre-trained models are used to observe the severity variation in these regions. This work is evaluated on ADNI database. The outcome of the proposed work shows that curve evolution method could segment HC and GM regions with better correlation. Pre-trained models are able to show significant severity difference among WB, GM and HC regions for the considered classes. Further, prominent variation is observed between AD vs. EMCI, AD vs. MCI and AD vs. LMCI in the whole brain, GM and HC. It is concluded that AlexNet model for HC region result in better classification for AD vs. EMCI, AD vs. MCI and AD vs. LMCI with an accuracy of 93, 78.3 and 91% respectively.

Brain Shape Changes Associated With Cerebral Atrophy in Healthy Aging and Alzheimer's Disease

Both healthy and pathological brain aging are characterized by various degrees of cognitive decline that strongly correlate with morphological changes referred to as cerebral atrophy. These hallmark morphological changes include cortical thinning, white and gray matter volume loss, ventricular enlargement, and loss of gyrification all caused by a myriad of subcellular and cellular aging processes. While the biology of brain aging has been investigated extensively, the mechanics of brain aging remains vastly understudied. Here, we propose a multiphysics model that couples tissue atrophy and Alzheimer's disease biomarker progression. We adopt the multiplicative split of the deformation gradient into a shrinking and an elastic part. We model atrophy as region-specific isotropic shrinking and differentiate between a constant, tissue-dependent atrophy rate in healthy aging, and an atrophy rate in Alzheimer's disease that is proportional to the local biomarker concentration. Our finite element modeling approach delivers a computational framework to systematically study the spatiotemporal progression of cerebral atrophy and its regional effect on brain shape. We verify our results via comparison with cross-sectional medical imaging studies that reveal persistent age-related atrophy patterns. Our long-term goal is to develop a diagnostic tool able to differentiate between healthy and accelerated aging, typically observed in Alzheimer's disease and related dementias, in order to allow for earlier and more effective interventions.

Cortical morphometry and neural dysfunction in Huntington's disease: a review

Numerous neuroimaging techniques have been used to identify biomarkers of disease progression in Huntington's disease (HD). To date, the earliest and most sensitive of these is caudate volume; however, it is becoming increasingly evident that numerous changes to cortical structures, and their interconnected networks, occur throughout the course of the disease. The mechanisms by which atrophy spreads from the caudate to these cortical regions remains unknown. In this review, the neuroimaging literature specific to T1-weighted and diffusion-weighted magnetic resonance imaging is summarized and new strategies for the investigation of cortical morphometry and the network spread of degeneration in HD are proposed. This new avenue of research may enable further characterization of disease pathology and could add to a suite of biomarker/s of disease progression for patient stratification that will help guide future clinical trials.

Parieto-occipital sulcus widening differentiates posterior cortical atrophy from typical Alzheimer disease

OBJECTIVES

Posterior Cortical Atrophy (PCA) is an atypical presentation of Alzheimer disease (AD) characterized by atrophy of posterior brain regions. This pattern of atrophy is usually evaluated with Koedam visual rating scale, a score developed to enable visual assessment of parietal atrophy on magnetic resonance imaging (MRI). However, Koedam scale is complex to assess and its utility in the differential diagnosis between PCA and typical AD has not been demonstrated yet. The aim of this study is therefore to spot a simple and reliable MRI element able to differentiate between PCA and typical AD using visual rating scales.

METHODS

15 patients who presented with progressive complex visual disorders and predominant occipitoparietal hypometabolism on PET-FDG were selected from our centre and compared with 30 typical AD patients and 15 healthy subjects. We used previously validated visual rating scales including Koedam scale, which we divided into three major components: posterior cingulate, precuneus and parieto-occipital. Subsequently we validated the results using the automated software Brainvisa Morphologist and Voxel Based Morphometry (VBM).

RESULTS

Patients with PCA, compared to typical AD, showed higher widening of the parieto-occipital sulcus, assessed both with visual rating scales and Brainvisa. In the corresponding areas, the VBM analysis showed an inverse correlation between the results obtained from the visual evaluation scales with the volume of the grey matter and a direct correlation between the same results with the cerebrospinal fluid volume.

CONCLUSIONS

A visually based rating scale for parieto-occipital sulcus can distinguish Posterior Cortical Atrophy from typical Alzheimer disease.

Machine Learning Techniques for the Diagnosis of Alzheimer’s Disease

Alzheimer’s disease is an incurable neurodegenerative disease primarily affecting the elderly population. Efficient automated techniques are needed for early diagnosis of Alzheimer’s. Many novel approaches are proposed by researchers for classification of Alzheimer’s disease. However, to develop more efficient learning techniques, better understanding of the work done on Alzheimer’s is needed. Here, we provide a review on 165 papers from 2005 to 2019, using various feature extraction and machine learning techniques. The machine learning techniques are surveyed under three main categories: support vector machine (SVM), artificial neural network (ANN), and deep learning (DL) and ensemble methods. We present a detailed review on these three approaches for Alzheimer’s with possible future directions.

Robust estimation of sulcal morphology

While it is well established that cortical morphology differs in relation to a variety of inter-individual factors, it is often characterized using estimates of volume, thickness, surface area, or gyrification. Here we developed a computational approach for estimating sulcal width and depth that relies on cortical surface reconstructions output by FreeSurfer. While other approaches for estimating sulcal morphology exist, studies often require the use of multiple brain morphology programs that have been shown to differ in their approaches to localize sulcal landmarks, yielding morphological estimates based on inconsistent boundaries. To demonstrate the approach, sulcal morphology was estimated in three large sample of adults across the lifespan, in relation to aging. A fourth sample is additionally used to estimate test–retest reliability of the approach. This toolbox is now made freely available as supplemental to this paper: https://cmadan.github.io/calcSulc/.

Transfer Learning Assisted Classification and Detection of Alzheimer's Disease Stages Using 3D MRI Scans

Alzheimer’s disease effects human brain cells and results in dementia. The gradual deterioration of the brain cells results in disability of performing daily routine tasks. The treatment for this disease is still not mature enough. However, its early diagnosis may allow restraining the spread of disease. For early detection of Alzheimer’s through brain Magnetic Resonance Imaging (MRI), an automated detection and classification system needs to be developed that can detect and classify the subject having dementia. These systems also need not only to classify dementia patients but to also identify the four progressing stages of dementia. The proposed system works on an efficient technique of utilizing transfer learning to classify the images by fine-tuning a pre-trained convolutional network, AlexNet. The architecture is trained and tested over the pre-processed segmented (Grey Matter, White Matter, and Cerebral Spinal Fluid) and un-segmented images for both binary and multi-class classification. The performance of the proposed system is evaluated over Open Access Series of Imaging Studies (OASIS) dataset. The algorithm showed promising results by giving the best overall accuracy of 92.85% for multi-class classification of un-segmented images.

Characterization of Alzheimer conditions in MR images using volumetric and sagittal brainstem texture features

BACKGROUND AND OBJECTIVE

Brainstem analysis in Magnetic Resonance Images is essential to detect Alzheimer's condition in the preclinical stages. In this work, an attempt has been made to segment the brainstem in sagittal (2D) and volumetric (3D) images and evaluate texture changes to differentiate Alzheimer's disease (AD) stages.

METHOD

The images obtained from a public access database are spatial normalized, skull stripped and contrast enhanced. Morphological Reconstruction based Fast and Robust Fuzzy 'C' Means technique is used to cluster the brain tissue in preprocessed images into three groups namely cerebrospinal fluid, grey matter and white matter. Brainstem is segmented from the white matter tissue using connected component labelling. Texture features from volumetric and sagittal brainstem slices are extracted and its statistical significance is evaluated.

RESULTS

Results show that the proposed approach is able to segment the brainstem from all the considered images. Variation in texture is observed to be less than 2% among sagittal brainstem slices. Additionally, midsagittal and volumetric features are correlated, suggesting that midsagittal brainstem structure gives an estimate of brainstem volume. Texture features extracted from midsagittal slice shows significant variation (p < 0.05) and is able to differentiate AD classes.

CONCLUSION

Midsagittal brainstem texture features are able to capture the changes occurring in the early stages of disease condition. As the distinction of AD in preclinical stage is complex and clinically significant, this approach could be useful for early diagnosis of the disease.

A novel method and software for automatically classifying Alzheimer's disease patients by magnetic resonance imaging analysis

BACKGROUND AND OBJECTIVE

The cause of the Alzheimer's disease is poorly understood and to date no treatment to stop or reverse its progression has been discovered. In developed countries, the Alzheimer's disease is one of the most financially costly diseases due to the requirement of continuous treatments as well as the need of assistance or supervision with the most cognitively demanding activities as time goes by. The objective of this work is to present an automated approach for classifying the Alzheimer's disease from magnetic resonance imaging (MRI) patient brain scans. The method is fast and reliable for a suitable and straightforward deploy in clinical applications for helping diagnosing and improving the efficacy of medical treatments by recognising the disease state of the patient.

METHODS

Many features can be extracted from magnetic resonance images, but most are not suitable for the classification task. Therefore, we propose a new feature extraction technique from patients' MRI brain scans that is based on a recent computer vision method, called Oriented FAST and Rotated BRIEF. The extracted features are processed with the definition and the combination of two new metrics, i.e., their spatial position and their distribution around the patient's brain, and given as input to a function-based classifier (i.e., Support Vector Machines).

RESULTS

We report the comparison with recent state-of-the-art approaches on two established medical data sets (ADNI and OASIS). In the case of binary classification (case vs control), our proposed approach outperforms most state-of-the-art techniques, while having comparable results with the others. Specifically, we obtain 100% (97%) of accuracy, 100% (97%) sensitivity and 99% (93%) specificity for the ADNI (OASIS) data set. When dealing with three or four classes (i.e., classification of all subjects) our method is the only one that reaches remarkable performance in terms of classification accuracy, sensitivity and specificity, outperforming the state-of-the-art approaches. In particular, in the ADNI data set we obtain a classification accuracy, sensitivity and specificity of 99% while in the OASIS data set a classification accuracy and sensitivity of 77% and specificity of 79% when dealing with four classes.

CONCLUSIONS

By providing a quantitative comparison on the two established data sets with many state-of-the-art techniques, we demonstrated the effectiveness of our proposed approach in classifying the Alzheimer's disease from MRI patient brain scans.