Longitudinal clustering analysis and prediction of Parkinson's disease progression using radiomics and hybrid machine learning

Machine learning predictions of tumor progression: How reliable are we?

BACKGROUND

Cancer continues to pose significant challenges in healthcare due to the complex nature of tumor progression. In this digital era, artificial intelligence has emerged as a powerful tool that can potentially transform multiple aspects of cancer care.

METHODS

In the current study, we conducted a comprehensive literature search across databases such as PubMed, Scopus, and IEEE Xplore. Studies published between 2014 and 2024 were considered. The selection process involved a systematic screening based on predefined inclusion and exclusion criteria. Studies were included if they focused on applying machine learning techniques for tumor progression modeling, diagnosis, or prognosis, were published in peer-reviewed journals or conference proceedings, were available in English, and presented experimental results, simulations, or real-world applications. In total, 87 papers were included in this review, ensuring a diverse and representative analysis of the field. A workflow is included to illustrate the procedure followed to achieve this aim.

RESULTS

This review delves into the cutting-edge applications of machine learning (ML), including supervised learning methods like Support Vector Machines and Random Forests, as well as advanced deep learning (DL). It focuses on the integration of ML into oncological research, particularly its application in tumor progression through the tumor microenvironment, genetic data, histopathological data, and radiological data. This work provides a critical analysis of the challenges associated with the reliability and accuracy of ML models, which limit their clinical integration.

CONCLUSION

This review offers expert insights and strategies to address these challenges in order to improve the robustness and applicability of ML in real-world oncology settings. By emphasizing the potential for personalized cancer treatment and bridging gaps between technology and clinical needs, this review serves as a comprehensive resource for advancing the integration of ML models into clinical oncology.

Neuroimaging-based data-driven subtypes of spatiotemporal atrophy due to Parkinson's disease

Parkinson's disease is the second most common neurodegenerative disease. Despite this, there are no robust biomarkers to predict progression, and understanding of disease mechanisms is limited. We used the Subtype and Stage Inference algorithm to characterize Parkinson's disease heterogeneity in terms of spatiotemporal subtypes of macroscopic atrophy detectable on T1-weighted MRI-a successful approach used in other neurodegenerative diseases. We trained the model on covariate-adjusted cortical thicknesses and subcortical volumes from the largest known T1-weighted MRI dataset in Parkinson's disease, Enhancing Neuroimaging through Meta-Analysis consortium Parkinson's Disease dataset (n = 1100 cases). We tested the model by analyzing clinical progression over up to 9 years in openly-available data from people with Parkinson's disease from the Parkinson's Progression Markers Initiative (n = 584 cases). Under cross-validation, our analysis supported three spatiotemporal atrophy subtypes, named for the location of the earliest affected regions as: 'Subcortical' (n = 359, 33%), 'Limbic' (n = 237, 22%) and 'Cortical' (n = 187, 17%). A fourth subgroup having sub-threshold/no atrophy was named 'Sub-threshold atrophy' (n = 317, 29%). Statistical differences in clinical scores existed between the no-atrophy subgroup and the atrophy subtypes, but not among the atrophy subtypes. This suggests that the prime T1-weighted MRI delineator of clinical differences in Parkinson's disease is atrophy severity, rather than atrophy location. Future work on unravelling the biological and clinical heterogeneity of Parkinson's disease should leverage more sensitive neuroimaging modalities and multimodal data.

Radiomics across modalities: a comprehensive review of neurodegenerative diseases

Radiomics allows extraction from medical images of quantitative features that are able to reveal tissue patterns that are generally invisible to human observers. Despite the challenges in visually interpreting radiomic features and the computational resources required to generate them, they hold significant value in downstream automated processing. For instance, in statistical or machine learning frameworks, radiomic features enhance sensitivity and specificity, making them indispensable for tasks such as diagnosis, prognosis, prediction, monitoring, image-guided interventions, and evaluating therapeutic responses. This review explores the application of radiomics in neurodegenerative diseases, with a focus on Alzheimer's disease, Parkinson's disease, Huntington's disease, and multiple sclerosis. While radiomics literature often focuses on magnetic resonance imaging (MRI) and computed tomography (CT), this review also covers its broader application in nuclear medicine, with use cases of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) radiomics. Additionally, we review integrated radiomics, where features from multiple imaging modalities are fused to improve model performance. This review also highlights the growing integration of radiomics with artificial intelligence and the need for feature standardisation and reproducibility to facilitate its translation into clinical practice.

Radiomics score derived from T1-w/T2-w ratio image can predict motor symptom progression in Parkinson's disease

OBJECTIVES

To clarify the association between a radiomics score (Rad-score) derived from T1-weighted signal intensity to T2-weighted signal intensity (T1-w/T2-w) ratio images and the progression of motor symptoms in Parkinson's disease (PD).

MATERIALS AND METHODS

This retrospective study included patients with PD enrolled in the Parkinson's Progression Markers Initiative. The Movement Disorders Society-Unified Parkinson's Disease Rating Scale Part III score ≥ 33 and/or Hoehn and Yahr stage ≥ 3 indicated motor function decline. The Rad-score was constructed using radiomics features extracted from T1-w/T2-w ratio images. The Kaplan-Meier analysis and Cox regression analyses were used to assess the time differences in motor function decline between the high and low Rad-score groups.

RESULTS

A total of 171 patients with PD were divided into training (n = 101, mean age at baseline, 61.6 ± 9.3 years) and testing (n = 70, mean age at baseline, 61.6 ± 10 years). The patients in the high Rad-score group had a shorter time to motor function decline than those in the low Rad-score group in the training dataset (log-rank test, p < 0.001) and testing dataset (log-rank test, p < 0.001). The multivariate Cox regression using the Rad-score and clinical factors revealed a significant association between the Rad-score and motor function decline in the training dataset (HR = 2.368, 95%CI:1.423-3.943, p < 0.001) and testing dataset (HR = 2.931, 95%CI:1.472-5.837, p = 0.002).

CONCLUSION

Rad-scores based on radiomics features derived from T1-w/T2-w ratio images were associated with the progression of motor symptoms in PD.

CLINICAL RELEVANCE STATEMENT

The radiomics score derived from the T1-weighted/T2-weighted ratio images offers a predictive tool for assessing the progression of motor symptom in patients with PD.

KEY POINTS

Radiomics score derived from T1-weighted/T2-weighted ratio images is correlated with the motor symptoms of Parkinson's disease. A high radiomics score correlated with faster motor function decline in patients with Parkinson's disease. The proposed radiomics score offers predictive insight into the progression of motor symptoms of Parkinson's disease.

Radiomics incorporating deep features for predicting Parkinson's disease in 123I-Ioflupane SPECT

PURPOSE

123I-Ioflupane SPECT is an effective tool for the diagnosis and progression assessment of Parkinson's disease (PD). Radiomics and deep learning (DL) can be used to track and analyze the underlying image texture and features to predict the Hoehn-Yahr stages (HYS) of PD. In this study, we aim to predict HYS at year 0 and year 4 after the first diagnosis with combined imaging, radiomics and DL-based features using 123I-Ioflupane SPECT images at year 0.

METHODS

In this study, 161 subjects from the Parkinson's Progressive Marker Initiative database underwent baseline 3T MRI and 123I-Ioflupane SPECT, with HYS assessment at years 0 and 4 after first diagnosis. Conventional imaging features (IF) and radiomic features (RaF) for striatum uptakes were extracted from SPECT images using MRI- and SPECT-based (SPECT-V and SPECT-T) segmentations respectively. A 2D DenseNet was used to predict HYS of PD, and simultaneously generate deep features (DF). The random forest algorithm was applied to develop models based on DF, RaF, IF and combined features to predict HYS (stage 0, 1 and 2) at year 0 and (stage 0, 1 and ≥ 2) at year 4, respectively. Model predictive accuracy and receiver operating characteristic (ROC) analysis were assessed for various prediction models.

RESULTS

For the diagnostic accuracy at year 0, DL (0.696) outperformed most models, except DF + IF in SPECT-V (0.704), significantly superior based on paired t-test. For year 4, accuracy of DF + RaF model in MRI-based method is the highest (0.835), significantly better than DF + IF, IF + RaF, RaF and IF models. And DL (0.820) surpassed models in both SPECT-based methods. The area under the ROC curve (AUC) highlighted DF + RaF model (0.854) in MRI-based method at year 0 and DF + RaF model (0.869) in SPECT-T method at year 4, outperforming DL models, respectively. And then, there was no significant differences between SPECT-based and MRI-based segmentation methods except for the imaging feature models.

CONCLUSION

The combination of radiomic and deep features enhances the prediction accuracy of PD HYS compared to only radiomics or DL. This suggests the potential for further advancements in predictive model performance for PD HYS at year 0 and year 4 after first diagnosis using 123I-Ioflupane SPECT images at year 0, thereby facilitating early diagnosis and treatment for PD patients. No significant difference was observed in radiomics results obtained between MRI- and SPECT-based striatum segmentations for radiomic and deep features.

Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics

OBJECTIVE

This study used unsupervised machine learning (UML) cluster analysis to explore clinical phenotypes of endovascular aortic repair (EVAR) for abdominal aortic aneurysm (AAA) patients based on radiomics.

METHOD

We retrospectively reviewed 1785 patients with infra-renal AAA who underwent elective EVAR procedures between January 2010 and December 2020. Pyradiomics was used to extract the radiomics features. Statistical analysis was applied to determine the radiomics features that related to severe adverse events (SAEs) after EVAR. The selected features were used for UML cluster analysis in training set and validation in test set. Comparison of basic characteristics and radiomics features of different clusters. The Kaplan-Meier analysis was conducted to generate the cumulative incidence of freedom from SAEs rate.

RESULT

A total of 1180 patients were enrolled. During the follow-up, 353 patients experienced EVAR-related SAEs. In total, 1223 radiomics features were extracted from each patient, of which 23 radiomics features were finally preserved to identify different clinical phenotypes. 944 patients were allocated to the training set. Three clusters were identified in training set, in which patients had identical clinical characteristics and morphological features, while varied considerably of selected radiomics features. This encouraging performance was further approved in the test set. In addition, each cluster was well differentiated from other clusters and Kaplan-Meier analysis showed significant differences of freedom from SAEs rate between different clusters both in the training (p = .0216) and test sets (p = .0253).

CONCLUSION

Based on radiomics, UML cluster analysis can identify clinical phenotypes in EVAR patients with distinct long-term outcomes.

Longitudinal clustering of Life's Essential 8 health metrics: application of a novel unsupervised learning method in the CARDIA study

OBJECTIVE

Changes in cardiovascular health (CVH) during the life course are associated with future cardiovascular disease (CVD). Longitudinal clustering analysis using subgraph augmented non-negative matrix factorization (SANMF) could create phenotypic risk profiles of clustered CVH metrics.

MATERIALS AND METHODS

Life's Essential 8 (LE8) variables, demographics, and CVD events were queried over 15 ears in 5060 CARDIA participants with 18 years of subsequent follow-up. LE8 subgraphs were mined and a SANMF algorithm was applied to cluster frequently occurring subgraphs. K-fold cross-validation and diagnostics were performed to determine cluster assignment. Cox proportional hazard models were fit for future CV event risk and logistic regression was performed for cluster phenotyping.

RESULTS

The cohort (54.6% female, 48.7% White) produced 3 clusters of CVH metrics: Healthy & Late Obesity (HLO) (29.0%), Healthy & Intermediate Sleep (HIS) (43.2%), and Unhealthy (27.8%). HLO had 5 ideal LE8 metrics between ages 18 and 39 years, until BMI increased at 40. HIS had 7 ideal LE8 metrics, except sleep. Unhealthy had poor levels of sleep, smoking, and diet but ideal glucose. Race and employment were significantly different by cluster (P < .001) but not sex (P = .734). For 301 incident CV events, multivariable hazard ratios (HRs) for HIS and Unhealthy were 0.73 (0.53-1.00, P = .052) and 2.00 (1.50-2.68, P < .001), respectively versus HLO. A 15-year event survival was 97.0% (HIS), 96.3% (HLO), and 90.4% (Unhealthy, P < .001).

DISCUSSION AND CONCLUSION

SANMF of LE8 metrics identified 3 unique clusters of CVH behavior patterns. Clustering of longitudinal LE8 variables via SANMF is a robust tool for phenotypic risk assessment for future adverse cardiovascular events.

Robustly uncovering the heterogeneity of neurodegenerative disease by using data-driven subtyping in neuroimaging: A review

Neurodegenerative diseases are associated with heterogeneity in genetics, pathology, and clinical manifestation. Understanding this heterogeneity is particularly relevant for clinical prognosis and stratifying patients for disease modifying treatments. Recently, data-driven methods based on neuroimaging have been applied to investigate the subtyping of neurodegenerative disease, helping to disentangle this heterogeneity. We reviewed brain-based subtyping studies in aging and representative neurodegenerative diseases, including Alzheimer's disease, mild cognitive impairment, frontotemporal dementia, and Lewy body dementia, from January 2000 to November 2022. We summarized clustering methods, validation, robustness, reproducibility, and clinical relevance of 71 eligible studies in the present study. We found vast variations in approaches between studies, including ten neuroimaging modalities, 24 cluster algorithms, and 41 methods of cluster number determination. The clinical relevance of subtyping studies was evaluated by summarizing the analysis method of clinical measurements, showing a relatively low clinical utility in the current studies. Finally, we conclude that future studies of heterogeneity in neurodegenerative disease should focus on validation, comparison between subtyping approaches, and prioritise clinical utility.

Disentangling the complex landscape of sleep-wake disorders with data-driven phenotyping: A study of the Bernese center

BACKGROUND AND PURPOSE

The diagnosis of sleep-wake disorders (SWDs) is challenging because of the existence of only few accurate biomarkers and the frequent coexistence of multiple SWDs and/or other comorbidities. The aim of this study was to assess in a large cohort of well-characterized SWD patients the potential of a data-driven approach for the identification of SWDs.

METHODS

We included 6958 patients from the Bernese Sleep Registry and 300 variables/biomarkers including questionnaires, results of polysomnography/vigilance tests, and final clinical diagnoses. A pipeline, based on machine learning, was created to extract and cluster the clinical data. Our analysis was performed on three cohorts: patients with central disorders of hypersomnolence (CDHs), a full cohort of patients with SWDs, and a clean cohort without coexisting SWDs.

RESULTS

A first analysis focused on the cohort of patients with CDHs and revealed four patient clusters: two clusters for narcolepsy type 1 (NT1) but not for narcolepsy type 2 or idiopathic hypersomnia. In the full cohort of SWDs, nine clusters were found: four contained patients with obstructive and central sleep apnea syndrome, one with NT1, and four with intermixed SWDs. In the cohort of patients without coexisting SWDs, an additional cluster of patients with chronic insomnia disorder was identified.

CONCLUSIONS

This study confirms the existence of clear clusters of NT1 in CDHs, but mainly intermixed groups in the full spectrum of SWDs, with the exception of sleep apnea syndromes and NT1. New biomarkers are needed for better phenotyping and diagnosis of SWDs.

Applications of machine learning and deep learning in SPECT and PET imaging: General overview, challenges and future prospects

The integration of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging techniques with machine learning (ML) algorithms, including deep learning (DL) models, is a promising approach. This integration enhances the precision and efficiency of current diagnostic and treatment strategies while offering invaluable insights into disease mechanisms. In this comprehensive review, we delve into the transformative impact of ML and DL in this domain. Firstly, a brief analysis is provided of how these algorithms have evolved and which are the most widely applied in this domain. Their different potential applications in nuclear imaging are then discussed, such as optimization of image adquisition or reconstruction, biomarkers identification, multimodal fusion and the development of diagnostic, prognostic, and disease progression evaluation systems. This is because they are able to analyse complex patterns and relationships within imaging data, as well as extracting quantitative and objective measures. Furthermore, we discuss the challenges in implementation, such as data standardization and limited sample sizes, and explore the clinical opportunities and future horizons, including data augmentation and explainable AI. Together, these factors are propelling the continuous advancement of more robust, transparent, and reliable systems.

Automatic Localization of Key Structures for Subthalamic Nucleus-Deep Brain Stimulation Surgery via Prior-Enhanced Multi-Object Magnetic Resonance Imaging Segmentation

BACKGROUND

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an established and effective neurosurgical treatment for relieving motor symptoms in Parkinson disease. The localization of key brain structures is critical to the success of DBS surgery. However, in clinical practice, this process is heavily dependent on the radiologist's experience.

METHODS

In this study, we propose an automatic localization method of key structures for STN-DBS surgery via prior-enhanced multi-object magnetic resonance imaging segmentation. We use the U-Net architecture for the multi-object segmentation, including STN, red nucleus, brain sulci, gyri, and ventricles. To address the challenge that only half of the brain sulci and gyri locate in the upper area, potentially causing interference in the lower area, we perform region of interest detection and ensemble joint processing to enhance the segmentation performance of brain sulci and gyri.

RESULTS

We evaluate the segmentation accuracy by comparing our method with other state-of-the-art machine learning segmentation methods. The experimental results show that our approach outperforms state-of-the-art methods in terms of segmentation performance. Moreover, our method provides effective visualization of key brain structures from a clinical application perspective and can reduce the segmentation time compared with manual delineation.

CONCLUSIONS

Our proposed method uses deep learning to achieve accurate segmentation of the key structures more quickly than and with comparable accuracy to human manual segmentation. Our method has the potential to improve the efficiency of surgical planning for STN-DBS.

Predicting Ambulatory Capacity in Parkinson's Disease to Analyze Progression, Biomarkers, and Trial Design

BACKGROUND

In Parkinson's disease (PD), gait and balance is impaired, relatively resistant to available treatment and associated with falls and disability. Predictive models of ambulatory progression could enhance understanding of gait/balance disturbances and aid in trial design.

OBJECTIVES

To predict trajectories of ambulatory abilities from baseline clinical data in early PD, relate trajectories to clinical milestones, compare biomarkers, and evaluate trajectories for enrichment of clinical trials.

METHODS

Data from two multicenter, longitudinal, observational studies were used for model training (Tracking Parkinson's, n = 1598) and external testing (Parkinson's Progression Markers Initiative, n = 407). Models were trained and validated to predict individuals as having a "Progressive" or "Stable" trajectory based on changes of ambulatory capacity scores from the Movement Disorders Society Unified Parkinson's Disease Rating Scale parts II and III. Survival analyses compared time-to-clinical milestones and trial outcomes between predicted trajectories.

RESULTS

On external evaluation, a support vector machine model predicted Progressive trajectories using baseline clinical data with an accuracy, weighted-F1 (proportionally weighted harmonic mean of precision and sensitivity), and sensitivity/specificity of 0.735, 0.799, and 0.688/0.739, respectively. Over 4 years, the predicted Progressive trajectory was more likely to experience impaired balance, loss of independence, impaired function and cognition. Baseline dopamine transporter imaging and select biomarkers of neurodegeneration were significantly different between predicted trajectory groups. For an 18-month, randomized (1:1) clinical trial, sample size savings up to 30% were possible when enrollment was enriched for the Progressive trajectory versus no enrichment.

CONCLUSIONS

It is possible to predict ambulatory abilities from clinical data that are associated with meaningful outcomes in people with early PD. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Preoperative differentiation of pancreatic cystic neoplasm subtypes on computed tomography radiomics

BACKGROUND

Serous cystic neoplasm (SCN), mucinous cystic neoplasm (MCN), and intraductal papillary mucinous neoplasm (IPMN) comprise a large proportion of pancreatic cystic neoplasms (PCNs). Patients with MCN and IPMN require surgery due to the potential of malignant transformation, whereas those with SCN require periodic surveillance. However, the differential diagnosis of patients with PCNs before treatment remains a great challenge for all surgeons. Therefore, the establishment of a reliable diagnostic tool is urgently required for the improvement of precision diagnostics.

METHODS

Between February 2015 and December 2020, 143 consecutive patients with PCNs who were confirmed by postoperative pathology were retrospectively included in the study cohort, then randomized into development and test cohorts at a ratio of 7:3. The predictors of preoperative clinical-radiologic parameters were evaluated by univariate and multivariable logistic regression analyses. A total of 1,218 radiomics features were computationally extracted from the enhanced computed tomography (CT) scans of the tumor region, and a radiomics signature was established by the random forest algorithm. In the development cohort, multi- and binary-class radiomics models integrating preoperative variables and radiomics features were constructed to distinguish between the 3 types of PCNs. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the predictive efficiency of the model. An independent internal test cohort was applied to validate the classification models.

RESULTS

All preoperative prediction models were built by integrating the radiomics signature with 13 diagnosis-related radiomics features and 3 important clinical-radiologic parameters: age, sex, and tumor diameter. The multiclass prediction model presented an overall accuracy of 0.804 in the development cohort and 0.707 in the test cohort. The binary-class prediction models displayed higher overall accuracies of 0.853, 0.866, and 0.928 in the development dataset and 0.750, 0.839, and 0.889 in the test dataset. In the test cohort, the binary-class radiomics models showed better predictive performances {AUC =0.914 [95% confidence interval (CI): 0.786 to 1.000], 0.863 (95% CI: 0.714 to 0.941), and 0.926 (95% CI: 0.824 to 1.000)} than the multiclass radiomics model [AUC =0.850 (95% CI: 0.696 to 1.000)], with a large net benefit in the decision curve analysis (DCA). The radiomics-based nomogram provided the correct predicted probability for the diagnosis of PCNs.

CONCLUSIONS

The proposed radiomics models with clinical-radiologic parameters and radiomics features help to predict the accurate diagnosis among PCNs to advance personalized medicine.

Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer

BACKGROUND

Numerous features are commonly generated in radiomics applications as applied to medical imaging, and identification of robust radiomics features (RFs) can be an important step to derivation of reliable, reproducible solutions. In this work, we utilize a tensor radiomics (TR) framework, where numerous fusions are explored, to generate different flavours of RFs, and we aimed to identify RFs that are robust to fusion techniques in head and neck cancer. Overall, we aimed to predict progression-free survival (PFS) using Hybrid Machine Learning Systems (HMLS) and reproducible RFs.

METHODS

The study was performed on 408 patients with head and neck cancer from The Cancer Imaging Archive. After image preprocessing, 15 fusion techniques were employed to combine Positron Emission Tomography (PET) and Computed Tomography (CT) images. Subsequently, 215 RFs were extracted through a standardized radiomics software, with 17 'flavours' generated using PET-only, CT-only, and 15 fused PET&CT images. The variability of RFs across flavours was studied using the Intraclass Correlation Coefficient (ICC). Furthermore, the features were categorized into seven reliability groups, 106 reproducible RFs with ICC>0.75 were selected, highly correlated flavours were removed, Principal Component Analysis was used to convert 17 flavours to 1 attribute, the polynomial function was utilized to increase RFs, and Analysis of variance (ANOVA) was used to select the relevant attributes. Finally, 3 classifiers including Random Forest (RFC), Logistic regression (LR), and Multi-layer perceptron were applied to the preselected relevant attributes to predict binary PFS. In 5-fold cross-validation, 80% of 4 divisions were utilized to train the model, and the remaining 20% was utilized to evaluate the model. Further, the remaining fold was used for external nested testing.

RESULTS

Reliability analysis indicated that most morphological features belong to the high-reliability category. By contrast, local intensity and statistical features extracted from images belong to the low-reliability category. In the tensor framework, the highest 5-fold cross-validation accuracy of 76.7%±3.3% with an external nested testing of 70.6%±6.7% resulted from the reproducible TR+polynomial function+ANOVA+LR algorithm while the accuracy of 70.0%±4.2% with the external nested testing of 67.7%±4.9% was achieved through the PCA fusion+RFC (non-tensor paradigm).

CONCLUSIONS

This study demonstrated that using reproducible RFs as utilized within a tensor fusion radiomics framework, linked with ANOVA and LR, added value to prediction of progression-free survival outcome in head and neck cancer patients.

Comparative study of bilateral putamen for patients with severe Parkinson's disease detected by 1H magnetic resonance spectroscopy

Background

The diagnosis of Parkinson's disease (PD) is challenging because the clinical symptoms overlap with other neurodegenerative diseases. The discovery of reliable biomarkers is highly expected to facilitate clinical diagnosis. Through the analysis of the 1H magnetic resonance spectroscopy (1H-MRS) in the putamen, the purpose of the study was to discuss the possibility of the difference in metabolite concentrations between the left and right putamen as biomarkers for patients with severe PD.

Methods

We collected 1H-MRS of unilateral or bilateral putamen from 41 patients and used the independent sample t-test and paired t-test to analyze 4 metabolite concentrations, including choline (Cho), total N-acetyl aspartate (tNAA), total creatine (tCr), and combined glutamate and glutamine; Bonferroni correction was used to correct P values for multiple comparisons. We designed 4 controlled experiments as follows: (I) PD patients versus healthy controls (HCs) in the left putamen; (II) PD patients versus HCs in the right putamen; (III) the left putamen versus the right putamen for PD patients; and (IV) the left putamen versus the right putamen for HCs.

Results

No statistically significant differences (P>0.05) were detected among 4 metabolites in the ipsilateral and bilateral putamen for the PD and HCs groups, except for tCr in the left putamen (PD 6.426±0.557, HCs 6.026±0.460, P=0.046) for ipsilateral comparisons.

Conclusions

In the bilateral putamen of severe PD patients, there was no statistically significant difference in the 4 metabolites. The difference (P<0.05) in tCr in the left putamen might be a potential biomarker to distinguish HCs from severe patients in clinic. This might provide a reference for the clinical diagnosis and acquisition strategy of 1H-MRS in severe PD.

Prediction of Parkinson's disease pathogenic variants using hybrid Machine learning systems and radiomic features

PURPOSE

In Parkinson's disease (PD), 5-10% of cases are of genetic origin with mutations identified in several genes such as leucine-rich repeat kinase 2 (LRRK2) and glucocerebrosidase (GBA). We aim to predict these two gene mutations using hybrid machine learning systems (HMLS), via imaging and non-imaging data, with the long-term goal to predict conversion to active disease.

METHODS

We studied 264 and 129 patients with known LRRK2 and GBA mutations status from PPMI database. Each dataset includes 513 features such as clinical features (CFs), conventional imaging features (CIFs) and radiomic features (RFs) extracted from DAT-SPECT images. Features, normalized by Z-score, were univariately analyzed for statistical significance by the t-test and chi-square test, adjusted by Benjamini-Hochberg correction. Multiple HMLSs, including 11 features extraction (FEA) or 10 features selection algorithms (FSA) linked with 21 classifiers were utilized. We also employed Ensemble Voting (EV) to classify the genes.

RESULTS

For prediction of LRRK2 mutation status, a number of HMLSs resulted in accuracies of 0.98 ± 0.02 and 1.00 in 5-fold cross-validation (80% out of total data points) and external testing (remaining 20%), respectively. For predicting GBA mutation status, multiple HMLSs resulted in high accuracies of 0.90 ± 0.08 and 0.96 in 5-fold cross-validation and external testing, respectively. We additionally showed that SPECT-based RFs added value to the specific prediction of of GBA mutation status.

CONCLUSION

We demonstrated that combining medical information with SPECT-based imaging features, and optimal utilization of HMLS can produce excellent prediction of the mutations status in PD patients.

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

BACKGROUND

Although handcrafted radiomics features (RF) are commonly extracted via radiomics software, employing deep features (DF) extracted from deep learning (DL) algorithms merits significant investigation. Moreover, a "tensor'' radiomics paradigm where various flavours of a given feature are generated and explored can provide added value. We aimed to employ conventional and tensor DFs, and compare their outcome prediction performance to conventional and tensor RFs.

METHODS

408 patients with head and neck cancer were selected from TCIA. PET images were first registered to CT, enhanced, normalized, and cropped. We employed 15 image-level fusion techniques (e.g., dual tree complex wavelet transform (DTCWT)) to combine PET and CT images. Subsequently, 215 RFs were extracted from each tumor in 17 images (or flavours) including CT only, PET only, and 15 fused PET-CT images through the standardized-SERA radiomics software. Furthermore, a 3 dimensional autoencoder was used to extract DFs. To predict the binary progression-free-survival-outcome, first, an end-to-end CNN algorithm was employed. Subsequently, we applied conventional and tensor DFs vs. RFs as extracted from each image to three sole classifiers, namely multilayer perceptron (MLP), random-forest, and logistic regression (LR), linked with dimension reduction algorithms.

RESULTS

DTCWT fusion linked with CNN resulted in accuracies of 75.6 ± 7.0% and 63.4 ± 6.7% in five-fold cross-validation and external-nested-testing, respectively. For the tensor RF-framework, polynomial transform algorithms + analysis of variance feature selector (ANOVA) + LR enabled 76.67 ± 3.3% and 70.6 ± 6.7% in the mentioned tests. For the tensor DF framework, PCA + ANOVA + MLP arrived at 87.0 ± 3.5% and 85.3 ± 5.2% in both tests.

CONCLUSIONS

This study showed that tensor DF combined with proper machine learning approaches enhanced survival prediction performance compared to conventional DF, tensor and conventional RF, and end-to-end CNN frameworks.

Prediction of Cognitive Decline in Parkinson's Disease Using Clinical and DAT SPECT Imaging Features, and Hybrid Machine Learning Systems

BACKGROUND

We aimed to predict Montreal Cognitive Assessment (MoCA) scores in Parkinson's disease patients at year 4 using handcrafted radiomics (RF), deep (DF), and clinical (CF) features at year 0 (baseline) applied to hybrid machine learning systems (HMLSs).

METHODS

297 patients were selected from the Parkinson's Progressive Marker Initiative (PPMI) database. The standardized SERA radiomics software and a 3D encoder were employed to extract RFs and DFs from single-photon emission computed tomography (DAT-SPECT) images, respectively. The patients with MoCA scores over 26 were indicated as normal; otherwise, scores under 26 were indicated as abnormal. Moreover, we applied different combinations of feature sets to HMLSs, including the Analysis of Variance (ANOVA) feature selection, which was linked with eight classifiers, including Multi-Layer Perceptron (MLP), K-Neighbors Classifier (KNN), Extra Trees Classifier (ETC), and others. We employed 80% of the patients to select the best model in a 5-fold cross-validation process, and the remaining 20% were employed for hold-out testing.

RESULTS

For the sole usage of RFs and DFs, ANOVA and MLP resulted in averaged accuracies of 59 ± 3% and 65 ± 4% for 5-fold cross-validation, respectively, with hold-out testing accuracies of 59 ± 1% and 56 ± 2%, respectively. For sole CFs, a higher performance of 77 ± 8% for 5-fold cross-validation and a hold-out testing performance of 82 + 2% were obtained from ANOVA and ETC. RF+DF obtained a performance of 64 ± 7%, with a hold-out testing performance of 59 ± 2% through ANOVA and XGBC. Usage of CF+RF, CF+DF, and RF+DF+CF enabled the highest averaged accuracies of 78 ± 7%, 78 ± 9%, and 76 ± 8% for 5-fold cross-validation, and hold-out testing accuracies of 81 ± 2%, 82 ± 2%, and 83 ± 4%, respectively.

CONCLUSIONS

We demonstrated that CFs vitally contribute to predictive performance, and combining them with appropriate imaging features and HMLSs can result in the best prediction performance.

Radiomics insight into the neurodegenerative "hot" brain: A narrative review from the nuclear medicine perspective

The application of radiomics for non-oncologic diseases is currently emerging. Despite its relative infancy state, the evidence highlights the potential of radiomics approaches to serve as neuroimaging biomarkers in the field of the neurodegenerative brain. This systematic review presents the last progress and potential application of radiomics in the field of neurodegenerative nuclear imaging applied to positron-emission tomography (PET) and single-photon emission computed tomography (SPECT) by focusing mainly on the two most common neurodegenerative disorders, Alzheimer's (AD) and Parkinson's disease (PD). A comprehensive review of the current literature was performed using the PubMed and Web of Science databases up to November 2022. The final collection of eighteen relevant publications was grouped as AD-related and PD-related. The main efforts in the field of AD dealt with radiomics-based early diagnosis of preclinical AD and the prediction of MCI to AD conversion, meanwhile, in the setting of PD, the radiomics techniques have been used in the attempt to improve the assessment of PD diagnosis, the differential diagnosis between PD and other parkinsonism, severity assessment, and outcome prediction. Although limited evidence with relatively small cohort studies, it seems that radiomics-based analysis using nuclear medicine tools, mainly [18F]Fluorodeoxyglucose (FDG) and β-amyloid (Aβ) PET, and dopamine transporter (DAT) SPECT, can be used for computer-aided diagnoses in AD-continuum and parkinsonian disorders. Combining nuclear radiomics analysis with clinical factors and introducing a multimodality approach can significantly improve classification and prediction efficiency in neurodegenerative disorders.

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.