Radiomics: a novel feature extraction method for brain neuron degeneration disease using ¹⁸F-FDG PET imaging and its implementation for Alzheimer’s disease and mild cognitive impairment

Abstract

Background: Alzheimer’s disease (AD) is the most common form of progressive and irreversible dementia, and accurate diagnosis of AD at its prodromal stage is clinically important. Currently, computer-aided diagnosis of AD and mild cognitive impairment (MCI) using 18F-fluorodeoxy-glucose positron emission tomography (18F-FDG PET) imaging is usually based on low-level imaging features or deep learning methods, which have difficulties in achieving sufficient classification accuracy or lack clinical significance. This research therefore aimed to implement a new feature extraction method known as radiomics, to improve the classification accuracy and discover high-order features that can reveal pathological information. Methods: In this study, 18F-FDG PET and clinical assessments were collected in a cohort of 422 individuals [including 130 with AD, 130 with MCI, and 162 healthy controls (HCs)] from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and 44 individuals (including 22 with AD, and 22 HCs) from Huashan Hospital, Shanghai, China. First, we performed a group comparison using a two-sample Student’s t test to determine the regions of interest (ROIs) based on 30 AD patients and 30 HCs from ADNI cohorts. Second, based on two time scans of 32 HCs from ADNI cohorts, we used Cronbach’s alpha coefficient for radiomic feature stability analyses. Pearson’s correlation coefficients were regarded as a feature selection criterion, to select effective features associated with the clinical cognitive scale [clinical dementia rating scale in its sum of boxes (CDRSB); Alzheimer’s disease assessment scale (ADAS)] with 500-times cross-validation. Finally, a support vector machine (SVM) was used to test the ability of the radiomic features to classify HCs, MCI and AD patients. Results: As a result, we identified brain regions which were mainly distributed in the temporal, occipital and frontal areas as ROIs. A total of 168 radiomic features of AD were stable (alpha > 0.8). The classification experiment led to maximal accuracies of 91.5%, 83.1% and 85.9% for classifying AD versus HC, MCI versus HCs and AD versus MCI. Conclusion: The research in this paper proved that the novel approach based on high-order radiomic features extracted from 18F-FDG PET brain images that can be used for AD and MCI computer-aided diagnosis.

Parkinson's Disease Diagnosis Using Neostriatum Radiomic Features Based on T2-Weighted Magnetic Resonance Imaging

“…In the early years of radiomics, this new approach has been widely applied in oncology fields and has shown potential benefits for tumor grading and pathological classification (15,16). However, given its power in capturing the microstructural changes in tissues and its correlation with clinical endpoints (17) and age progression (18,19), the use of radiomics is expected to increase in neurodegenerative disorders (20). Presently, radiomics has been applied to the diagnosis of neurodegenerative diseases, including Alzheimer's disease (AD), amyotrophic lateral sclerosis, and Machado-Joseph disease with conventional MRI (21)(22)(23)(24)(25), which have similar pathological changes with PD, such as atrophy, abnormal proteins, or iron deposition in many brain regions.…”

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

“…A study by Ashrafinia et al showed that ZSN extracted from 99m Tc-Sestamibi Myocardial-Perfusion SPECT (MPS) images showed high reproducibility [ 44 ]. Another recent study by Li et al on FDG PET radiomics analysis showed that ZSN is a stable feature [ 45 ]. The phantom repeatability and reproducibility study provides robust features for further radiomics modeling that has the potential to generalize to PET images reconstructed at other institutions where different reconstruction settings might have been applied.…”

Tumor Response Prediction in 90Y Radioembolization with PET-based Radiomics Features and Absorbed Dose Metrics

“…A study by Ashrafinia et al showed that ZSN extracted from ⁹⁹ᵐTc-Sestamibi Myocardial-Perfusion SPECT (MPS) images showed high reproducibility [37]. Another recent study by Li et al on FDG PET radiomics analysis, showed that ZSN is a stable feature [38].…”