Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learning

Landscape of 2D Deep Learning Segmentation Networks Applied to CT Scan from Lung Cancer Patients: A Systematic Review

BACKGROUND

The increasing rates of lung cancer emphasize the need for early detection through computed tomography (CT) scans, enhanced by deep learning (DL) to improve diagnosis, treatment, and patient survival. This review examines current and prospective applications of 2D- DL networks in lung cancer CT segmentation, summarizing research, highlighting essential concepts and gaps; Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a systematic search of peer-reviewed studies from 01/2020 to 12/2024 on data-driven population segmentation using structured data was conducted across databases like Google Scholar, PubMed, Science Direct, IEEE (Institute of Electrical and Electronics Engineers) and ACM (Association for Computing Machinery) library. 124 studies met the inclusion criteria and were analyzed.

RESULTS

The LIDC-LIDR dataset was the most frequently used; The finding particularly relies on supervised learning with labeled data. The UNet model and its variants were the most frequently used models in medical image segmentation, achieving Dice Similarity Coefficients (DSC) of up to 0.9999. The reviewed studies primarily exhibit significant gaps in addressing class imbalances (67%), underuse of cross-validation (21%), and poor model stability evaluations (3%). Additionally, 88% failed to address the missing data, and generalizability concerns were only discussed in 34% of cases.

CONCLUSIONS

The review emphasizes the importance of Convolutional Neural Networks, particularly UNet, in lung CT analysis and advocates for a combined 2D/3D modeling approach. It also highlights the need for larger, diverse datasets and the exploration of semi-supervised and unsupervised learning to enhance automated lung cancer diagnosis and early detection.

PIDGN: An explainable multimodal deep learning framework for early prediction of Parkinson's disease

BACKGROUND

Parkinson's disease (PD), the second most common neurodegenerative disease in the world, is usually not diagnosed until the later stages of the disease, when patients might have already missed the best treatment period. Therefore, more effective prediction methods based on artificial intelligence (AI) are needed to assist physicians in timely diagnosis.

NEW METHODS

An explainable deep learning-based early Parkinson's disease diagnostic model, Parkinson's Integrative Diagnostic Gated Network (PIDGN), was designed by fusing Single Nucleotide Polymorphism (SNP) and brain sMRI data. Firstly, unimodal internal information was extracted using EmsembleTree dimensionality reduction method, Transformer encoder and 3D ResNet. Secondly, gated attention fusion technique was utilized to explore the inter-modal interactions. Finally, the classification results were output through the fully connected layer. SHapley additive interpretation (SHAP) values and Gradient-weighted Class Activation Mapping (Grad-CAM) techniques were used to help explain the importance of SNPs and brain regions for PD.

RESULTS

The results showed that the PIDGN model achieved the best results with the accuracy of 0.858 and AUROC of 0.897. Top 20 SNPs and the brain regions near the midbrain potentially related to PD were identified using two explainable techniques via SHAP values and Grad-CAM respectively.

COMPARISON WITH EXISTING METHODS AND CONCLUSION

The PIDGN model trained by fusing genetic and imaging data outperforms 13 other commonly used unimodal or bimodal models. Explainable PIDGN model helps deepen understanding of several SNPs and sMRI key factors that may affect PD. This study provides a potentially effective solution for automated early diagnosis of PD using AI.

Individualized diagnosis of Parkinson's disease based on multivariate magnetic resonance imaging radiomics and clinical indexes

Objective

To explore MRI-based radiomics models, integrating clinical characteristics, for differential diagnosis of Parkinson's disease (PD) to evaluate their diagnostic performance.

Methods

A total of 256 participants [153 PD, 103 healthy controls (HCs)] from the First Affiliated Hospital of Wenzhou Medical Hospital, were enrolled as the training set, and 120 subjects (74 PD, 46 HCs) from the PPMI dataset served as the test set. Radiomics features were extracted from structural MRI (T1WI and T2-FLair). Support Vector Machine (SVM) classifiers were developed using MRI radiomics data from both monomodal and multimodal radiomics models. The clinical-radiomics model was constructed by integrating clinical variables, including UPDRS, Hoehn-Yahr stage, age, sex, and MMSE scores. Receiver operating characteristic (ROC) curves were generated to evaluate the performance of the models. Decision curve analysis (DCA) was performed to access the clinical usefulness of the models.

Results

In the training set, the T2-FLair and T1WI radiomics model achieved an AUC of 0.896 (95% CI, 0.812-0.900) and 0.899 (95% CI, 0.818-0.908), respectively. The double-sequence radiomics model demonstrated superior diagnostic performance, with an AUC of 0.965 (95% CI, 0.885-0.978) in the training set and an AUC of 0.852 (95% CI, 0.748-0.910) in the test set. The integrated clinical-radiomics model showed enhanced diagnostic accuracy, with AUC = 0.983 (95% CI, 0.897-0.996) in the training set and AUC = 0.837 (95% CI, 0.786-0.902) in the test set. Rad-scores derived from the radiomics model were significantly correlated with diagnostic outcomes (P < 0.001). DCA confirmed the substantial clinical usefulness of the clinical-radiomics integrated model.

Conclusion

The integrated clinical-radiomics model offered superior diagnostic performance compared to models based relying solely on imaging or clinical data, underscoring its potential as a non-invasive and effective tool in routine clinical practice for the early diagnosis of PD.

Prospective study of dual-phase 99mTc-MIBI SPECT/CT nomogram for differentiating non-small cell lung cancer from benign pulmonary lesions

OBJECTIVES

To establish and validate a technetium 99m sestamibi (99mTc-MIBI) single-photon emission computed tomography/computed tomography (SPECT/CT) nomogram for predicting non-small cell lung cancer (NSCLC). Comparing the diagnostic performance of early and delayed SPECT/CT nomogram, and compare the diagnostic performance of SPECT/CT radiomics models with single SPECT and CT radiomics models.

METHODS

This prospective study included 119 lesions (NSCLC: n = 92, benign pulmonary lesions: n = 27) from 103 patients (mean age: 59.68 ± 8.94 years). Patients underwent dual-phase 99mTc-MIBI SPECT/CT imaging. They were divided into the training (n = 83) and validation (n = 36) cohorts. Logistic regression, support vector machine, random forest, and light-gradient boosting machine were applied to train and determine the optimal machine learning model. Then, combining radiomics score and clinical factors, establish nomograms for diagnosing NSCLC.

RESULT

CYFRA21-1 was selected for constructing the clinical model. In early imaging, the areas under the curve (AUCs) of the clinical model, radiomics model, and nomogram were 0.571, 0.830, and 0.875, respectively. The nomogram performed better than the clinical model and similarly to the radiomics model (P=0.020, P=0.216), and there are no statistically significant differences in the predictive performance between the radiomics model and the clinical model (P=0.103). In delayed imaging, the AUC was 0.643, 0.888, and 0.893, respectively. The predictive performance of the nomogram was superior compared to the clinical model and comparable to the radiomics model (P=0.042, P=0.480), and the radiomics model also demonstrated superior diagnostic performance compared to the clinical model (P=0.049). Compared to early SPECT/CT results, the AUC values of the nomogram and radiomics models in the delayed phase were higher, although no statistical differences were found (P=0.831, P=0.568). In delayed imaging, the AUC of the radiomics models for CT and SPECT was 0.696 and 0.768, respectively, SPECT/CT radiomics exhibited significant differences compared with CT and SPECT alone (P=0.042, P=0.038).

CONCLUSION

Dual-phase 99mTc-MIBI SPECT/CT nomograms and radiomics models can effectively predict NSCLC, providing an economically and non-invasive imaging method for diagnosing NSCLC, moreover, these findings provide a basis for early diagnosis and treatment strategies in NSCLC patients. Delayed-phase SPECT/CT imaging may offer greater practical value than early-phase imaging for diagnosing NSCLC. However, this novel approach necessitates further validation in larger, multi-center cohorts.

CLINICAL RELEVANCE

Radiomics nomogram based on SPECT/CT for discriminating NSCLC from benign lung lesions helps to aid early diagnosis and guide treatment.

KEY POINTS

Nomograms, based on dual-phase SPECT/CT, was constructed to discriminate between non-small cell lung cancer and benign lesions. SPECT/CT radiomics model has better predictive performance than SPECT and CT radiomics model.

Artificial intelligence in Parkinson's disease: Early detection and diagnostic advancements

Parkinson's disease (PD) is the second most common neurodegenerative disorder, globally affecting men and women at an exponentially growing rate, with currently no cure. Disease progression starts when dopaminergic neurons begin to die. In PD, the loss of neurotransmitter, dopamine is responsible for the overall communication of neural cells throughout the body. Clinical symptoms of PD are slowness of movement, involuntary muscular contractions, speech & writing changes, lessened automatic movement, and chronic tremors in the body. PD occurs in both familial and sporadic forms and modifiable and non-modifiable risk factors and socioeconomic conditions cause PD. Early detectable diagnostics and treatments have been developed in the last several decades. However, we still do not have precise early detectable biomarkers and therapeutic agents/drugs that prevent and/or delay the disease process. Recently, artificial intelligence (AI) science and machine learning tools have been promising in identifying early detectable markers with a greater rate of accuracy compared to past forms of treatment and diagnostic processes. Artificial intelligence refers to the intelligence exhibited by machines or software, distinct from the intelligence observed in humans that is based on neural networks in a form and can be used to diagnose the longevity and disease severity of disease. The term Machine Learning or Neural Networks is a blanket term used to identify an emerging technology that is created to work in the way of a "human brain" using many intertwined neurons to achieve the same level of raw intelligence as that of a brain. These processes have been used for neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease, to assess the severity of the patient's condition. In the current article, we discuss the prevalence and incidence of PD, and currently available diagnostic biomarkers and therapeutic strategies. We also highlighted currently available artificial intelligence science and machine learning tools and their applications to detect disease and develop therapeutic interventions.

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.

Regional changes in brain metabolism during the progression of mild cognitive impairment: a longitudinal study based on radiomics

BACKGROUND

This study aimed to establish radiomics models based on positron emission tomography (PET) images to longitudinally predict transition from mild cognitive impairment (MCI) to Alzheimer's disease (AD).

METHODS

In our study, 278 MCI patients from the ADNI database were analyzed, where 60 transitioned to AD (pMCI) and 218 remained stable (sMCI) over 48 months. Patients were divided into a training set (n = 222) and a validation set (n = 56). We first employed voxel-based analysis of 18F-FDG PET images to identify brain regions that present significant SUV difference between pMCI and sMCI groups. Radiomic features were extracted from these regions, key features were selected, and predictive models were developed for individual and combined brain regions. The models' effectiveness was evaluated using metrics like AUC to determine the most accurate predictive model for MCI progression.

RESULTS

Voxel-based analysis revealed four brain regions implicated in the progression from MCI to AD. These include ROI1 within the Temporal lobe, ROI2 and ROI3 in the Thalamus, and ROI4 in the Limbic system. Among the predictive models developed for these individual regions, the model utilizing ROI4 demonstrated superior predictive accuracy. In the training set, the AUC for the ROI4 model was 0.803 (95% CI 0.736, 0.865), and in the validation set, it achieved an AUC of 0.733 (95% CI 0.559, 0.893). Conversely, the model based on ROI3 showed the lowest performance, with an AUC of 0.75 (95% CI 0.685, 0.809). Notably, the comprehensive model encompassing all identified regions (ROI total) outperformed the single-region models, achieving an AUC of 0.884 (95% CI 0.845, 0.921) in the training set and 0.816 (95% CI 0.705, 0.909) in the validation set, indicating significantly enhanced predictive capability for MCI progression to AD.

CONCLUSION

Our findings underscore the Limbic system as the brain region most closely associated with the progression from MCI to AD. Importantly, our study demonstrates that a PET brain radiomics model encompassing multiple brain regions (ROI total) significantly outperforms models based on single brain regions. This comprehensive approach more accurately identifies MCI patients at high risk of progressing to AD, offering valuable insights for non-invasive diagnostics and facilitating early and timely interventions in clinical settings.

Prediction of Seropositivity in Suspected Autoimmune Encephalitis by Use of Radiomics: A Radiological Proof-of-Concept Study

In this study, we sought to evaluate the capabilities of radiomics and machine learning in predicting seropositivity in patients with suspected autoimmune encephalitis (AE) from MR images obtained at symptom onset. In 83 patients diagnosed with AE between 2011 and 2022, manual bilateral segmentation of the amygdala was performed on pre-contrast T2 images using 3D Slicer open-source software. Our sample of 83 patients contained 43 seropositive and 40 seronegative AE cases. Images were obtained at our tertiary care center and at various secondary care centers in North Rhine-Westphalia, Germany. The sample was randomly split into training data and independent test data. A total of 107 radiomic features were extracted from bilateral regions of interest (ROIs). Automated machine learning (AutoML) was used to identify the most promising machine learning algorithms. Feature selection was performed using recursive feature elimination (RFE) and based on the determination of the most important features. Selected features were used to train various machine learning algorithms on 100 different data partitions. Performance was subsequently evaluated on independent test data. Our radiomics approach was able to predict the presence of autoantibodies in the independent test samples with a mean AUC of 0.90, a mean accuracy of 0.83, a mean sensitivity of 0.84 and a mean specificity of 0.82, with Lasso regression models yielding the most promising results. These results indicate that radiomics-based machine learning could be a promising tool in predicting the presence of autoantibodies in suspected AE patients. Given the implications of seropositivity for definitive diagnosis of suspected AE cases, this may expedite diagnostic workup even before results from specialized laboratory testing can be obtained. Furthermore, in conjunction with recent publications, our results indicate that characterization of AE subtypes by use of radiomics may become possible in the future, potentially allowing physicians to tailor treatment in the spirit of personalized medicine even before laboratory workup is completed.

Analysis and prediction of interactions between transmembrane and non-transmembrane proteins

BACKGROUND

Most of the important biological mechanisms and functions of transmembrane proteins (TMPs) are realized through their interactions with non-transmembrane proteins(nonTMPs). The interactions between TMPs and nonTMPs in cells play vital roles in intracellular signaling, energy metabolism, investigating membrane-crossing mechanisms, correlations between disease and drugs.

RESULTS

Despite the importance of TMP-nonTMP interactions, the study of them remains in the wet experimental stage, lacking specific and comprehensive studies in the field of bioinformatics. To fill this gap, we performed a comprehensive statistical analysis of known TMP-nonTMP interactions and constructed a deep learning-based predictor to identify potential interactions. The statistical analysis describes known TMP-nonTMP interactions from various perspectives, such as distributions of species and protein families, enrichment of GO and KEGG pathways, as well as hub proteins and subnetwork modules in the PPI network. The predictor implemented by an end-to-end deep learning model can identify potential interactions from protein primary sequence information. The experimental results over the independent validation demonstrated considerable prediction performance with an MCC of 0.541.

CONCLUSIONS

To our knowledge, we were the first to focus on TMP-nonTMP interactions. We comprehensively analyzed them using bioinformatics methods and predicted them via deep learning-based solely on their sequence. This research completes a key link in the protein network, benefits the understanding of protein functions, and helps in pathogenesis studies of diseases and associated drug development.

Identification of Parkinson's disease and multiple system atrophy using multimodal PET/MRI radiomics

OBJECTIVES

To construct a machine learning model for differentiating Parkinson's disease (PD) and multiple system atrophy (MSA) by using multimodal PET/MRI radiomics and clinical characteristics.

METHODS

One hundred and nineteen patients (81 with PD and 38 with MSA) underwent brain PET/CT and MRI to obtain metabolic images ([18F]FDG, [11C]CFT PET) and structural MRI (T1WI, T2WI, and T2-FLAIR). Image analysis included automatic segmentation on MRI, co-registration of PET images onto the corresponding MRI. Radiomics features were then extracted from the putamina and caudate nuclei and selected to construct predictive models. Moreover, based on PET/MRI radiomics and clinical characteristics, we developed a nomogram. Receiver operating characteristic (ROC) curves were performed to evaluate the performance of the models. Decision curve analysis (DCA) was employed to access the clinical usefulness of the models.

RESULTS

The combined PET/MRI radiomics model of five sequences outperformed monomodal radiomics models alone. Further, PET/MRI radiomics-clinical combined model could perfectly distinguish PD from MSA (AUC = 0.993), which outperformed the clinical model (AUC = 0.923, p = 0.028) in training set, with no significant difference in test set (AUC = 0.860 vs 0.917, p = 0.390). However, no significant difference was found between PET/MRI radiomics-clinical model and PET/MRI radiomics model in training (AUC = 0.988, p = 0.276) and test sets (AUC = 0.860 vs 0.845, p = 0.632). DCA demonstrated the highest clinical benefit of PET/MRI radiomics-clinical model.

CONCLUSIONS

Our study indicates that multimodal PET/MRI radiomics could achieve promising performance to differentiate between PD and MSA in clinics.

CLINICAL RELEVANCE STATEMENT

This study developed an optimal radiomics signature and construct model to distinguish PD from MSA by multimodal PET/MRI imaging methods in clinics for parkinsonian syndromes, which achieved an excellent performance.

KEY POINTS

•Multimodal PET/MRI radiomics from putamina and caudate nuclei increase the diagnostic efficiency for distinguishing PD from MSA. •The radiomics-based nomogram was developed to differentiate between PD and MSA. •Combining PET/MRI radiomics-clinical model achieved promising performance to identify PD and MSA.

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.

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.

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.

Parkinson's Disease Detection Using Filter Feature Selection and a Genetic Algorithm with Ensemble Learning

Parkinson's disease (PD) is a neurodegenerative disorder marked by motor and non-motor symptoms that have a severe impact on the quality of life of the affected individuals. This study explores the effect of filter feature selection, followed by ensemble learning methods and genetic selection, on the detection of PD patients from attributes extracted from voice clips from both PD patients and healthy patients. Two distinct datasets were employed in this study. Filter feature selection was carried out by eliminating quasi-constant features. Several classification models were then tested on the filtered data. Decision tree, random forest, and XGBoost classifiers produced remarkable results, especially on Dataset 1, where 100% accuracy was achieved by decision tree and random forest. Ensemble learning methods (voting, stacking, and bagging) were then applied to the best-performing models to see whether the results could be enhanced further. Additionally, genetic selection was applied to the filtered data and evaluated using several classification models for their accuracy and precision. It was found that in most cases, the predictions for PD patients showed more precision than those for healthy individuals. The overall performance was also better on Dataset 1 than on Dataset 2, which had a greater number of features.

An interpretable multiparametric radiomics model of basal ganglia to predict dementia conversion in Parkinson's disease

Cognitive impairment in Parkinson's disease (PD) severely affects patients' prognosis, and early detection of patients at high risk of dementia conversion is important for establishing treatment strategies. We aimed to investigate whether multiparametric MRI radiomics from basal ganglia can improve the prediction of dementia development in PD when integrated with clinical profiles. In this retrospective study, 262 patients with newly diagnosed PD (June 2008-July 2017, follow-up >5 years) were included. MRI radiomic features (n = 1284) were extracted from bilateral caudate and putamen. Two models were developed to predict dementia development: (1) a clinical model-age, disease duration, and cognitive composite scores, and (2) a combined clinical and radiomics model. The area under the receiver operating characteristic curve (AUC) were calculated for each model. The models' interpretabilities were studied. Among total 262 PD patients (mean age, 68 years ± 8 [standard deviation]; 134 men), 51 (30.4%), and 24 (25.5%) patients developed dementia within 5 years of PD diagnosis in the training (n = 168) and test sets (n = 94), respectively. The combined model achieved superior predictive performance compared to the clinical model in training (AUCs 0.928 vs. 0.894, P = 0.284) and test set (AUCs 0.889 vs. 0.722, P = 0.016). The cognitive composite scores of the frontal/executive function domain contributed most to predicting dementia. Radiomics derived from the caudate were also highly associated with cognitive decline. Multiparametric MRI radiomics may have an incremental prognostic value when integrated with clinical profiles to predict future cognitive decline in PD.

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.

Intelligent personalized diagnosis modeling in advanced medical system for Parkinson's disease using voice signals

Currently, machine learning methods have been utilized to realize the early detection of Parkinson's disease (PD) by using voice signals. Because the vocal system of each person is unique, and the same person's pronunciation can be different at different times, the training samples used in machine learning become very different from the speech signal of the patient to be diagnosed, frequently resulting in poor diagnostic performance. On this account, this paper presents a new intelligent personalized diagnosis method (PDM) for Parkinson's disease. The method was designed to begin with constructing new training data by assigning the best classifier to each training sample composed of features from the speech signals of patients. Subsequently, a meta-classifier was trained on the new training data. Finally, for the signal of each test patient, the method used the meta-classifier to select the most appropriate classifier, followed by adopting the selected classifier to classify the signal so that the more accurate diagnosis result of the test patient can be obtained. The novelty of the proposed method is that the proposed method uses different classifiers to perform the diagnosis of PD for diversified patients, whereas the current method uses the same classifier to diagnose all patients to be tested. Results of a large number of experiments show that PDM not only improves the performance but also exceeds the existing methods in speed.

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.

Machine learning-based prediction of cognitive outcomes in de novo Parkinson's disease

Cognitive impairment is a debilitating symptom in Parkinson's disease (PD). We aimed to establish an accurate multivariate machine learning (ML) model to predict cognitive outcome in newly diagnosed PD cases from the Parkinson's Progression Markers Initiative (PPMI). Annual cognitive assessments over an 8-year time span were used to define two cognitive outcomes of (i) cognitive impairment, and (ii) dementia conversion. Selected baseline variables were organized into three subsets of clinical, biofluid and genetic/epigenetic measures and tested using four different ML algorithms. Irrespective of the ML algorithm used, the models consisting of the clinical variables performed best and showed better prediction of cognitive impairment outcome over dementia conversion. We observed a marginal improvement in the prediction performance when clinical, biofluid, and epigenetic/genetic variables were all included in one model. Several cerebrospinal fluid measures and an epigenetic marker showed high predictive weighting in multiple models when included alongside clinical variables.

Multi-Class Classifier in Parkinson’s Disease Using an Evolutionary Multi-Objective Optimization Algorithm

In this contribution, a novel methodology for multi-class classification in the field of Parkinson’s disease is proposed. The methodology is structured in two phases. In a first phase, the most relevant volumes of interest (VOI) of the brain are selected by means of an evolutionary multi-objective optimization (MOE) algorithm. Each of these VOIs are subjected to volumetric feature extraction using the Three-Dimensional Discrete Wavelet Transform (3D-DWT). When applying 3D-DWT, a high number of coefficients is obtained, requiring the use of feature selection/reduction algorithms to find the most relevant features. The method used in this contribution is based on Mutual Redundancy (MI) and Minimum Maximum Relevance (mRMR) and PCA. To optimize the VOI selection, a first group of 550 MRI was used for the 5 classes: PD, SWEDD, Prodromal, GeneCohort and Normal. Once the Pareto Front of the solutions is obtained (with varying degrees of complexity, reflected in the number of selected VOIs), these solutions are tested in a second phase. In order to analyze the SVM classifier accuracy, a test set of 367 MRI was used. The methodology obtains relevant results in multi-class classification, presenting several solutions with different levels of complexity and precision (Pareto Front solutions), reaching a result of 97% as the highest precision in the test data.

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

The high-throughput extraction of quantitative imaging features from medical images for the purpose of radiomic analysis, i.e., radiomics in a broad sense, is a rapidly developing and emerging research field that has been attracting increasing interest, particularly in multimodality and multi-omics studies. In this context, the quantitative analysis of multidimensional data plays an essential role in assessing the spatio-temporal characteristics of different tissues and organs and their microenvironment. Herein, recent developments in this method, including manually defined features, data acquisition and preprocessing, lesion segmentation, feature extraction, feature selection and dimension reduction, statistical analysis, and model construction, are reviewed. In addition, deep learning-based techniques for automatic segmentation and radiomic analysis are being analyzed to address limitations such as rigorous workflow, manual/semi-automatic lesion annotation, and inadequate feature criteria, and multicenter validation. Furthermore, a summary of the current state-of-the-art applications of this technology in disease diagnosis, treatment response, and prognosis prediction from the perspective of radiology images, multimodality images, histopathology images, and three-dimensional dose distribution data, particularly in oncology, is presented. The potential and value of radiomics in diagnostic and therapeutic strategies are also further analyzed, and for the first time, the advances and challenges associated with dosiomics in radiotherapy are summarized, highlighting the latest progress in radiomics. Finally, a robust framework for radiomic analysis is presented and challenges and recommendations for future development are discussed, including but not limited to the factors that affect model stability (medical big data and multitype data and expert knowledge in medical), limitations of data-driven processes (reproducibility and interpretability of studies, different treatment alternatives for various institutions, and prospective researches and clinical trials), and thoughts on future directions (the capability to achieve clinical applications and open platform for radiomics analysis).

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

BACKGROUND

We employed machine learning approaches to (I) determine distinct progression trajectories in Parkinson's disease (PD) (unsupervised clustering task), and (II) predict progression trajectories (supervised prediction task), from early (years 0 and 1) data, making use of clinical and imaging features.

METHODS

We studied PD-subjects derived from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative). We extracted and analyzed 981 features, including motor, non-motor, and radiomics features extracted for each region-of-interest (ROIs: left/right caudate and putamen) using our standardized standardized environment for radiomics analysis (SERA) radiomics software. Segmentation of ROIs on dopamine transposer - single photon emission computed tomography (DAT SPECT) images were performed via magnetic resonance images (MRI). After performing cross-sectional clustering on 885 subjects (original dataset) to identify disease subtypes, we identified optimal longitudinal trajectories using hybrid machine learning systems (HMLS), including principal component analysis (PCA) + K-Means algorithms (KMA) followed by Bayesian information criterion (BIC), Calinski-Harabatz criterion (CHC), and elbow criterion (EC). Subsequently, prediction of the identified trajectories from early year data was performed using multiple HMLSs including 16 Dimension Reduction Algorithms (DRA) and 10 classification algorithms.

RESULTS

We identified 3 distinct progression trajectories. Hotelling's t squared test (HTST) showed that the identified trajectories were distinct. The trajectories included those with (I, II) disease escalation (2 trajectories, 27% and 38% of patients) and (III) stable disease (1 trajectory, 35% of patients). For trajectory prediction from early year data, HMLSs including the stochastic neighbor embedding algorithm (SNEA, as a DRA) as well as locally linear embedding algorithm (LLEA, as a DRA), linked with the new probabilistic neural network classifier (NPNNC, as a classifier), resulted in accuracies of 78.4% and 79.2% respectively, while other HMLSs such as SNEA + Lib_SVM (library for support vector machines) and t_SNE (t-distributed stochastic neighbor embedding) + NPNNC resulted in 76.5% and 76.1% respectively.

CONCLUSIONS

This study moves beyond cross-sectional PD subtyping to clustering of longitudinal disease trajectories. We conclude that combining medical information with SPECT-based radiomics features, and optimal utilization of HMLSs, can identify distinct disease trajectories in PD patients, and enable effective prediction of disease trajectories from early year data.

Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection

OBJECTIVE

Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.

METHODS

Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm³ voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation.

RESULTS

In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis.

CONCLUSION

This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).

Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes

Purpose

Deep convolutional neural networks (CNN) provide high accuracy for automatic classification of dopamine transporter (DAT) SPECT images. However, CNN are inherently black-box in nature lacking any kind of explanation for their decisions. This limits their acceptance for clinical use. This study tested layer-wise relevance propagation (LRP) to explain CNN-based classification of DAT-SPECT in patients with clinically uncertain parkinsonian syndromes.

Methods

The study retrospectively included 1296 clinical DAT-SPECT with visual binary interpretation as “normal” or “reduced” by two experienced readers as standard-of-truth. A custom-made CNN was trained with 1008 randomly selected DAT-SPECT. The remaining 288 DAT-SPECT were used to assess classification performance of the CNN and to test LRP for explanation of the CNN-based classification.

Results

Overall accuracy, sensitivity, and specificity of the CNN were 95.8%, 92.8%, and 98.7%, respectively. LRP provided relevance maps that were easy to interpret in each individual DAT-SPECT. In particular, the putamen in the hemisphere most affected by nigrostriatal degeneration was the most relevant brain region for CNN-based classification in all reduced DAT-SPECT. Some misclassified DAT-SPECT showed an “inconsistent” relevance map more typical for the true class label.

Conclusion

LRP is useful to provide explanation of CNN-based decisions in individual DAT-SPECT and, therefore, can be recommended to support CNN-based classification of DAT-SPECT in clinical routine. Total computation time of 3 s is compatible with busy clinical workflow. The utility of “inconsistent” relevance maps to identify misclassified cases requires further investigation.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05569-9.