MRI Radiomics Classification and Prediction in Alzheimer's Disease and Mild Cognitive Impairment: A Review

The value of hippocampal sub-region imaging features for the diagnosis and severity grading of ASD in children

BACKGROUND

Hippocampal structural changes in Autism Spectrum Disorder (ASD) are inconsistent. This study investigates hippocampal subregion changes in ASD patients to reveal intrinsic hippocampal anomalies.

METHODS

A retrospective study from Hainan Children's Hospital database (2020-2023) included ASD patients and matched controls. We classified ASD participants based on severity, dividing all subjects into four groups: normal, mild, moderate, and severe. High-resolution T1-weighted MRI images were analyzed for hippocampal subregion segmentation and volume calculations using Freesurfer. Texture features were extracted via the Gray-Level Co-occurrence Matrix. The Receiver Operating Characteristic curve was used to evaluate seven random forest predictive models constructed from volume, subregion, and texture features, as well as their combinations following feature selection.

RESULTS

The study included 114 ASD patients (98 boys, 2-8 years; 16 girls, 2-6 years; 17 mild, 57 moderate, 40 severe) and 111 healthy controls (HCs). No significant differences in volumes were found between ASD patients and HCs (adjusted P-value >0.05). The seven random forest models showed that single volume and texture features performed poorly for ASD classification; however, integrating various feature types improved AUC values. Further selection of texture, subregion, and volume features enhanced AUC performance across normal and varying severity categories, demonstrating the potential value of specific subregions and integrated features in ASD diagnosis.

CONCLUSION

Random forest models revealed that hippocampal volume, texture features, and subregion characteristics are crucial for diagnosing and assessing the severity of ASD. Integrating selected texture and subregion features optimized diagnostic efficacy, while combining texture, subregion, and volume features further improved severity grading effectiveness.

Support Vector Machine for Stratification of Cognitive Impairment Using 3D T1WI in Patients with Type 2 Diabetes Mellitus

Purpose

To explore the potential of MRI-based radiomics in predicting cognitive dysfunction in patients with diagnosed type 2 diabetes mellitus (T2DM).

Patients and Methods

In this study, data on 158 patients with T2DM were retrospectively collected between September 2019 and December 2020. The participants were categorized into a normal cognitive function (N) group (n=30), a mild cognitive impairment (MCI) group (n=90), and a dementia (DM) group (n=38) according to the Chinese version of the Montréal Cognitive Assessment Scale-B (MoCA-B). Radiomics features were extracted from the brain tissue except ventricles and sulci in the 3D T1WI images, support vector machine (SVM) model was then established to identify the CI and N groups, and the MCI and DM groups, respectively. The models were evaluated based on their area under the receiver operating characteristic curve (AUC), Precision (P), Recall rate (Recall, R), F1-score, and Support. Finally, ROC curves were plotted for each model.

Results

The study consisted of 68 cases in the N and CI group, with 54 cases in the training set and 14 in the verification set, and 128 cases were included in the MCI and DM groups, with 90 training sets and 38 verification sets. The consistency for inter-group and intra-group of radiomics features in two physicians were 0.86 and 0.90, respectively. After features selection, there were 11 optimal features to distinguish N and CI and 12 optimal features to MCI and DM. In the test set, the AUC for the SVM classifier was 0.857 and the accuracy was 0.830 in distinguishing CI and N, while AUC was 0.821 and the accuracy was 0.830 in distinguishing MCI and DM.

Conclusion

The SVM model based on MRI radiomics exhibits high efficacy in the diagnosis of cognitive dysfunction and evaluation of its severity among patients with T2DM.

MRI Radiomics Nomogram for Predicting Disease Transition Time and Risk Stratification in Preclinical Alzheimer's Disease

RATIONALE AND OBJECTIVES

Accurate prediction of the progression of preclinical Alzheimer's disease (AD) is crucial for improving clinical management and disease prognosis. The objective of this study was to develop and validate clinical-radimoics integrated model to predict the time to progression (TTP) and disease risk stratification of preclinical AD.

MATERIALS AND METHODS

A total of 244 cases (mean age: 73.8 ± 5.5 years, 120 women) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were randomly divided into the training cohort (n = 172) and validation cohort (n = 72) using a 7:3 ratio. Clinical factors were identified by univariate and multivariate COX regression. Radiomics features were extracted from GM, WM and CSF of T1WI images and selected by Spearman correlation analysis and least absolute shrinkage and selection operator (LASSO). Using selected clinical factors and radiomics features, the clinical, radimocis and clinical-radiomics nomogram models were developed for predicting the TTP. The performance of each model was assessed by C-index. The risk stratification ability and predicting efficacy of the clinical-radiomics model were utilizing the Kaplan-Meier curve and receiver operator characteristic (ROC) curve.

RESULTS

The C-index of clinical, radimocis and clinical-radiomics models were 0.852 (95% confidence interval[CI]:0.810-0.893), 0.863 (95%CI:0.816-0.910) and 0.903 (95%:0.870-0.936) in the training cohort and 0.725 (95%CI:0.630-0.820), 0.788 (95%CI:0.678-0.898), 0.813(95%CI:0.734-0.892) in the validation cohort. The AUCs of the multi-predictor nomogram at 1-, 3-, 5- and 7-year were 0.894, 0.908, 0.930, 0.979 in the training cohort and 0.671, 0.726, 0.839, 0.931 in the validation cohort.

CONCLUSION

In this study, we constructed a clinical-radimoics integrated model to predict the progression of preclinical AD and stratified the risk of disease progression in preclinical AD.

Identification of Depression Subtypes in Parkinson's Disease Patients via Structural MRI Whole-Brain Radiomics: An Unsupervised Machine Learning Study

OBJECTIVE

Current clinical evaluation may tend to lack precision in detecting depression in Parkinson's disease (DPD). Radiomics features have gradually shown potential as auxiliary diagnostic tools in identifying and distinguishing different subtypes of Parkinson's disease (PD), and a radiomic approach that combines unsupervised machine learning has the potential to identify DPD.

METHODS

Analyze the clinical and imaging data of 272 Parkinson's disease (PD) patients from the PPMI dataset, along with 45 PD patients from the NACC dataset. Extract radiomic features from T1-weighted MRI images and employ principal component analysis (PCA) for dimensionality reduction. Subsequently, apply four unsupervised clustering methods including Gaussian mixture model (GMM), hierarchical clustering, K-means, and partitioning around medoids (PAM) to classify cases in the PPMI dataset into distinct subtypes. Identify high-risk subtypes of DPD on the basis of the time and number of depression progression, and validate these findings using the NACC dataset. The data from the high-risk subtype were divided into a training subtype and a testing subtype in a 7:3 ratio. Multiple logistic regression analysis was conducted on the training subtype data to develop a traditional logistic regression model for the high-risk subtype, which was subsequently compared with a supervised logistic regression model constructed for the entire PPMI cohort. Finally, the performance of both models was evaluated using receiver operating characteristic (ROC) curves. In addition, a decision tree (DT) model was constructed based on independent risk factors of high-risk subtypes and validated using low-risk subtype data. ROC curves were employed to validate this model across training subtype, testing subtype, and low-risk subtype datasets.

RESULTS

The PAM clustering method demonstrates superior performance compared to the other three clustering methods when the number of clusters is 2. High-risk subtypes of DPD can be effectively distinguished in both the PPMI and NACC datasets. A traditional logistic regression model was developed based on rapid-eye-movement behavior disorder, UPDRS I score, UPDRS II score, and ptau in high-risk subgroups. This model exhibits a diagnostic efficacy (AUC = 0.731) that surpasses that of the traditional regression model constructed using the entire PPMI cohort (AUC = 0.674). The prediction model based on high-risk subtypes had AUC values of 0.853 and 0.81 in the training and testing subtypes, sensitivities of 0.765 and 0.786, and specificities of 0.771 and 0.815, respectively. The AUC, sensitivity, and specificity in the nonhigh-risk subtype were 0.859, 0.654, and 0.852, respectively.

CONCLUSION

By identifying MRI structural radiomics and clinical features as potential biomarkers, the radiomic approach and UCA provide new insights into the pathophysiology of DPD to support the clinical diagnosis with high prediction accuracy.

Application of radiomics in acute and severe non-neoplastic diseases: A literature review

Radiomics involves the integration of computer technology, big data analysis, and clinical medicine. Currently, there have been initial advancements in the fields of acute cerebrovascular disease and cardiovascular disease. The objective of radiomics is to extract quantitative features from medical images for analysis to predict the risk or treatment outcome, help in differential diagnosis, and guide clinical decisions and management. Radiomics applied research has reached a more advanced stage yet encounters several obstacles, including the need for standardization of radiomics features and alignment with treatment requirements for acute and severe illnesses. Future research should aim to seamlessly incorporate radiomics with various disciplines, leverage big data and artificial intelligence advancements, cater to the requirements of acute and critical medicine, and enhance the effectiveness of technological innovation and application in diagnosing and treating acute and critical illnesses.

Quantitative and Computational Spinal Imaging in Neurodegenerative Conditions and Acquired Spinal Disorders: Academic Advances and Clinical Prospects

Introduction: Quantitative spinal cord imaging has facilitated the objective appraisal of spinal cord pathology in a range of neurological conditions both in the academic and clinical setting. Diverse methodological approaches have been implemented, encompassing a range of morphometric, diffusivity, susceptibility, magnetization transfer, and spectroscopy techniques. Advances have been fueled both by new MRI platforms and acquisition protocols as well as novel analysis pipelines. The quantitative evaluation of specific spinal tracts and grey matter indices has the potential to be used in diagnostic and monitoring applications. The comprehensive characterization of spinal disease burden in pre-symptomatic cohorts, in carriers of specific genetic mutations, and in conditions primarily associated with cerebral disease, has contributed important academic insights. Methods: A narrative review was conducted to examine the clinical and academic role of quantitative spinal cord imaging in a range of neurodegenerative and acquired spinal cord disorders, including hereditary spastic paraparesis, hereditary ataxias, motor neuron diseases, Huntington's disease, and post-infectious or vascular disorders. Results: The clinical utility of specific methods, sample size considerations, academic role of spinal imaging, key radiological findings, and relevant clinical correlates are presented in each disease group. Conclusions: Quantitative spinal cord imaging studies have demonstrated the feasibility to reliably appraise structural, microstructural, diffusivity, and metabolic spinal cord alterations. Despite the notable academic advances, novel acquisition protocols and analysis pipelines are yet to be implemented in the clinical setting.

Disparities in the diagnostic efficacy of radiomics models in predicting various degrees of cognitive impairment in patients with cerebral small vessel disease

BACKGROUND

Aim to validate the diagnostic efficacy of radiomics models for predicting various degrees of cognitive impairment in patients with cerebral small vessel disease (CSVD).

METHODS

Participants were divided into mild cognitive impairment group (mild-CSVD group) and sever cognitive impairment group (sever-CSVD group) according to Montreal Cognitive Assessment (MoCA) performance, 98 gender-age-education matched subjects served as normal controls. Radiomic features were extracted from the segmented hippocampus using PyRadiomics. The feature preprocessing involved replacing missing values with the mean, applying stratified random sampling to allocate subjects into training (80%) and testing (20%) sets, ensuring balance among the three classes (normal controls, mild-CSVD group, and sever-CSVD group). A feature selection method was applied to identify discriminative radiomic features, with the optimal texture feature chosen for developing diagnostic models. Performance was evaluated in both the training and testing sets using receiver operating characteristic (ROC) curve analysis.

RESULTS

The radiomics model achieved an accuracy of 0.625, an AUC of 0.593, a sensitivity of 0.828, and a specificity of 0.316 in distinguishing mild-CSVD group from normal controls. When distinguishing mild-CSVD group from sever-CSVD group, the radiomics model reached an accuracy of 0.683, an AUC of 0.660, a sensitivity of 0.167, and a specificity of 0.897. Similarly, in distinguishing sever-CSVD group from normal controls, the radiomics model exhibited an accuracy of 0.781, an AUC of 0.818, a sensitivity of 0.538, and a specificity of 0.947.

CONCLUSION

Radiomics model based on hippocampal texture had disparities in the diagnostic efficacy of radiomics models in predicting various degrees of cognitive impairment in patients with CSVD.

Study on the Effects of Acupuncture with the "Yizhi Tiaoshen" Acupoint Formula on Blood Oxygen Metabolism and Neural Function in Key Brain Regions of AD Rats

Purpose

Exploring the effects of acupuncture at the "Yizhi Tiaoshen" acupoint on blood oxygen metabolism and neurological function changes in the brain regions of AD model rats.

Methods

The AD model was replicated by intraperitoneal injection of D-galactose combined with bilateral hippocampal CA1 injection of Okadaic acid (OA). Thirty rats with successfully replicated model were selected through Morris water maze experiment and randomly divided into model group, donepezil hydrochloride group, and acupuncture group, with 10 rats in each group. After treatment, fNIRs were used to detect changes in Oxy Hb, Deoxy Hb, and Total Hb in the cerebral cortex of rats in each group, in order to evaluate the neurological function changes in key brain areas.

Results

The escape latency of the donepezil hydrochloride group and the acupuncture group was shortened, the number of crossings through the original platform increased, and the duration of stay in the quadrant where the original platform was located was prolonged. Based on fNIRs detection, the main differential channels of blood oxygen metabolism in AD rats were identified as 2-2 and 8-7, corresponding to the prefrontal and parietal lobes, respectively. The concentrations of Oxy Hb and Total Hb were significantly increased in both treatment groups, while the concentration of Deoxy Hb was significantly decreased.

Conclusion

Acupuncture with the "Yizhi Tiaoshen" acupoint formula and donepezil hydrochloride can improve the learning and memory function of AD rats, and its mechanism may be related to improving blood oxygen metabolism in the prefrontal and parietal regions and protecting neuronal function.

Differences between Alzheimer's disease and mild cognitive impairment using brain networks from magnetic resonance texture analysis

Several studies have aimed at identifying biomarkers in the initial phases of Alzheimer's disease (AD). Conversely, texture features, such as those from gray-level co-occurrence matrices (GLCMs), have highlighted important information from several types of medical images. More recently, texture-based brain networks have been shown to provide useful information in characterizing healthy individuals. However, no studies have yet explored the use of this type of network in the context of AD. This work aimed to employ texture brain networks to investigate the distinction between groups of patients with amnestic mild cognitive impairment (aMCI) and mild dementia due to AD, and a group of healthy subjects. Magnetic resonance (MR) images from the three groups acquired at two instances were used. Images were segmented and GLCM texture parameters were calculated for each region. Structural brain networks were generated using regions as nodes and the similarity among texture parameters as links, and graph theory was used to compute five network measures. An ANCOVA was performed for each network measure to assess statistical differences between groups. The thalamus showed significant differences between aMCI and AD patients for four network measures for the right hemisphere and one network measure for the left hemisphere. There were also significant differences between controls and AD patients for the left hippocampus, right superior parietal lobule, and right thalamus-one network measure each. These findings represent changes in the texture of these regions which can be associated with the cortical volume and thickness atrophies reported in the literature for AD. The texture networks showed potential to differentiate between aMCI and AD patients, as well as between controls and AD patients, offering a new tool to help understand these conditions and eventually aid early intervention and personalized treatment, thereby improving patient outcomes and advancing AD research.

Beyond Macrostructure: Is There a Role for Radiomics Analysis in Neuroimaging ?

The most commonly used neuroimaging biomarkers of brain structure, particularly in neurodegenerative diseases, have traditionally been summary measurements from ROIs derived from structural MRI, such as volume and thickness. Advances in MR acquisition techniques, including high-field imaging, and emergence of learning-based methods have opened up opportunities to interrogate brain structure in finer detail, allowing investigators to move beyond macrostructural measurements. On the one hand, superior signal contrast has the potential to make appearance-based metrics that directly analyze intensity patterns, such as texture analysis and radiomics features, more reliable. Quantitative MRI, particularly at high-field, can also provide a richer set of measures with greater interpretability. On the other hand, use of neural networks-based techniques has the potential to exploit subtle patterns in images that can now be mined with advanced imaging. Finally, there are opportunities for integration of multimodal data at different spatial scales that is enabled by developments in many of the above techniques-for example, by combining digital histopathology with high-resolution ex-vivo and in-vivo MRI. Some of these approaches are at early stages of development and present their own set of challenges. Nonetheless, they hold promise to drive the next generation of validation and biomarker studies. This article will survey recent developments in this area, with a particular focus on Alzheimer's disease and related disorders. However, most of the discussion is equally relevant to imaging of other neurological disorders, and even to other organ systems of interest. It is not meant to be an exhaustive review of the available literature, but rather presented as a summary of recent trends through the discussion of a collection of representative studies with an eye towards what the future may hold.

AITeQ: a machine learning framework for Alzheimer's prediction using a distinctive five-gene signature

Neurodegenerative diseases, such as Alzheimer's disease, pose a significant global health challenge with their complex etiology and elusive biomarkers. In this study, we developed the Alzheimer's Identification Tool (AITeQ) using ribonucleic acid-sequencing (RNA-seq), a machine learning (ML) model based on an optimized ensemble algorithm for the identification of Alzheimer's from RNA-seq data. Analysis of RNA-seq data from several studies identified 87 differentially expressed genes. This was followed by a ML protocol involving feature selection, model training, performance evaluation, and hyperparameter tuning. The feature selection process undertaken in this study, employing a combination of four different methodologies, culminated in the identification of a compact yet impactful set of five genes. Twelve diverse ML models were trained and tested using these five genes (CNKSR1, EPHA2, CLSPN, OLFML3, and TARBP1). Performance metrics, including precision, recall, F1 score, accuracy, Matthew's correlation coefficient, and receiver operating characteristic area under the curve were assessed for the finally selected model. Overall, the ensemble model consisting of logistic regression, naive Bayes classifier, and support vector machine with optimized hyperparameters was identified as the best and was used to develop AITeQ. AITeQ is available at: https://github.com/ishtiaque-ahammad/AITeQ.

Predicting brain age gap with radiomics and automl: A Promising approach for age-Related brain degeneration biomarkers

The Brain Age Gap (BAG), which refers to the difference between chronological age and predicted neuroimaging age, is proposed as a potential biomarker for age-related brain degeneration. However, existing brain age prediction models usually rely on a single marker and can not discover meaningful hidden information in radiographic images. This study focuses on the application of radiomics, an advanced imaging analysis technique, combined with automated machine learning to predict BAG. Our methods achieve a promising result with a mean absolute error of 1.509 using the Alzheimer's Disease Neuroimaging Initiative dataset. Furthermore, we find that the hippocampus and parahippocampal gyrus play a significant role in predicting age with interpretable method called SHapley Additive exPlanations. Additionally, our investigation of age prediction discrepancies between patients with Alzheimer's disease (AD) and those with mild cognitive impairment (MCI) reveals a notable correlation with clinical cognitive assessment scale scores. This suggests that BAG has the potential to serve as a biomarker to support the diagnosis of AD and MCI. Overall, this study presents valuable insights into the application of neuroimaging models in the diagnosis of neurodegenerative diseases.

Explainable machine learning radiomics model for Primary Progressive Aphasia classification

Introduction

Primary Progressive Aphasia (PPA) is a neurodegenerative disease characterized by linguistic impairment. The two main clinical subtypes are semantic (svPPA) and non-fluent/agrammatic (nfvPPA) variants. Diagnosing and classifying PPA patients represents a complex challenge that requires the integration of multimodal information, including clinical, biological, and radiological features. Structural neuroimaging can play a crucial role in aiding the differential diagnosis of PPA and constructing diagnostic support systems.

Methods

In this study, we conducted a white matter texture analysis on T1-weighted images, including 56 patients with PPA (31 svPPA and 25 nfvPPA), and 53 age- and sex-matched controls. We trained a tree-based algorithm over combined clinical/radiomics measures and used Shapley Additive Explanations (SHAP) model to extract the greater impactful measures in distinguishing svPPA and nfvPPA patients from controls and each other.

Results

Radiomics-integrated classification models demonstrated an accuracy of 95% in distinguishing svPPA patients from controls and of 93.7% in distinguishing svPPA from nfvPPA. An accuracy of 93.7% was observed in differentiating nfvPPA patients from controls. Moreover, Shapley values showed the strong involvement of the white matter near left entorhinal cortex in patients classification models.

Discussion

Our study provides new evidence for the usefulness of radiomics features in classifying patients with svPPA and nfvPPA, demonstrating the effectiveness of an explainable machine learning approach in extracting the most impactful features for assessing PPA.

Predicting the Rapid Progression of Mild Cognitive Impairment by Intestinal Flora and Blood Indicators through Machine Learning Method

INTRODUCTION

The aim of the work was to establish a prediction model of mild cognitive impairment (MCI) progression based on intestinal flora by machine learning method.

METHOD

A total of 1,013 patients were recruited, in which 87 patients with MCI finished a two-year follow-up. To establish a prediction model, 61 patients were randomly divided into a training set and 26 patients were divided into a testing set. A total of 121 features including demographic characteristics, hematological indicators, and intestinal flora abundance were analyzed.

RESULTS

Of the 87 patients who finished a two-year follow-up, 44 presented rapid progression. Model 1 was established based on 121 features with the accuracy 85%, sensitivity 85%, and specificity 83%. Model 2 was based on the first fifteen features of model 1 (triglyceride, uric acid, alanine transaminase, F-Clostridiaceae, G-Megamonas, S-Megamonas, G-Shigella, G-Shigella, S-Shigella, average hemoglobin concentration, G-Alistipes, S-Collinsella, median cell count, average hemoglobin volume, low-density lipoprotein), with the accuracy 97%, sensitivity 92%, and specificity 100%. Model 3 was based on the first ten features of model 1, with the accuracy 97%, sensitivity 86%, and specificity 100%. Other models based on the demographic characteristics, hematological indicators, or intestinal flora abundance features presented lower sensitivity and specificity.

CONCLUSION

The 15 features (including intestinal flora abundance) could establish an effective model for predicting rapid MCI progression.

Radiomic tractometry reveals tract-specific imaging biomarkers in white matter

Tract-specific microstructural analysis of the brain's white matter (WM) using diffusion MRI has been a driver for neuroscientific discovery with a wide range of applications. Tractometry enables localized tissue analysis along tracts but relies on bare summary statistics and reduces complex image information along a tract to few scalar values, and so may miss valuable information. This hampers the applicability of tractometry for predictive modelling. Radiomics is a promising method based on the analysis of numerous quantitative image features beyond what can be visually perceived, but has not yet been used for tract-specific analysis of white matter. Here we introduce radiomic tractometry (RadTract) and show that introducing rich radiomics-based feature sets into the world of tractometry enables improved predictive modelling while retaining the localization capability of tractometry. We demonstrate its value in a series of clinical populations, showcasing its performance in diagnosing disease subgroups in different datasets, as well as estimation of demographic and clinical parameters. We propose that RadTract could spark the establishment of a new generation of tract-specific imaging biomarkers with benefits for a range of applications from basic neuroscience to medical research.

[Immunological and neuroanatomic markers of the clinical dynamics of MCI and pre-MCI]

OBJECTIVE

To study the relationship of the parameters of immunity and systemic inflammation with the structural magnetic resonance imaging (MRI) parameters in patients with mild cognitive impairment (MCI) and pre-MCI undergoing neurocognitive rehabilitation to search for candidate markers of its effectiveness.

MATERIAL AND METHODS

The main group included 49 patients, aged ≥60 years, with MCI and pre-MCI with memory impairment, who underwent a course of neurorehabilitation for 5 weeks. The control group included 19 volunteers of similar age with a total MoCA score of ≥25, who did not have cognitive impairment and immuno-inflammatory disorders. The parameters of cellular and humoral immunity and markers of inflammation were studied, and structural MRI was performed.

RESULTS

The content of activated natural killer cells (NK-cells) was increased in MCI and pre-MCI (0.63±0.12% vs. 0.22±0.07% in the control group, p=2.2·10-7). The level of immunoglobulin G (IgG) <12.5 g/l in patients with MCI and pre-MCI with the Montreal Cognitive Assessment Scale (MoCA) score <22 was associated with a decrease in the volume of the right nucleus accumbens (376±35 mm3 in patients with IgG <12.5 g/l (p=0.0013) and 480±44 mm3 at IgG <12.5 g/l, 480±44 mm3 in the control group), as well as with a decrease of the thickness and volume of a number of other cortical zones. A logistic regression model including the level of immunoglobulin G, NK cells, CD8+ NK cells and right amygdala volume was constructed to predict the number of MoCA scores 6 months after the course of rehabilitation (R2=0.57; p<1·10-5; standard error of estimate: 2.93).

CONCLUSION

As a result of this work, the perspectives of assessing the immunological parameters in combination with socio-demographic data and morphometric changes of the brain as potential prognostic markers of the dynamics of cognitive impairment in patients with MCI and pre-MCI after neurorehabilitation has been shown.

Development and validation of an automatic classification algorithm for the diagnosis of Alzheimer's disease using a high-performance interpretable deep learning network

OBJECTIVES

To develop and validate an automatic classification algorithm for diagnosing Alzheimer's disease (AD) or mild cognitive impairment (MCI).

METHODS AND MATERIALS

This study evaluated a high-performance interpretable network algorithm (TabNet) and compared its performance with that of XGBoost, a widely used classifier. Brain segmentation was performed using a commercially approved software. TabNet and XGBoost were trained on the volumes or radiomics features of 102 segmented regions for classifying subjects into AD, MCI, or cognitively normal (CN) groups. The diagnostic performances of the two algorithms were compared using areas under the curves (AUCs). Additionally, 20 deep learning-based AD signature areas were investigated.

RESULTS

Between December 2014 and March 2017, 161 AD, 153 MCI, and 306 CN cases were enrolled. Another 120 AD, 90 MCI, and 141 CN cases were included for the internal validation. Public datasets were used for external validation. TabNet with volume features had an AUC of 0.951 (95% confidence interval [CI], 0.947-0.955) for AD vs CN, which was similar to that of XGBoost (0.953 [95% CI, 0.951-0.955], p = 0.41). External validation revealed the similar performances of two classifiers using volume features (0.871 vs. 0.871, p = 0.86). Likewise, two algorithms showed similar performances with one another in classifying MCI. The addition of radiomics data did not improve the performance of TabNet. TabNet and XGBoost focused on the same 13/20 regions of interest, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

CONCLUSIONS

TabNet shows high performance in AD classification and detailed interpretation of the selected regions.

CLINICAL RELEVANCE STATEMENT

Using a high-performance interpretable deep learning network, the automatic classification algorithm assisted in accurate Alzheimer's disease detection using 3D T1-weighted brain MRI and detailed interpretation of the selected regions.

KEY POINTS

• MR volumetry data revealed that TabNet had a high diagnostic performance in differentiating Alzheimer's disease (AD) from cognitive normal cases, which was comparable with that of XGBoost. • The addition of radiomics data to the volume data did not improve the diagnostic performance of TabNet. • Both TabNet and XGBoost selected the clinically meaningful regions of interest in AD, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

Diagnostic performance of MRI radiomics for classification of Alzheimer's disease, mild cognitive impairment, and normal subjects: a systematic review and meta-analysis

BACKGROUND

Alzheimer's disease (AD) is a debilitating neurodegenerative disease. Early diagnosis of AD and its precursor, mild cognitive impairment (MCI), is crucial for timely intervention and management. Radiomics involves extracting quantitative features from medical images and analyzing them using advanced computational algorithms. These characteristics have the potential to serve as biomarkers for disease classification, treatment response prediction, and patient stratification. Of note, Magnetic resonance imaging (MRI) radiomics showed a promising result for diagnosing and classifying AD, and MCI from normal subjects. Thus, we aimed to systematically evaluate the diagnostic performance of the MRI radiomics for this task.

METHODS AND MATERIALS

A comprehensive search of the current literature was conducted using relevant keywords in PubMed/MEDLINE, Embase, Scopus, and Web of Science databases from inception to August 5, 2023. Original studies discussing the diagnostic performance of MRI radiomics for the classification of AD, MCI, and normal subjects were included. Method quality was evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and the Radiomics Quality Score (RQS) tools.

RESULTS

We identified 13 studies that met the inclusion criteria, involving a total of 5448 participants. The overall quality of the included studies was moderate to high. The pooled sensitivity and specificity of MRI radiomics for differentiating AD from normal subjects were 0.92 (95% CI [0.85; 0.96]) and 0.91 (95% CI [0.85; 0.95]), respectively. The pooled sensitivity and specificity of MRI radiomics for differentiating MCI from normal subjects were 0.74 (95% CI [0.60; 0.85]) and 0.79 (95% CI [0.70; 0.86]), respectively. Also, the pooled sensitivity and specificity of MRI radiomics for differentiating AD from MCI were 0.73 (95% CI [0.64; 0.80]) and 0.79 (95% CI [0.64; 0.90]), respectively.

CONCLUSION

MRI radiomics has promising diagnostic performance in differentiating AD, MCI, and normal subjects. It can potentially serve as a non-invasive and reliable tool for early diagnosis and classification of AD and MCI.

An integrated neuroimaging-omics approach for the gut-brain communication pathways in Alzheimer's disease

A key role of the gut microbiota in the pathogenesis of neurodegenerative diseases, such as Alzheimer's disease (AD), has been identified over the past decades. Increasing clinical and preclinical evidence implicates that there is bidirectional communication between the gut microbiota and the central nervous system (CNS), which is also known as the microbiota-gut-brain axis. Nevertheless, current knowledge on the interplay between gut microbiota and the brain remains largely unclear. One of the primary mediating factors by which the gut microbiota interacts with the host is peripheral metabolites, including blood or gut-derived metabolites. However, mechanistic knowledge about the effect of the microbiome and metabolome signaling on the brain is limited. Neuroimaging techniques, such as multi-modal magnetic resonance imaging (MRI), and fluorodeoxyglucose-positron emission tomography (FDG-PET), have the potential to directly elucidate brain structural and functional changes corresponding with alterations of the gut microbiota and peripheral metabolites in vivo. Employing a combination of gut microbiota, metabolome, and advanced neuroimaging techniques provides a future perspective in illustrating the microbiota-gut-brain pathway and further unveiling potential therapeutic targets for AD treatments.

Radiomics and Artificial Intelligence for the Diagnosis and Monitoring of Alzheimer's Disease: A Systematic Review of Studies in the Field

The use of radiomics and artificial intelligence applied for the diagnosis and monitoring of Alzheimer's disease has developed in recent years. However, this approach is not yet completely applicable in clinical practice. The aim of this paper is to provide a systematic analysis of the studies that have included the use of radiomics from different imaging techniques and artificial intelligence for the diagnosis and monitoring of Alzheimer's disease in order to improve the clinical outcomes and quality of life of older patients. A systematic review of the literature was conducted in February 2023, analyzing manuscripts and articles of the last 5 years from the PubMed, Scopus and Embase databases. All studies concerning discrimination among Alzheimer's disease, Mild Cognitive Impairment and healthy older people performing radiomics analysis through machine and deep learning were included. A total of 15 papers were included. The results showed a very good performance of this approach in the differentiating Alzheimer's disease patients-both at the dementia and pre-dementia phases of the disease-from healthy older people. In summary, radiomics and AI can be valuable tools for diagnosing and monitoring the progression of Alzheimer's disease, potentially leading to earlier and more accurate diagnosis and treatment. However, the results reported by this review should be read with great caution, keeping in mind that imaging alone is not enough to identify dementia due to Alzheimer's.

A novel collaborative self-supervised learning method for radiomic data

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity of information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.

Multi-modal cross-attention network for Alzheimer's disease diagnosis with multi-modality data

Alzheimer's disease (AD) is a neurodegenerative disorder, the most common cause of dementia, so the accurate diagnosis of AD and its prodromal stage mild cognitive impairment (MCI) is significant. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis. Many existing multi-modal models based on deep learning simply concatenate each modality's features despite substantial differences in representation spaces. In this paper, we propose a novel multi-modal cross-attention AD diagnosis (MCAD) framework to learn the interaction between modalities for better playing their complementary roles for AD diagnosis with multi-modal data including structural magnetic resonance imaging (sMRI), fluorodeoxyglucose-positron emission tomography (FDG-PET) and cerebrospinal fluid (CSF) biomarkers. Specifically, the imaging and non-imaging representations are learned by the image encoder based on cascaded dilated convolutions and CSF encoder, respectively. Then, a multi-modal interaction module is introduced, which takes advantage of cross-modal attention to integrate imaging and non-imaging information and reinforce relationships between these modalities. Moreover, an extensive objective function is designed to reduce the discrepancy between modalities for effectively fusing the features of multi-modal data, which could further improve the diagnosis performance. We evaluate the effectiveness of our proposed method on the ADNI dataset, and the extensive experiments demonstrate that our MCAD achieves superior performance for multiple AD-related classification tasks, compared to several competing methods. Also, we investigate the importance of cross-attention and the contribution of each modality to the diagnostics performance. The experimental results demonstrate that combining multi-modality data via cross-attention is helpful for accurate AD diagnosis.

MRI texture-based radiomics analysis for the identification of altered functional networks in alcoholic patients and animal models

Alcohol use disorder (AUD) is a complex condition representing a leading risk factor for death, disease and disability. Its high prevalence and severe health consequences make necessary a better understanding of the brain network alterations to improve diagnosis and treatment. The purpose of this study was to evaluate the potential of resting-state fMRI 3D texture features as a novel source of biomarkers to identify AUD brain network alterations following a radiomics approach. A longitudinal study was conducted in Marchigian Sardinian alcohol-preferring msP rats (N = 36) who underwent resting-state functional and structural MRI before and after 30 days of alcohol or water consumption. A cross-sectional human study was also conducted among 33 healthy controls and 35 AUD patients. The preprocessed functional data corresponding to control and alcohol conditions were used to perform a probabilistic independent component analysis, identifying seven independent components as resting-state networks. Forty-three radiomic features extracted from each network were compared using a Wilcoxon signed-rank test with Holm correction to identify the network most affected by alcohol consumption. Features extracted from this network were then used in the machine learning process, evaluating two feature selection methods and six predictive models within a nested cross-validation structure. The classification was evaluated by computing the area under the ROC curve. Images were quantized using different numbers of gray-levels to test their influence on the results. The influence of ageing, data preprocessing, and brain iron accumulation were also analyzed. The methodology was validated using structural scans. The striatal network in alcohol-exposed msP rats presented the most significant number of altered features. The radiomics approach supported this result achieving good classification performance in animals (AUC = 0.915 ± 0.100, with 12 features) and humans (AUC = 0.724 ± 0.117, with 9 features) using a random forest model. Using the structural scans, high accuracy was achieved with a multilayer perceptron in both species (animals: AUC > 0.95 with 2 features, humans: AUC > 0.82 with 18 features). The best results were obtained using a feature selection method based on the p-value. The proposed radiomics approach is able to identify AUD patients and alcohol-exposed rats with good accuracy, employing a subset of 3D features extracted from fMRI. Furthermore, it can help identify relevant networks in drug addiction.

Amygdala's T1-weighted image radiomics outperforms volume for differentiation of anxiety disorder and its subtype

Introduction

Anxiety disorder is the most common psychiatric disorder among adolescents, with generalized anxiety disorder (GAD) being a common subtype of anxiety disorder. Current studies have revealed abnormal amygdala function in patients with anxiety compared with healthy people. However, the diagnosis of anxiety disorder and its subtypes still lack specific features of amygdala from T1-weighted structural magnetic resonance (MR) imaging. The purpose of our study was to investigate the feasibility of using radiomics approach to distinguish anxiety disorder and its subtype from healthy controls on T1-weighted images of the amygdala, and provide a basis for the clinical diagnosis of anxiety disorder.

Methods

T1-weighted MR images of 200 patients with anxiety disorder (including 103 GAD patients) as well as 138 healthy controls were obtained in the Healthy Brain Network (HBN) dataset. We extracted 107 radiomics features for the left and right amygdala, respectively, and then performed feature selection using the 10-fold LASSO regression algorithm. For the selected features, we performed group-wise comparisons, and use different machine learning algorithms, including linear kernel support vector machine (SVM), to achieve the classification between the patients and healthy controls.

Results

For the classification task of anxiety patients vs. healthy controls, 2 and 4 radiomics features were selected from left and right amygdala, respectively, and the area under receiver operating characteristic curve (AUC) of linear kernel SVM in cross-validation experiments was 0.6739±0.0708 for the left amygdala features and 0.6403±0.0519 for the right amygdala features; for classification task for GAD patients vs. healthy controls, 7 and 3 features were selected from left and right amygdala, respectively, and the cross-validation AUCs were 0.6755±0.0615 for the left amygdala features and 0.6966±0.0854 for the right amygdala features. In both classification tasks, the selected amygdala radiomics features had higher discriminatory significance and effect sizes compared with the amygdala volume.

Discussion

Our study suggest that radiomics features of bilateral amygdala potentially could serve as a basis for the clinical diagnosis of anxiety disorder.

Based on Tau PET Radiomics Analysis for the Classification of Alzheimer's Disease and Mild Cognitive Impairment

Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) are closely associated with Tau proteins accumulation. In this study, we aimed to implement radiomics analysis to discover high-order features from pathological biomarker and improve the classification accuracy based on Tau PET images. Two cross-racial independent cohorts from the ADNI database (121 AD patients, 197 MCI patients and 211 normal control (NC) subjects) and Huashan hospital (44 AD patients, 33 MCI patients and 36 NC subjects) were enrolled. The radiomics features of Tau PET imaging of AD related brain regions were computed for classification using a support vector machine (SVM) model. The radiomics model was trained and validated in the ADNI cohort and tested in the Huashan hospital cohort. The standard uptake value ratio (SUVR) and clinical scores model were also performed to compared with radiomics analysis. Additionally, we explored the possibility of using Tau PET radiomics features as a good biomarker to make binary identification of Tau-negative MCI versus Tau-positive MCI or apolipoprotein E (ApoE) ε4 carrier versus ApoE ε4 non-carrier. We found that the radiomics model demonstrated best classification performance in differentiating AD/MCI patients and NC in comparison to SUVR and clinical scores models, with an accuracy of 84.8 ± 4.5%, 73.1 ± 3.6% in the ANDI cohort. Moreover, the radiomics model also demonstrated greater performance in diagnosing AD than other methods in the Huashan hospital cohort, with an accuracy of 81.9 ± 6.1%. In addition, the radiomics model also showed the satisfactory classification performance in the MCI-tau subgroup experiment (72.3 ± 3.5%, 71.9 ± 3.6% and 63.7 ± 5.9%) and in the MCI-ApoE subgroup experiment (73.5 ± 4.3%, 70.1 ± 3.9% and 62.5 ± 5.4%). In conclusion, our study showed that based on Tau PET radiomics analysis has the potential to guide and facilitate clinical diagnosis, further providing evidence for identifying the risk factors in MCI patients.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

A novel cascade machine learning pipeline for Alzheimer's disease identification and prediction

Introduction

Alzheimer's disease (AD) is a progressive and irreversible brain degenerative disorder early. Among all diagnostic strategies, hippocampal atrophy is considered a promising diagnostic method. In order to proactively detect patients with early Alzheimer's disease, we built an Alzheimer's segmentation and classification (AL-SCF) pipeline based on machine learning.

Methods

In our study, we collected coronal T1 weighted images that include 187 patients with AD and 230 normal controls (NCs). Our pipeline began with the segmentation of the hippocampus by using a modified U2-net. Subsequently, we extracted 851 radiomics features and selected 37 features most relevant to AD by the Hierarchical clustering method and Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. At last, four classifiers were implemented to distinguish AD from NCs, and the performance of the models was evaluated by accuracy, specificity, sensitivity, and area under the curve.

Results

Our proposed pipeline showed excellent discriminative performance of classification with AD vs NC in the training set (AUC=0.97, 95% CI: (0.96-0.98)). The model was also verified in the validation set with Dice=0.93 for segmentation and accuracy=0.95 for classification.

Discussion

The AL-SCF pipeline can automate the process from segmentation to classification, which may assist doctors with AD diagnosis and develop individualized medical plans for AD in clinical practice.

Asymmetry of radiomics features in the white matter of patients with primary progressive aphasia

Introduction

Primary Progressive Aphasia (PPA) is a neurological disease characterized by linguistic deficits. Semantic (svPPA) and non-fluent/agrammatic (nfvPPA) variants are the two main clinical subtypes. We applied a novel analytical framework, based on radiomic analysis, to investigate White Matter (WM) asymmetry and to examine whether asymmetry is associated with verbal fluency performance.

Methods

Analyses were performed on T1-weighted images including 56 patients with PPA (31 svPPA and 25 nfvPPA) and 53 age- and sex-matched controls. Asymmetry Index (AI) was computed for 86 radiomics features in 34 white matter regions. The relationships between AI, verbal fluency performance (semantic and phonemic) and Boston Naming Test score (BNT) were explored through Spearman correlation analysis.

Results

Relative to controls, WM asymmetry in svPPA patients involved regions adjacent to middle temporal cortex as part of the inferior longitudinal (ILF), fronto-occipital (IFOF) and superior longitudinal fasciculi. Conversely, nfvPPA patients showed an asymmetry of WM in lateral occipital regions (ILF/IFOF). A higher lateralization involving IFOF, cingulum and forceps minor was found in nfvPPA compared to svPPA patients. In nfvPPA patients, semantic fluency was positively correlated to asymmetry in ILF/IFOF tracts. Performances at BNT were associated with AI values of the middle temporal (ILF/SLF) and parahippocampal (ILF/IFOF) gyri in svPPA patients.

Discussion

Radiomics features depicted distinct pathways of asymmetry in svPPA and nfvPPA involving damage of principal fiber tracts associated with speech and language. Assessing asymmetry of radiomics in PPA allows achieving a deeper insight into the neuroanatomical damage and may represent a candidate severity marker for language impairments in PPA patients.

Radiomic and clinical nomogram for cognitive impairment prediction in Wilson's disease

Objective

To investigate potential biomarkers for the early detection of cognitive impairment in patients with Wilson's disease (WD), we developed a computer-assisted radiomics model to distinguish between WD and WD cognitive impairment.

Methods

Overall, 136 T1-weighted MR images were retrieved from the First Affiliated Hospital of Anhui University of Chinese Medicine, including 77 from patients with WD and 59 from patients with WD cognitive impairment. The images were divided into training and test groups at a ratio of 70:30. The radiomic features of each T1-weighted image were extracted using 3D Slicer software. R software was used to establish clinical and radiomic models based on clinical characteristics and radiomic features, respectively. The receiver operating characteristic profiles of the three models were evaluated to assess their diagnostic accuracy and reliability in distinguishing between WD and WD cognitive impairment. We combined relevant neuropsychological test scores of prospective memory to construct an integrated predictive model and visual nomogram to effectively assess the risk of cognitive decline in patients with WD.

Results

The area under the curve values for distinguishing WD and WD cognitive impairment for the clinical, radiomic, and integrated models were 0.863, 0.922, and 0.935 respectively, indicative of excellent performance. The nomogram based on the integrated model successfully differentiated between WD and WD cognitive impairment.

Conclusion

The nomogram developed in the current study may assist clinicians in the early identification of cognitive impairment in patients with WD. Early intervention following such identification may help improve long-term prognosis and quality of life of these patients.

A Radiomics Approach on Chest CT Distinguishes Primary Lung Cancer from Solitary Lung Metastasis in Colorectal Cancer Patients

PURPOSE

This study utilized a radiomics approach combined with a machine learning algorithm to distinguish primary lung cancer (LC) from solitary lung metastasis (LM) in colorectal cancer (CRC) patients with a solitary pulmonary nodule (SPN).

MATERIALS AND METHODS

In a retrospective study, 239 patients who underwent chest computerized tomography (CT) at three different institutions between 2011 and 2019 and were diagnosed as primary LC or solitary LM were included. The data from the first institution were divided into training and internal testing datasets. The data from the second and third institutions were used as an external testing dataset. Radiomic features were extracted from the intra and perinodular regions of interest (ROI). After a feature selection process, Support vector machine (SVM) was used to train models for classifying between LC and LM. The performances of the SVM classifiers were evaluated with both the internal and external testing datasets. The performances of the model were compared to those of two radiologists who reviewed the CT images of the testing datasets for the binary prediction of LC versus LM.

RESULTS

The SVM classifier trained with the radiomic features from the intranodular ROI and achieved the sensitivity/specificity of 0.545/0.828 in the internal test dataset, and 0.833/0.964 in the external test dataset, respectively. The SVM classifier trained with the combined radiomic features from the intra- and perinodular ROIs achieved the sensitivity/specificity of 0.545/0.966 in the internal test dataset, and 0.833/1.000 in the external test data set, respectively. Two radiologists demonstrated the sensitivity/specificity of 0.545/0.966 and 0.636/0.828 in the internal test dataset, and 0.917/0.929 and 0.833/0.929 in the external test dataset, which were comparable to the performance of the model trained with the combined radiomics features.

CONCLUSION

Our results suggested that the machine learning classifiers trained using radiomics features of SPN in CRC patients can be used to distinguish the primary LC and the solitary LM with a similar level of performance to radiologists.

The impact of harmonization on radiomic features in Parkinson's disease and healthy controls: A multicenter study

Radiomics is a challenging development area in imaging field that is greatly capturing interest of radiologists and neuroscientists. However, radiomics features show a strong non-biological variability determined by different facilities and imaging protocols, limiting the reproducibility and generalizability of analysis frameworks. Our study aimed to investigate the usefulness of harmonization to reduce site-effects on radiomics features over specific brain regions. We selected T1-weighted magnetic resonance imaging (MRI) by using the MRI dataset Parkinson's Progression Markers Initiative (PPMI) from different sites with healthy controls (HC) and Parkinson's disease (PD) patients. First, the investigation of radiomics measure discrepancies were assessed on healthy brain regions-of-interest (ROIs) via a classification pipeline based on LASSO feature selection and support vector machine (SVM) model. Then, a ComBat-based harmonization approach was applied to correct site-effects. Finally, a validation step on PD subjects evaluated diagnostic accuracy before and after harmonization of radiomics data. Results on healthy subjects demonstrated a dependence from site-effects that could be corrected with ComBat harmonization. LASSO regressor after harmonization was unable to select any feature to distinguish controls by site. Moreover, harmonized radiomics features achieved an area under the receiving operating characteristic curve (AUC) of 0.77 (compared to AUC of 0.71 for raw radiomics measures) in distinguish Parkinson's patients from HC. We found a not-negligible site-effect studying radiomics of HC pre- and post-harmonization of features. Our validation study on PD patients demonstrated a significant influence of non-biological noise source in diagnostic performances. Finally, harmonization of multicenter radiomic data represent a necessary step to make analysis pipelines reliable and replicable for multisite neuroimaging studies.

Phantom Study on the Robustness of MR Radiomics Features: Comparing the Applicability of 3D Printed and Biological Phantoms

The objectives of our study were to (a) evaluate the feasibility of using 3D printed phantoms in magnetic resonance imaging (MR) in assessing the robustness and repeatability of radiomic parameters and (b) to compare the results obtained from the 3D printed phantoms to metrics obtained in biological phantoms. To this end, three different 3D phantoms were printed: a Hilbert cube (5 × 5 × 5 cm³) and two cubic quick response (QR) code phantoms (a large phantom (large QR) (5 × 5 × 4 cm³) and a small phantom (small QR) (4 × 4 × 3 cm³)). All 3D printed and biological phantoms (kiwis, tomatoes, and onions) were scanned thrice on clinical 1.5 T and 3 T MR with 1 mm and 2 mm isotropic resolution. Subsequent analyses included analyses of several radiomics indices (RI), their repeatability and reliability were calculated using the coefficient of variation (CV), the relative percentage difference (RPD), and the interclass coefficient (ICC) parameters. Additionally, the readability of QR codes obtained from the MR images was examined with several mobile phones and algorithms. The best repeatability (CV ≤ 10%) is reported for the acquisition protocols with the highest spatial resolution. In general, the repeatability and reliability of RI were better in data obtained at 1.5 T (CV = 1.9) than at 3 T (CV = 2.11). Furthermore, we report good agreements between results obtained for the 3D phantoms and biological phantoms. Finally, analyses of the read-out rate of the QR code revealed better texture analyses for images with a spatial resolution of 1 mm than 2 mm. In conclusion, 3D printing techniques offer a unique solution to create textures for analyzing the reliability of radiomic data from MR scans.

How segmentation methods affect hippocampal radiomic feature accuracy in Alzheimer's disease analysis?

OBJECTIVES

Hippocampal radiomic features (HRFs) can serve as biomarkers in Alzheimer's disease (AD). However, how different hippocampal segmentation methods affect HRFs in AD is still unknown. The aim of the study was to investigate how different segmentation methods affect HRF accuracy in AD analysis.

METHODS

A total of 1650 subjects were identified from the Alzheimer's Disease Neuroimaging Initiative database (ADNI). The mini-mental state examination (MMSE) and Alzheimer's disease assessment scale (ADAS-cog13) were also adopted. After calculating the HRFs of intensity, shape, and textural features from each side of the hippocampus in structural magnetic resonance imaging (sMRI), the consistency of HRFs calculated from 7 different hippocampal segmentation methods was validated, and the performance of machine learning-based classification of AD vs. normal control (NC) adopting the different HRFs was also examined. Additional 571 subjects from the European DTI Study on Dementia database (EDSD) were to validate the consistency of results.

RESULTS

Between different segmentations, HRFs showed a high measurement consistency (R > 0.7), a high significant consistency between NC, mild cognitive impairment (MCI), and AD (T-value plot, R > 0.8), and consistent significant correlations between HRFs and MMSE/ADAS-cog13 (p < 0.05). The best NC vs. AD classification was obtained when the hippocampus was sufficiently segmented by primitive majority voting (threshold = 0.2). High consistent results were reproduced from independent EDSD cohort.

CONCLUSIONS

HRFs exhibited high consistency across different hippocampal segmentation methods, and the best performance in AD classification was obtained when HRFs were extracted by the naïve majority voting method with a more sufficient segmentation and relatively low hippocampus segmentation accuracy.

KEY POINTS

• The hippocampal radiomic features exhibited high measurement/statistical/clinical consistency across different hippocampal segmentation methods. • The best performance in AD classification was obtained when hippocampal radiomics were extracted by the naïve majority voting method with a more sufficient segmentation and relatively low hippocampus segmentation accuracy.

Radiomics Model for Frontotemporal Dementia Diagnosis Using T1-Weighted MRI

Radiomics has been proposed as a useful approach to extrapolate novel morphological and textural information from brain Magnetic resonance images (MRI). Radiomics analysis has shown unique potential in the diagnostic work-up and in the follow-up of patients suffering from neurodegenerative diseases. However, the potentiality of this technique in distinguishing frontotemporal dementia (FTD) subtypes has so far not been investigated. In this study, we explored the usefulness of radiomic features in differentiating FTD subtypes, namely, the behavioral variant of FTD (bvFTD), the non-fluent and/or agrammatic (PNFA) and semantic (svPPA) variants of a primary progressive aphasia (PPA). Classification analyses were performed on 3 Tesla T1-weighted images obtained from the Frontotemporal Lobar Degeneration Neuroimaging Initiative. We included 49 patients with bvFTD, 25 patients with PNFA, 34 patients with svPPA, and 60 healthy controls. Texture analyses were conducted to define the first-order statistic and textural features in cortical and subcortical brain regions. Recursive feature elimination was used to select the radiomics signature for each pairwise comparison followed by a classification framework based on a support vector machine. Finally, 10-fold cross-validation was used to assess classification performances. The radiomics-based approach successfully identified the brain regions typically involved in each FTD subtype, achieving a mean accuracy of more than 80% in distinguishing between patient groups. Note mentioning is that radiomics features extracted in the left temporal regions allowed achieving an accuracy of 91 and 94% in distinguishing patients with svPPA from those with PNFA and bvFTD, respectively. Radiomics features show excellent classification performances in distinguishing FTD subtypes, supporting the clinical usefulness of this approach in the diagnostic work-up of FTD.

Cross-Cultural Longitudinal Study on Cognitive Decline (CLoCODE) for Subjective Cognitive Decline in China and Germany: A Protocol for Study Design

Background: Subjective cognitive decline (SCD) is considered as the first symptomatic manifestation of Alzheimer’s disease (AD), which is also affected by different cultural backgrounds. Establishing cross-cultural prediction models of SCD is challenging. Objective: To establish prediction models of SCD available for both the Chinese and European populations. Methods: In this project, 330 SCD from China and 380 SCD from Germany are intended to be recruited. For all participants, standardized assessments, including clinical, neuropsychological, apolipoprotein E (APOE) genotype, blood, and multi-parameter magnetic resonance imaging (MRI) at baseline will be conducted. Participants will voluntarily undergo amyloid positron emission tomography (PET) and are classified into amyloid-β (Aβ) positive SCD (SCD+) and Aβ negative SCD (SCD-). First, baseline data of all SCD individuals between the two cohorts will be compared. Then, key features associated with brain amyloidosis will be extracted in SCD+ individuals, and the diagnosis model will be established using the radiomics method. Finally, the follow-up visits will be conducted every 12 months and the primary outcome is the conversion to mild cognitive impairment or dementia. After a 4-year follow-up, we will extract factors associated with the conversion risk of SCD using Cox regression analysis. Results: At present, 141 SCD from China and 338 SCD from Germany have been recruited. Initial analysis showed significant differences in demographic information, neuropsychological tests, and regional brain atrophy in SCD compared with controls in both cohorts. Conclusion: This project may be of great value for future implications of SCD studies in different cultural backgrounds. Trial registration: ClinicalTrials.gov, NCT04696315. Registered 3 January 2021.

Hippocampal-amygdalo-ventricular atrophy score: Alzheimer disease detection using normative and pathological lifespan models

In this article, we present an innovative MRI-based method for Alzheimer disease (AD) detection and mild cognitive impairment (MCI) prognostic, using lifespan trajectories of brain structures. After a full screening of the most discriminant structures between AD and normal aging based on MRI volumetric analysis of 3,032 subjects, we propose a novel Hippocampal-Amygdalo-Ventricular Atrophy score (HAVAs) based on normative lifespan models and AD lifespan models. During a validation on three external datasets on 1,039 subjects, our approach showed very accurate detection (AUC ≥ 94%) of patients with AD compared to control subjects and accurate discrimination (AUC = 78%) between progressive MCI and stable MCI (during a 3-year follow-up). Compared to normative modeling, classical machine learning methods and recent state-of-the-art deep learning methods, our method demonstrated better classification performance. Moreover, HAVAs simplicity makes it fully understandable and thus well-suited for clinical practice or future pharmaceutical trials.

Gray-Level Co-occurrence Matrix Analysis for the Detection of Discrete, Ethanol-Induced, Structural Changes in Cell Nuclei: An Artificial Intelligence Approach

Gray-level co-occurrence matrix (GLCM) analysis is a contemporary and innovative computational method for the assessment of textural patterns, applicable in almost any area of microscopy. The aim of our research was to perform the GLCM analysis of cell nuclei in Saccharomyces cerevisiae yeast cells after the induction of sublethal cell damage with ethyl alcohol, and to evaluate the performance of various machine learning (ML) models regarding their ability to separate damaged from intact cells. For each cell nucleus, five GLCM parameters were calculated: angular second moment, inverse difference moment, GLCM contrast, GLCM correlation, and textural variance. Based on the obtained GLCM data, we applied three ML approaches: neural network, random trees, and binomial logistic regression. Statistically significant differences in GLCM features were observed between treated and untreated cells. The multilayer perceptron neural network had the highest classification accuracy. The model also showed a relatively high level of sensitivity and specificity, as well as an excellent discriminatory power in the separation of treated from untreated cells. To the best of our knowledge, this is the first study to demonstrate that it is possible to create a relatively sensitive GLCM-based ML model for the detection of alcohol-induced damage in Saccharomyces cerevisiae cell nuclei.

Radiomics nomogram analysis of T2-fBLADE-TSE in pulmonary nodules evaluation

OBJECTIVES

To develop and validate a radiomics nomogram for differentiating between malignant pulmonary nodules and benign nodules.

METHODS

56 benign and 51 malignant nodules from 96 patients were analyzed using manual segmentation of the T2-fBLADE-TSE, while the nodules signal intensity (SIlesion), lesion muscle ratio (LMR) and nodule size were all measured and recorded. The maximum relevance and minimum redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) were used to select nonzero coefficients and develop the model in pulmonary nodules diagnosis. The radiomics nomogram was also developed. The clinical prediction value was determined by the decision curve analysis (DCA).

RESULTS

The nodule size, SIlesion and LMR of the benign group were 1.78 ± 0.57 cm, 227.50 ± 81.39 and 2.40 ± 1.27 respectively, in contrast to the 2.00 ± 0.64 cm, 232.87 ± 82.21 and 2.17 ± 0.91, respectively, in the malignant group (P = 0.09, 0.60 and 0.579). A total of 13 radiomics features were retained. The Rad-score of the benign nodules group was lower than that of the malignant nodules group (P < 0.001 & 0.049, training & test set). The AUC of radiomics signature for nodules diagnosis was 0.82 (95% CI, 0.73-0.91) in the training set and 0.71 (95% CI, 0.51-0.90) in the test set. A nomogram, consisting of 13 radiomics features and nodule size, produced good prediction in the training set (AUC, 0.82; 95% CI, 0.73-0.91), which was significantly better than that of T2-based quantitative parameters (AUC, 0.62; 95% CI, 0.50-0.75, P = 0.003). In the test set, the performance of radiomics nomogram (AUC, 0.70; 95% CI, 0.51-0.90) was also better than that of T2-based quantitative parameters (AUC, 0.46; 95% CI, 0.25-0.67) (P = 0.145). The DCA showed that radiomics nomogram and T2-based quantitative parameter had overall net benefits, while the performance of nomogram was better.

CONCLUSION

We constructed and validated a T2-fBLADE-TSE-based radiomics nomogram that can help to differentiate between malignant pulmonary nodules and benign nodules.

Prediction of the progression from mild cognitive impairment to Alzheimer's disease using a radiomics-integrated model

Objective:

This study aimed to build and validate a radiomics-integrated model with whole-brain magnetic resonance imaging (MRI) to predict the progression of mild cognitive impairment (MCI) to Alzheimer’s disease (AD).

Methods:

357 patients with MCI were selected from the ADNI database, which is an open-source database for AD with multicentre cooperation, of which 154 progressed to AD during the 48-month follow-up period. Subjects were divided into a training and test group. For each patient, the baseline T₁WI MR images were automatically segmented into white matter, gray matter and cerebrospinal fluid (CSF), and radiomics features were extracted from each tissue. Based on the data from the training group, a radiomics signature was built using logistic regression after dimensionality reduction. The radiomics signatures, in combination with the apolipoprotein E4 (APOE4) and baseline neuropsychological scales, were used to build an integrated model using machine learning. The receiver operating characteristics (ROC) curve and data of the test group were used to evaluate the diagnostic accuracy and reliability of the model, respectively. In addition, the clinical prognostic efficacy of the model was evaluated based on the time of progression from MCI to AD.

Results:

Stepwise logistic regression analysis showed that the APOE4, clinical dementia rating, AD assessment scale, and radiomics signature were independent predictors of MCI progression to AD. The integrated model was constructed based on independent predictors using machine learning. The ROC curve showed that the accuracy of the model in the training and the test sets was 0.814 and 0.807, with a specificity of 0.671 and 0.738, and a sensitivity of 0.822 and 0.745, respectively. In addition, the model had the most significant diagnostic efficacy in predicting MCI progression to AD within 12 months, with an AUC of 0.814, sensitivity of 0.726, and specificity of 0.798.

Conclusion:

The integrated model based on whole-brain radiomics can accurately identify and predict the high-risk population of MCI patients who may progress to AD. Radiomics biomarkers are practical in the precursory stage of such disease.

A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning

Urolithiasis is a common urological disease, and treatment strategy options vary between different stone types. However, accurate detection of stone composition can only be performed in vitro. The management of infection stones is particularly challenging with yet no effective approach to pre-operatively identify infection stones from non-infection stones. Therefore, we aimed to develop a radiomic model for preoperatively identifying infection stones with multicenter validation. In total, 1198 eligible patients with urolithiasis from three centers were divided into a training set, an internal validation set, and two external validation sets. Stone composition was determined by Fourier transform infrared spectroscopy. A total of 1316 radiomic features were extracted from the pre-treatment Computer Tomography images of each patient. Using the least absolute shrinkage and selection operator algorithm, we identified a radiomic signature that achieved favorable discrimination in the training set, which was confirmed in the validation sets. Moreover, we then developed a radiomic model incorporating the radiomic signature, urease-producing bacteria in urine, and urine pH based on multivariate logistic regression analysis. The nomogram showed favorable calibration and discrimination in the training and three validation sets (area under the curve [95% confidence interval], 0.898 [0.840-0.956], 0.832 [0.742-0.923], 0.825 [0.783-0.866], and 0.812 [0.710-0.914], respectively). Decision curve analysis demonstrated the clinical utility of the radiomic model. Thus, our proposed radiomic model can serve as a non-invasive tool to identify urinary infection stones in vivo, which may optimize disease management in urolithiasis and improve patient prognosis.

Multiclass diagnosis of stages of Alzheimer's disease using linear discriminant analysis scoring for multimodal data

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and mild cognitive impairment (MCI) is a transitional stage between normal control (NC) and AD. A multiclass classification of AD is a difficult task because there are multiple similarities between neighboring groups. The performance of classification can be improved by using multimodal data, but the improvement could be limited with inefficient fusion of multimodal data. This study aims to develop a framework for AD multiclass diagnosis with a linear discriminant analysis (LDA) scoring method to fuse multimodal data more efficiently. Magnetic resonance imaging, positron emission tomography, cerebrospinal fluid biomarkers, and genetic features were first preprocessed by performing age correction, feature selection, and feature reduction. Then, they were individually scored using LDA, and the scores that represent the AD pathological progress in different modalities were obtained. Finally, an extreme learning machine-based decision tree was established to perform multiclass diagnosis using these scores. The experiments were conducted on the AD Neuroimaging Initiative dataset, and accuracies of 66.7% and 57.3% and F1-scores of 64.9% and 55.7% were achieved in three- and four-way classifications, respectively. The results also showed that the proposed framework achieved a better performance than the method that did not score multimodal data and the methods in previous studies, thereby indicating that the LDA scoring strategy is an efficient way for multimodalities fusion in AD multiclass classification.

An Effective Brain Imaging Biomarker for AD and aMCI: ALFF in Slow-5 Frequency Band

BACKGROUND

As a potential brain imaging biomarker, amplitude of low frequency fluctuation (ALFF) has been used as a feature to distinguish patients with Alzheimer's disease (AD) and amnestic mild cognitive impairment (aMCI) from normal controls (NC). However, it remains unclear whether the frequency-dependent pattern of ALFF alterations can effectively distinguish the different phases of the disease.

METHODS

In the present study, 52 AD and 50 aMCI patients were enrolled together with 43 NC in total. The ALFF values were calculated in the following three frequency bands: classical (0.01-0.08 Hz), slow-4 (0.027-0.073 Hz) and slow-5 (0.01-0.027 Hz) for the three different groups. Subsequently, the local functional abnormalities were employed as features to examine the effect of classification among AD, aMCI and NC using a support vector machine (SVM).

RESULTS

We found that the among-group differences of ALFF in the different frequency bands were mainly located in the left hippocampus (HP), right HP, bilateral posterior cingulate cortex (PCC) and bilateral precuneus (PCu), left angular gyrus (AG) and left medial prefrontal cortex (mPFC). When the local functional abnormalities were employed as features, we identified that the ALFF in the slow-5 frequency band showed the highest accuracy to distinguish among the three groups.

CONCLUSION

These findings may deepen our understanding of the pathogenesis of AD and suggest that slow-5 frequency band may be helpful to explore the pathogenesis and distinguish the phases of this disease.