Random Forest-Based Manifold Learning for Classification of Imaging Data in Dementia

Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions

Nowadays, Artificial Intelligence (AI) and machine learning (ML) have successfully provided automated solutions to numerous real-world problems. Healthcare is one of the most important research areas for ML researchers, with the aim of developing automated disease prediction systems. One of the disease detection problems that AI and ML researchers have focused on is dementia detection using ML methods. Numerous automated diagnostic systems based on ML techniques for early prediction of dementia have been proposed in the literature. Few systematic literature reviews (SLR) have been conducted for dementia prediction based on ML techniques in the past. However, these SLR focused on a single type of data modality for the detection of dementia. Hence, the purpose of this study is to conduct a comprehensive evaluation of ML-based automated diagnostic systems considering different types of data modalities such as images, clinical-features, and voice data. We collected the research articles from 2011 to 2022 using the keywords dementia, machine learning, feature selection, data modalities, and automated diagnostic systems. The selected articles were critically analyzed and discussed. It was observed that image data driven ML models yields promising results in terms of dementia prediction compared to other data modalities, i.e., clinical feature-based data and voice data. Furthermore, this SLR highlighted the limitations of the previously proposed automated methods for dementia and presented future directions to overcome these limitations.

The Development of a Practical Artificial Intelligence Tool for Diagnosing and Evaluating Autism Spectrum Disorder: Multicenter Study

Background

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder with an unknown etiology. Early diagnosis and intervention are key to improving outcomes for patients with ASD. Structural magnetic resonance imaging (sMRI) has been widely used in clinics to facilitate the diagnosis of brain diseases such as brain tumors. However, sMRI is less frequently used to investigate neurological and psychiatric disorders, such as ASD, owing to the subtle, if any, anatomical changes of the brain.

Objective

This study aimed to investigate the possibility of identifying structural patterns in the brain of patients with ASD as potential biomarkers in the diagnosis and evaluation of ASD in clinics.

Methods

We developed a novel 2-level histogram-based morphometry (HBM) classification framework in which an algorithm based on a 3D version of the histogram of oriented gradients (HOG) was used to extract features from sMRI data. We applied this framework to distinguish patients with ASD from healthy controls using 4 datasets from the second edition of the Autism Brain Imaging Data Exchange, including the ETH Zürich (ETH), NYU Langone Medical Center: Sample 1, Oregon Health and Science University, and Stanford University (SU) sites. We used a stratified 10-fold cross-validation method to evaluate the model performance, and we applied the Naive Bayes approach to identify the predictive ASD-related brain regions based on classification contributions of each HOG feature.

Results

On the basis of the 3D HOG feature extraction method, our proposed HBM framework achieved an area under the curve (AUC) of >0.75 in each dataset, with the highest AUC of 0.849 in the ETH site. We compared the 3D HOG algorithm with the original 2D HOG algorithm, which showed an accuracy improvement of >4% in each dataset, with the highest improvement of 14% (6/42) in the SU site. A comparison of the 3D HOG algorithm with the scale-invariant feature transform algorithm showed an AUC improvement of >18% in each dataset. Furthermore, we identified ASD-related brain regions based on the sMRI images. Some of these regions (eg, frontal gyrus, temporal gyrus, cingulate gyrus, postcentral gyrus, precuneus, caudate, and hippocampus) are known to be implicated in ASD in prior neuroimaging literature. We also identified less well-known regions that may play unrecognized roles in ASD and be worth further investigation.

Conclusions

Our research suggested that it is possible to identify neuroimaging biomarkers that can distinguish patients with ASD from healthy controls based on the more cost-effective sMRI images of the brain. We also demonstrated the potential of applying data-driven artificial intelligence technology in the clinical setting of neurological and psychiatric disorders, which usually harbor subtle anatomical changes in the brain that are often invisible to the human eye.

Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study

Background

Up to half of patients with dementia may not receive a formal diagnosis, limiting access to appropriate services. It is hypothesised that it may be possible to identify undiagnosed dementia from a profile of symptoms recorded in routine clinical practice.

Aim

The aim of this study is to develop a machine learning-based model that could be used in general practice to detect dementia from routinely collected NHS data. The model would be a useful tool for identifying people who may be living with dementia but have not been formally diagnosed.

Design & setting

The study involved a case-control design and analysis of primary care data routinely collected over a 2-year period. Dementia diagnosed during the study period was compared to no diagnosis of dementia during the same period using pseudonymised routinely collected primary care clinical data.

Method

Routinely collected Read-encoded data were obtained from 18 consenting GP surgeries across Devon, for 26 483 patients aged >65 years. The authors determined Read codes assigned to patients that may contribute to dementia risk. These codes were used as features to train a machine-learning classification model to identify patients that may have underlying dementia.

Results

The model obtained sensitivity and specificity values of 84.47% and 86.67%, respectively.

Conclusion

The results show that routinely collected primary care data may be used to identify undiagnosed dementia. The methodology is promising and, if successfully developed and deployed, may help to increase dementia diagnosis in primary care.

MR volumetric assessment of endolymphatic hydrops

OBJECTIVES

We aimed to volumetrically quantify endolymph and perilymph spaces of the inner ear in order to establish a methodological basis for further investigations into the pathophysiology and therapeutic monitoring of Menière's disease.

METHODS

Sixteen patients (eight females, aged 38-71 years) with definite unilateral Menière's disease were included in this study. Magnetic resonance (MR) cisternography with a T2-SPACE sequence was combined with a Real reconstruction inversion recovery (Real-IR) sequence for delineation of inner ear fluid spaces. Machine learning and automated local thresholding segmentation algorithms were applied for three-dimensional (3D) reconstruction and volumetric quantification of endolymphatic hydrops. Test-retest reliability was assessed by the intra-class coefficient; correlation of cochlear endolymph volume ratio with hearing function was assessed by the Pearson correlation coefficient.

RESULTS

Endolymph volume ratios could be reliably measured in all patients, with a mean (range) value of 15% (2-25) for the cochlea and 28% (12-40) for the vestibulum. Test-retest reliability was excellent, with an intra-class coefficient of 0.99. Cochlear endolymphatic hydrops was significantly correlated with hearing loss (r = 0.747, p = 0.001).

CONCLUSIONS

MR imaging after local contrast application and image processing, including machine learning and automated local thresholding, enable the volumetric quantification of endolymphatic hydrops. This allows for a quantitative assessment of the effect of therapeutic interventions on endolymphatic hydrops.

KEY POINTS

• Endolymphatic hydrops is the pathological hallmark of Menière's disease. • Endolymphatic hydrops can be visualized by locally enhanced ultra-high-resolution MR imaging. • Computer-aided image processing enables quantification of endolymphatic hydrops. • Endolymphatic hydrops correlates with hearing loss in patients with Menière's disease. • Therapeutic trials in Menière's disease can be monitored with this quantitative approach.

KERNEL-BASED MULTI-TASK JOINT SPARSE CLASSIFICATION FOR ALZHEIMER'S DISEASE

Multi-modality imaging provides complementary information for diagnosis of neurodegenerative disorders such as Alzheimer's disease (AD) and its prodrome, mild cognitive impairment (MCI). In this paper, we propose a kernel-based multi-task sparse representation model to combine the strengths of MRI and PET imaging features for improved classification of AD. Sparse representation based classification seeks to represent the testing data with a sparse linear combination of training data. Here, our approach allows information from different imaging modalities to be used for enforcing class level joint sparsity via multi-task learning. Thus the common most representative classes in the training samples for all modalities are jointly selected to reconstruct the testing sample. We further improve the discriminatory power by extending the framework to the reproducing kernel Hilbert space (RKHS) so that nonlinearity in the features can be captured for better classification. Experiments on Alzheimer's Disease Neuroimaging Initiative database shows that our proposed method can achieve 93.3% and 78.9% accuracy for classification of AD and MCI from healthy controls, respectively, demonstrating promising performance in AD study.

Neighbourhood approximation forests

Methods that leverage neighbourhood structures in high-dimensional image spaces have recently attracted attention. These approaches extract information from a new image using its "neighbours" in the image space equipped with an application-specific distance. Finding the neighbourhood of a given image is challenging due to large dataset sizes and costly distance evaluations. Furthermore, automatic neighbourhood search for a new image is currently not possible when the distance is based on ground truth annotations. In this article we present a general and efficient solution to these problems. "neighbourhood approximation forests" (NAF) is a supervised learning algorithm that approximates the neighbourhood structure resulting from an arbitrary distance. As NAF uses only image intensities to infer neighbours it can also be applied to distances based on ground truth annotations. We demonstrate NAF in two scenarios: (i) choosing neighbours with respect to a deformation-based distance, and (ii) age prediction from brain MRI. The experiments show NAF's approximation quality, computational advantages and use in different contexts.