Application of texture analysis to DAT SPECT imaging: Relationship to clinical assessments

Heterogeneous PSMA ligand uptake inside parotid glands

The purpose of this investigation is to quantify the spatial heterogeneity of prostate-specific membrane antigen (PSMA) positron emission tomography (PET) uptake within parotid glands. We aim to quantify patterns in well-defined regions to facilitate further investigations. Furthermore, we investigate whether uptake is correlated with computed tomography (CT) texture features.

METHODS

Parotid glands from [18F]DCFPyL PSMA PET/CT images of 30 prostate cancer patients were analyzed. Uptake patterns were assessed with various segmentation schemes. Spearman's rank correlation coefficient was calculated between PSMA PET uptake and feature values of a Grey Level Run Length Matrix using a long and short run length emphasis (GLRLML and GLRLMS) in subregions of the parotid gland.

RESULTS

PSMA PET uptake was significantly higher (p < 0.001) in lateral/posterior regions of the glands than anterior/medial regions. Maximum uptake was found in the lateral half of parotid glands in 50 out of 60 glands. The difference in SUVmean between parotid halves is greatest when parotids are divided by a plane separating the anterior/medial and posterior/lateral halves symmetrically (out of 120 bisections tested). PSMA PET uptake was significantly correlated with CT GLRLML (p < 0.001), and anti-correlated with CT GLRLMS (p < 0.001).

CONCLUSION

Uptake of PSMA PET is heterogeneous within parotid glands, with uptake biased towards lateral/posterior regions. Uptake within parotid glands was strongly correlated with CT texture feature maps.

Robustness of radiomic features in 123I-ioflupane-dopamine transporter single-photon emission computer tomography scan

Radiomic features are usually used to predict target variables such as the absence or presence of a disease, treatment response, or time to symptom progression. One of the potential clinical applications is in patients with Parkinson's disease. Robust radiomic features for this specific imaging method have not yet been identified, which is necessary for proper feature selection. Thus, we are assessing the robustness of radiomic features in dopamine transporter imaging (DaT). For this study, we made an anthropomorphic head phantom with tissue heterogeneity using a personal 3D printer (polylactide 82% infill); the bone was subsequently reproduced with plaster. A surgical cotton ball with radiotracer (123I-ioflupane) was inserted. Scans were performed on the two-detector hybrid camera with acquisition parameters corresponding to international guidelines for DaT single photon emission tomography (SPECT). Reconstruction of SPECT was performed on a clinical workstation with iterative algorithms. Open-source LifeX software was used to extract 134 radiomic features. Statistical analysis was made in RStudio using the intraclass correlation coefficient (ICC) and coefficient of variation (COV). Overall, radiomic features in different reconstruction parameters showed a moderate reproducibility rate (ICC = 0.636, p <0.01). Assessment of ICC and COV within CT attenuation correction (CTAC) and non-attenuation correction (NAC) groups and within particular feature classes showed an excellent reproducibility rate (ICC > 0.9, p < 0.01), except for an intensity-based NAC group, where radiomic features showed a good repeatability rate (ICC = 0.893, p <0.01). By our results, CTAC becomes the main threat to feature stability. However, many radiomic features were sensitive to the selected reconstruction algorithm irrespectively to the attenuation correction. Radiomic features extracted from DaT-SPECT showed moderate to excellent reproducibility rates. These results make them suitable for clinical practice and human studies, but awareness of feature selection should be held, as some radiomic features are more robust than others.

The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods

PURPOSE

This study aimed to examine the robustness of positron emission tomography (PET) radiomic features extracted via different segmentation methods before and after ComBat harmonization in patients with non-small cell lung cancer (NSCLC).

METHODS

We included 120 patients (positive recurrence = 46 and negative recurrence = 74) referred for PET scanning as a routine part of their care. All patients had a biopsy-proven NSCLC. Nine segmentation methods were applied to each image, including manual delineation, K-means (KM), watershed, fuzzy-C-mean, region-growing, local active contour (LAC), and iterative thresholding (IT) with 40, 45, and 50% thresholds. Diverse image discretizations, both without a filter and with different wavelet decompositions, were applied to PET images. Overall, 6741 radiomic features were extracted from each image (749 radiomic features from each segmented area). Non-parametric empirical Bayes (NPEB) ComBat harmonization was used to harmonize the features. Linear Support Vector Classifier (LinearSVC) with L1 regularization For feature selection and Support Vector Machine classifier (SVM) with fivefold nested cross-validation was performed using StratifiedKFold with 'n_splits' set to 5 to predict recurrence in NSCLC patients and assess the impact of ComBat harmonization on the outcome.

RESULTS

From 749 extracted radiomic features, 206 (27%) and 389 (51%) features showed excellent reliability (ICC ≥ 0.90) against segmentation method variation before and after NPEB ComBat harmonization, respectively. Among all, 39 features demonstrated poor reliability, which declined to 10 after ComBat harmonization. The 64 fixed bin widths (without any filter) and wavelets (LLL)-based radiomic features set achieved the best performance in terms of robustness against diverse segmentation techniques before and after ComBat harmonization. The first-order and GLRLM and also first-order and NGTDM feature families showed the largest number of robust features before and after ComBat harmonization, respectively. In terms of predicting recurrence in NSCLC, our findings indicate that using ComBat harmonization can significantly enhance machine learning outcomes, particularly improving the accuracy of watershed segmentation, which initially had fewer reliable features than manual contouring. Following the application of ComBat harmonization, the majority of cases saw substantial increase in sensitivity and specificity.

CONCLUSION

Radiomic features are vulnerable to different segmentation methods. ComBat harmonization might be considered a solution to overcome the poor reliability of radiomic features.

Real-world evidence on levodopa dose escalation in patients with Parkinson's disease treated with istradefylline

OBJECTIVE

Istradefylline, a selective adenosine A2A receptor antagonist, is indicated in the US and Japan as adjunctive treatment to levodopa/decarboxylase inhibitors in adults with Parkinson's disease (PD) experiencing OFF time. This study aimed to observe patterns of dose escalation of levodopa over time in patients initiated on istradefylline.

METHODS

Using Japanese electronic health record data, interrupted time series analyses were used to compare levodopa daily dose (LDD, mg/day) gradients in patients before and after initiation of istradefylline. Data were analyzed by period relative to istradefylline initiation (Month 1): pre-istradefylline (Months -72 to 0), early istradefylline (Months 1 to 24), and late istradefylline (Months 25 to 72). Subgroup analyses included LDD before istradefylline initiation (<400, ≥400 to <600, ≥600 mg/day) and treatment with or without monoamine oxidase-B (MAO-B) inhibitors, catechol-O-methyltransferase (COMT) inhibitors, or dopamine agonists before istradefylline initiation.

RESULTS

The analysis included 4026 patients; mean (SD) baseline LDD was 419.27 mg (174.19). Patients receiving ≥600 mg/day levodopa or not receiving MAO-B inhibitors or COMT inhibitors demonstrated a significant reduction in LDD increase gradient for pre-istradefylline vs late-phase istradefylline (≥600 mg/day levodopa, -6.259 mg/day each month, p<0.001; no MAO-B inhibitors, -1.819 mg/day each month, p = 0.004; no COMT inhibitors, -1.412 mg/day each month, p = 0.027).

CONCLUSIONS

This real-world analysis of Japanese prescription data indicated that slowing of LDD escalation was observed in patients initiated on istradefylline, particularly in those receiving ≥600 mg/day levodopa, suggesting istradefylline may slow progressive LDD increases. These findings suggest that initiating istradefylline before other levodopa-adjunctive therapies may mitigate LDD increases, potentially reducing occurrence or severity of levodopa-induced complications in long-term istradefylline treatment.

Standardized Radiomics Analysis of Clinical Myocardial Perfusion Stress SPECT Images to Identify Coronary Artery Calcification

PURPOSE

Myocardial perfusion (MP) stress single-photon emission computed tomography (SPECT) is an established diagnostic test for patients suspected of coronary artery disease (CAD). Meanwhile, coronary artery calcification (CAC) scoring obtained from diagnostic CT is a highly sensitive test, offering incremental diagnostic information in identifying patients with significant CAD yet normal MP stress SPECT (MPSS) scans. However, after decades of wide utilization of MPSS, CAC is not commonly reimbursed (e.g. by the CMS), nor widely deployed in community settings. We studied the potential of complementary information deduced from the radiomics analysis of normal MPSS scans in predicting the CAC score.

METHODS

We collected data from 428 patients with normal (non-ischemic) MPSS (99mTc-sestamibi; consensus reading). A nuclear medicine physician verified iteratively reconstructed images (attenuation-corrected) to be free from fixed perfusion defects and artifactual attenuation. Three-dimensional images were automatically segmented into four regions of interest (ROIs), including myocardium and three vascular segments (left anterior descending [LAD]-left circumference [LCX]-right coronary artery [RCA]). We used our software package, standardized environment for radiomics analysis (SERA), to extract 487 radiomic features in compliance with the image biomarker standardization initiative (IBSI). Isotropic cubic voxels were discretized using fixed bin-number discretization (eight schemes). We first performed blind-to-outcome feature selection focusing on a priori usefulness, dynamic range, and redundancy of features. Subsequently, we performed univariate and multivariate machine learning analyses to predict CAC scores from i) selected radiomic features, ii) 10 clinical features, and iii) combined radiomics + clinical features. Univariate analysis invoked Spearman correlation with Benjamini-Hotchberg false-discovery correction. The multivariate analysis incorporated stepwise linear regression, where we randomly selected a 15% test set and divided the other 85% of data into 70% training and 30% validation sets. Training started from a constant (intercept) model, iteratively adding/removing features (stepwise regression), invoking the Akaike information criterion (AIC) to discourage overfitting. Validation was run similarly, except that the training output model was used as the initial model. We randomized training/validation sets 20 times, selecting the best model using log-likelihood for evaluation in the test set. Assessment in the test set was performed thoroughly by running the entire operation 50 times, subsequently employing Fisher's method to verify the significance of independent tests.

RESULTS

Unsupervised feature selection significantly reduced 8×487 features to 56. In univariate analysis, no feature survived the false-discovery rate (FDR) to directly correlate with CAC scores. Applying Fisher's method to the multivariate regression results demonstrated combining radiomics with the clinical features to enhance the significance of the prediction model across all cardiac segments.  Conclusions: Our standardized and statistically robust multivariate analysis demonstrated significant prediction of the CAC score for all cardiac segments when combining MPSS radiomic features with clinical features, suggesting radiomics analysis can add diagnostic or prognostic value to standard MPSS for wide clinical usage.

The differential diagnosis value of radiomics-based machine learning in Parkinson's disease: a systematic review and meta-analysis

Background

In recent years, radiomics has been increasingly utilized for the differential diagnosis of Parkinson's disease (PD). However, the application of radiomics in PD diagnosis still lacks sufficient evidence-based support. To address this gap, we carried out a systematic review and meta-analysis to evaluate the diagnostic value of radiomics-based machine learning (ML) for PD.

Methods

We systematically searched Embase, Cochrane, PubMed, and Web of Science databases as of November 14, 2022. The radiomics quality assessment scale (RQS) was used to evaluate the quality of the included studies. The outcome measures were the c-index, which reflects the overall accuracy of the model, as well as sensitivity and specificity. During this meta-analysis, we discussed the differential diagnostic value of radiomics-based ML for Parkinson's disease and various atypical parkinsonism syndromes (APS).

Results

Twenty-eight articles with a total of 6,057 participants were included. The mean RQS score for all included articles was 10.64, with a relative score of 29.56%. The pooled c-index, sensitivity, and specificity of radiomics for predicting PD were 0.862 (95% CI: 0.833-0.891), 0.91 (95% CI: 0.86-0.94), and 0.93 (95% CI: 0.87-0.96) in the training set, and 0.871 (95% CI: 0.853-0.890), 0.86 (95% CI: 0.81-0.89), and 0.87 (95% CI: 0.83-0.91) in the validation set, respectively. Additionally, the pooled c-index, sensitivity, and specificity of radiomics for differentiating PD from APS were 0.866 (95% CI: 0.843-0.889), 0.86 (95% CI: 0.84-0.88), and 0.80 (95% CI: 0.75-0.84) in the training set, and 0.879 (95% CI: 0.854-0.903), 0.87 (95% CI: 0.85-0.89), and 0.82 (95% CI: 0.77-0.86) in the validation set, respectively.

Conclusion

Radiomics-based ML can serve as a potential tool for PD diagnosis. Moreover, it has an excellent performance in distinguishing Parkinson's disease from APS. The support vector machine (SVM) model exhibits excellent robustness when the number of samples is relatively abundant. However, due to the diverse implementation process of radiomics, it is expected that more large-scale, multi-class image data can be included to develop radiomics intelligent tools with broader applicability, promoting the application and development of radiomics in the diagnosis and prediction of Parkinson's disease and related fields.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=383197, identifier ID: CRD42022383197.

Relevance of 18F-DOPA visual and semi-quantitative PET metrics for the diagnostic of Parkinson disease in clinical practice: a machine learning-based inference study

PURPOSE

To decipher the relevance of visual and semi-quantitative 6-fluoro-(18F)-L-DOPA (¹⁸F-DOPA) interpretation methods for the diagnostic of idiopathic Parkinson disease (IPD) in hybrid positron emission tomography (PET) and magnetic resonance imaging.

MATERIAL AND METHODS

A total of 110 consecutive patients (48 IPD and 62 controls) with 11 months of median clinical follow-up (reference standard) were included. A composite visual assessment from five independent nuclear imaging readers, together with striatal standard uptake value (SUV) to occipital SUV ratio, striatal gradients and putamen asymmetry-based semi-quantitative PET metrics automatically extracted used to train machine learning models to classify IPD versus controls. Using a ratio of 70/30 for training and testing sets, respectively, five classification models-k-NN, LogRegression, support vector machine, random forest and gradient boosting-were trained by using 100 times repeated nested cross-validation procedures. From the best model on average, the contribution of PET parameters was deciphered using the Shapley additive explanations method (SHAP). Cross-validated receiver operating characteristic curves (cv-ROC) of the most contributive PET parameters were finally estimated and compared.

RESULTS

The best machine learning model (k-NN) provided final cv-ROC of 0.81. According to SHAP analyses, visual PET metric was the most important contributor to the model overall performance, followed by the minimum between left and right striatal to occipital SUV ratio. The 10-time cv-ROC curves of visual, min SUVr or both showed quite similar performance (mean area under the ROC of 0.81, 0.81 and 0.79, respectively, for visual, min SUVr or both).

CONCLUSION

Visual expert analysis remains the most relevant parameter to predict IPD diagnosis at 11 months of median clinical follow-up in ¹⁸F-FDOPA. The min SUV ratio appears interesting in the perspective of simple semi-automated diagnostic workflows.

How Radiomics Can Improve Breast Cancer Diagnosis and Treatment

Recent technological advances in the field of artificial intelligence hold promise in addressing medical challenges in breast cancer care, such as early diagnosis, cancer subtype determination and molecular profiling, prediction of lymph node metastases, and prognostication of treatment response and probability of recurrence. Radiomics is a quantitative approach to medical imaging, which aims to enhance the existing data available to clinicians by means of advanced mathematical analysis using artificial intelligence. Various published studies from different fields in imaging have highlighted the potential of radiomics to enhance clinical decision making. In this review, we describe the evolution of AI in breast imaging and its frontiers, focusing on handcrafted and deep learning radiomics. We present a typical workflow of a radiomics analysis and a practical "how-to" guide. Finally, we summarize the methodology and implementation of radiomics in breast cancer, based on the most recent scientific literature to help researchers and clinicians gain fundamental knowledge of this emerging technology. Alongside this, we discuss the current limitations of radiomics and challenges of integration into clinical practice with conceptual consistency, data curation, technical reproducibility, adequate accuracy, and clinical translation. The incorporation of radiomics with clinical, histopathological, and genomic information will enable physicians to move forward to a higher level of personalized management of patients with breast cancer.

Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson's disease

Objectives.Parkinson's disease (PD) is a complex neurodegenerative disorder, affecting 2%-3% of the elderly population. Montreal Cognitive Assessment (MoCA), a rapid nonmotor screening test, assesses different cognitive dysfunctionality aspects. Early MoCA prediction may facilitate better temporal therapy and disease control. Radiomics features (RF), in addition to clinical features (CF), are indicated to increase clinical diagnoses, etc, bridging between medical imaging procedures and personalized medicine. We investigate the effect of RFs, CFs, and conventional imaging features (CIF) to enhance prediction performance using hybrid machine learning systems (HMLS).Methods.We selected 210 patients with 981 features (CFs, CIFs, and RFs) from the Parkinson's Progression-Markers-Initiative database. We generated 4 datasets, namely using (i), (ii) year-0 (D1) or year-1 (D2) features, (iii) longitudinal data (D3, putting datasets in years 0 and 1 longitudinally next to each other), and (iv) timeless data (D4, effectively doubling dataset size by listing both datasets from years 0 and 1 separately). First, we directly applied 23 predictor algorithms (PA) to the datasets to predict year-4 MoCA, which PD patients this year have a higher dementia risk. Subsequently, HMLSs, including 14 attribute extraction and 10 feature selection algorithms followed by PAs were employed to enhance prediction performances. 80% of all datapoints were utilized to select the best model based on minimum mean absolute error (MAE) resulting from 5-fold cross-validation. Subsequently, the remaining 20% was used for hold-out testing of the selected models.Results.When applying PAs without ASAs/FEAs to datasets (MoCA outcome range: [11,30]), Adaboost achieved an MAE of 1.74 ± 0.29 on D4 with a hold-out testing performance of 1.71. When employing HMLSs, D4 + Minimum_Redundancy_Maximum_Relevance (MRMR)+K_Nearest_Neighbor Regressor achieved the highest performance of 1.05 ± 0.25 with a hold-out testing performance of 0.57.Conclusion.Our study shows the importance of using larger datasets (timeless), and utilizing optimized HMLSs, for significantly improved prediction of MoCA in PD patients.

Dopamine dysfunction in depression: application of texture analysis to dopamine transporter single-photon emission computed tomography imaging

Dopamine dysfunction has been associated with depression. However, results of recent neuroimaging studies on dopamine transporter (DAT), which reflect the function of the dopaminergic system, are inconclusive. The aim of this study was to apply texture analysis, a novel method to extract information about the textural properties of images (e.g., coarseness), to single-photon emission computed tomography (SPECT) imaging in depression. We performed SPECT using ¹²³I-ioflupane to measure DAT binding in 150 patients with major depressive disorder (N = 112) and bipolar disorder (N = 38). The texture features of DAT binding in subregions of the striatum were calculated. We evaluated the relationship between the texture feature values (coarseness, contrast, and busyness) and severity of depression, and then examined the effects of medication and diagnosis on such relationship. Furthermore, using the data from 40 healthy subjects, we examined the effects of age and sex on the texture feature values. The degree of busyness of the limbic region in the left striatum linked to the severity of depression (p = 0.0025). The post-hoc analysis revealed that this texture feature value was significantly higher in both the severe and non-severe depression groups than in the remission group (p = 0.001 and p = 0.028, respectively). This finding remained consistent after considering the effect of medication. The effects of age and sex in healthy individuals were not evident in this texture feature value. Our findings imply that the application of texture analysis to DAT-SPECT may provide a state-marker of depression.

A tissue‐fraction estimation‐based segmentation method for quantitative dopamine transporter SPECT

BACKGROUND

Quantitative measures of dopamine transporter (DaT) uptake in caudate, putamen, and globus pallidus (GP) derived from dopamine transporter-single-photon emission computed tomography (DaT-SPECT) images have potential as biomarkers for measuring the severity of Parkinson's disease. Reliable quantification of this uptake requires accurate segmentation of the considered regions. However, segmentation of these regions from DaT-SPECT images is challenging, a major reason being partial-volume effects (PVEs) in SPECT. The PVEs arise from two sources, namely the limited system resolution and reconstruction of images over finite-sized voxel grids. The limited system resolution results in blurred boundaries of the different regions. The finite voxel size leads to TFEs, that is, voxels contain a mixture of regions. Thus, there is an important need for methods that can account for the PVEs, including the TFEs, and accurately segment the caudate, putamen, and GP, from DaT-SPECT images.

PURPOSE

Design and objectively evaluate a fully automated tissue-fraction estimation-based segmentation method that segments the caudate, putamen, and GP from DaT-SPECT images.

METHODS

The proposed method estimates the posterior mean of the fractional volumes occupied by the caudate, putamen, and GP within each voxel of a three-dimensional DaT-SPECT image. The estimate is obtained by minimizing a cost function based on the binary cross-entropy loss between the true and estimated fractional volumes over a population of SPECT images, where the distribution of true fractional volumes is obtained from existing populations of clinical magnetic resonance images. The method is implemented using a supervised deep-learning-based approach.

RESULTS

Evaluations using clinically guided highly realistic simulation studies show that the proposed method accurately segmented the caudate, putamen, and GP with high mean Dice similarity coefficients of ∼ 0.80 and significantly outperformed ( p < 0.01 $p &lt; 0.01$ ) all other considered segmentation methods. Further, an objective evaluation of the proposed method on the task of quantifying regional uptake shows that the method yielded reliable quantification with low ensemble normalized root mean square error (NRMSE) < 20% for all the considered regions. In particular, the method yielded an even lower ensemble NRMSE of ∼ 10% for the caudate and putamen.

CONCLUSIONS

The proposed tissue-fraction estimation-based segmentation method for DaT-SPECT images demonstrated the ability to accurately segment the caudate, putamen, and GP, and reliably quantify the uptake within these regions. The results motivate further evaluation of the method with physical-phantom and patient studies.

Development and validation of a radiomic model for the diagnosis of dopaminergic denervation on [18F]FDOPA PET/CT

Purpose

FDOPA PET shows good performance for the diagnosis of striatal dopaminergic denervation, making it a valuable tool for the differential diagnosis of Parkinsonism. Textural features are image biomarkers that could potentially improve the early diagnosis and monitoring of neurodegenerative parkinsonian syndromes. We explored the performances of textural features for binary classification of FDOPA scans.

Methods

We used two FDOPA PET datasets: 443 scans for feature selection, and 100 scans from a different PET/CT system for model testing. Scans were labelled according to expert interpretation (dopaminergic denervation versus no dopaminergic denervation). We built LASSO logistic regression models using 43 biomarkers including 32 textural features. Clinical data were also collected using a shortened UPDRS scale.

Results

The model built from the clinical data alone had a mean area under the receiver operating characteristics (AUROC) of 63.91. Conventional imaging features reached a maximum score of 93.47 but the addition of textural features significantly improved the AUROC to 95.73 (p < 0.001), and 96.10 (p < 0.001) when limiting the model to the top three features: GLCM_Correlation, Skewness and Compacity. Testing the model on the external dataset yielded an AUROC of 96.00, with 95% sensitivity and 97% specificity. GLCM_Correlation was one of the most independent features on correlation analysis, and systematically had the heaviest weight in the classification model.

Conclusion

A simple model with three radiomic features can identify pathologic FDOPA PET scans with excellent sensitivity and specificity. Textural features show promise for the diagnosis of parkinsonian syndromes.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-022-05816-7.

Dopamine Transporter Imaging, Current Status of a Potential Biomarker: A Comprehensive Review

A major goal of current clinical research in Parkinson's disease (PD) is the validation and standardization of biomarkers enabling early diagnosis, predicting outcomes, understanding PD pathophysiology, and demonstrating target engagement in clinical trials. Molecular imaging with specific dopamine-related tracers offers a practical indirect imaging biomarker of PD, serving as a powerful tool to assess the status of presynaptic nigrostriatal terminals. In this review we provide an update on the dopamine transporter (DAT) imaging in PD and translate recent findings to potentially valuable clinical practice applications. The role of DAT imaging as diagnostic, preclinical and predictive biomarker is discussed, especially in view of recent evidence questioning the incontrovertible correlation between striatal DAT binding and nigral cell or axon counts.

Feature selection and machine learning methods for optimal identification and prediction of subtypes in Parkinson's disease

OBJECTIVES

The present work focuses on assessment of Parkinson's disease (PD), including both PD subtype identification (unsupervised task) and prediction (supervised task). We specifically investigate optimal feature selection and machine learning algorithms for these tasks.

METHODS

We selected 885 PD subjects as derived from longitudinal datasets (years 0-4; Parkinson's Progressive Marker Initiative), and investigated 981 features including motor, non-motor, and imaging features (SPECT-based radiomics features extracted using our standardized SERA software). Two different hybrid machine learning systems (HMLS) were constructed and applied to the data in order to select optimal combinations in both tasks: (i) identification of subtypes in PD (unsupervised-clustering), and (ii) prediction of these subtypes in year 4 (supervised-classification). From the original data based on years 0 (baseline) and 1, we created new datasets as inputs to the prediction task: (i,ii) CSD0 and CSD01: cross-sectional datasets from year 0 only and both years 0 & 1, respectively; (iii) TD01: timeless dataset from both years 0 & 1. In addition, PD subtype in year 4 was considered as outcome. Finally, high score features were derived via ensemble voting based on their prioritizations from feature selector algorithms (FSAs).

RESULTS

In clustering task, the most optimal combinations (out of 981) were selected by individual FSAs to enable high correlation compared to using all features (arriving at 547). In prediction task, we were able to select optimal combinations, resulting in an accuracy >90% only for timeless dataset (TD01); there, we were able to select the most optimal combination using 77 features, directly selected by FSAs. In both tasks, however, using combination of only high score features from ensemble voting did not enable acceptable performances, showing optimal feature selection via individual FSAs to be more effective.

CONCLUSION

Combining non-imaging information with SPECT-based radiomics features, and optimal utilization of HMLSs, can enable robust identification of subtypes as well as appropriate prediction of these subtypes in PD patients. Moreover, use of timeless dataset, beyond cross-sectional datasets, enabled predictive accuracies over 90%. Overall, we showed that radiomics features extracted from SPECT images are important in clustering as well as prediction of PD subtypes.

Recent Radiomics Advancements in Breast Cancer: Lessons and Pitfalls for the Next Future

Radiomics is an emerging translational field of medicine based on the extraction of high-dimensional data from radiological images, with the purpose to reach reliable models to be applied into clinical practice for the purposes of diagnosis, prognosis and evaluation of disease response to treatment. We aim to provide the basic information on radiomics to radiologists and clinicians who are focused on breast cancer care, encouraging cooperation with scientists to mine data for a better application in clinical practice. We investigate the workflow and clinical application of radiomics in breast cancer care, as well as the outlook and challenges based on recent studies. Currently, radiomics has the potential ability to distinguish between benign and malignant breast lesions, to predict breast cancer’s molecular subtypes, the response to neoadjuvant chemotherapy and the lymph node metastases. Even though radiomics has been used in tumor diagnosis and prognosis, it is still in the research phase and some challenges need to be faced to obtain a clinical translation. In this review, we discuss the current limitations and promises of radiomics for improvement in further research.

Multivariate radiomics models based on 18F-FDG hybrid PET/MRI for distinguishing between Parkinson's disease and multiple system atrophy

PURPOSE

To construct multivariate radiomics models using hybrid ¹⁸F-FDG PET/MRI for distinguishing between Parkinson's disease (PD) and multiple system atrophy (MSA).

METHODS

Ninety patients (60 with PD and 30 with MSA) were randomized to training and test sets in a 7:3 ratio. All patients underwent ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET/MRI to simultaneously obtain metabolic images (¹⁸F-FDG), structural MRI images (T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and T2-weighted fluid-attenuated inversion recovery (T2/FLAIR)) and functional MRI images (susceptibility-weighted imaging (SWI) and apparent diffusion coefficient). Using PET and five MRI sequences, we extracted 1172 radiomics features from the putamina and caudate nuclei. The radiomics signatures were constructed with the least absolute shrinkage and selection operator algorithm in the training set, with progressive optimization through single-sequence and double-sequence radiomics models. Multivariable logistic regression analysis was used to develop a clinical-radiomics model, combining the optimal multi-sequence radiomics signature with clinical characteristics and SUV values. The diagnostic performance of the models was assessed by receiver operating characteristic and decision curve analysis (DCA).

RESULTS

The radiomics signatures showed favourable diagnostic efficacy. The optimal model comprised structural (T1WI), functional (SWI) and metabolic (¹⁸F-FDG) sequences (Radscore_{FDG_T1WI_SWI}) with the area under curves (AUCs) of the training and test sets of 0.971 and 0.957, respectively. The integrated model, incorporating Radscore_{FDG_T1WI_SWI}, three clinical symptoms (disease duration, dysarthria and autonomic failure) and SUV_max, demonstrated satisfactory calibration and discrimination in the training and test sets (0.993 and 0.994, respectively). DCA indicated the highest clinical benefit of the clinical-radiomics integrated model.

CONCLUSIONS

The radiomics signature with metabolic, structural and functional information provided by hybrid ¹⁸F-FDG PET/MRI may achieve promising diagnostic efficacy for distinguishing between PD and MSA. The clinical-radiomics integrated model performed best.

Improved motor outcome prediction in Parkinson's disease applying deep learning to DaTscan SPECT images

PURPOSE

Dopamine transporter (DAT) SPECT imaging is routinely used in the diagnosis of Parkinson's disease (PD). Our previous efforts demonstrated the use of DAT SPECT images in a data-driven manner by improving prediction of PD clinical assessment outcome using radiomic features. In this work, we develop a convolutional neural network (CNN) based technique to predict clinical motor function evaluation scores directly from longitudinal DAT SPECT images and non-imaging clinical measures.

PROCEDURES

Data of 252 subjects from the Parkinson's Progression Markers Initiative (PPMI) database were used in this work. The motor part (III) score of the unified Parkinson's disease rating scale (UPDRS) at year 4 was selected as outcome, and the DAT SPECT images and UPDRS_III scores acquired at year 0 and year 1 were used as input data. The specified inputs and outputs were used to develop a CNN based regression method for prediction. Ten-fold cross-validation was used to test the trained network and the absolute difference between predicted and actual scores was used as the performance metric. Prediction using inputs with and without DAT images was evaluated.

RESULTS

Using only UPDRS_III scores at year 0 and year 1, the prediction yielded an average difference of 7.6 ± 6.1 between the predicted and actual year 4 motor scores (range [5, 77]). The average difference was reduced to 6.0 ± 4.8 when longitudinal DAT SPECT images were included, which was determined to be statistically significant via a two-sample t-test, and demonstrates the benefit of including images.

CONCLUSIONS

This study shows that adding DAT SPECT images to UPDRS_III scores as inputs to deep-learning based prediction significantly improves the outcome. Without requiring segmentation and feature extraction, the CNN based prediction method allows easier and more universial application.

Texture-based markers from structural imaging correlate with motor handicap in Parkinson's disease

There is a growing need for surrogate biomarkers for Parkinson’s disease (PD). Structural analysis using magnetic resonance imaging with T1-weighted sequences has the potential to quantify histopathological changes. Degeneration is typically measured by the volume and shape of morphological changes. However, these changes appear late in the disease, preventing their use as surrogate markers. We investigated texture changes in 108 individuals, divided into three groups, matched in terms of sex and age: (1) healthy controls (n = 32); (2) patients with early-stage PD (n = 39); and (3) patients with late-stage PD and severe L-dopa-related complications (n = 37). All patients were assessed in off-treatment conditions. Statistical analysis of first- and second-order texture features was conducted in the substantia nigra, striatum, thalamus and sub-thalamic nucleus. Regions of interest volumetry and voxel-based morphometry were performed for comparison. Significantly different texture features were observed between the three populations, with some showing a gradual linear progression between the groups. The volumetric changes in the two PD patient groups were not significantly different. Texture features were significantly associated with clinical scores for motor handicap. These results suggest that texture features, measured in the nigrostriatal pathway at PD diagnosis, may be useful in predicting clinical progression of motor handicap.

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

OBJECTIVES

It is important to subdivide Parkinson's disease (PD) into subtypes, enabling potentially earlier disease recognition and tailored treatment strategies. We aimed to identify reproducible PD subtypes robust to variations in the number of patients and features.

METHODS

We applied multiple feature-reduction and cluster-analysis methods to cross-sectional and timeless data, extracted from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative; 885 PD/163 healthy-control visits; 35 datasets with combinations of non-imaging, conventional-imaging, and radiomics features from DAT-SPECT images). Hybrid machine-learning systems were constructed invoking 16 feature-reduction algorithms, 8 clustering algorithms, and 16 classifiers (C-index clustering evaluation used on each trajectory). We subsequently performed: i) identification of optimal subtypes, ii) multiple independent tests to assess reproducibility, iii) further confirmation by a statistical approach, iv) test of reproducibility to the size of the samples.

RESULTS

When using no radiomics features, the clusters were not robust to variations in features, whereas, utilizing radiomics information enabled consistent generation of clusters through ensemble analysis of trajectories. We arrived at 3 distinct subtypes, confirmed using the training and testing process of k-means, as well as Hotelling's T2 test. The 3 identified PD subtypes were 1) mild; 2) intermediate; and 3) severe, especially in terms of dopaminergic deficit (imaging), with some escalating motor and non-motor manifestations.

CONCLUSION

Appropriate hybrid systems and independent statistical tests enable robust identification of 3 distinct PD subtypes. This was assisted by utilizing radiomics features from SPECT images (segmented using MRI). The PD subtypes provided were robust to the number of the subjects, and features.

Striatal dopamine transporter SPECT quantification: head-to-head comparison between two three-dimensional automatic tools

Purpose

Our aim was to compare a widely distributed commercial tool with an older free software (i) one another, (ii) with a clinical motor score, (iii) versus reading by experts.

Procedures

We analyzed consecutive scans from one-hundred and fifty-one outpatients submitted to brain DAT SPECT for a suspected parkinsonism. Images were post-processed using a commercial (Datquant®) and a free (BasGanV2) software. Reading by expert was the gold standard. A subset of patients with pathological or borderline scan was evaluated with the clinical Unified Parkinson’s Disease Rating Scale, motor part (MDS-UPDRS-III).

Results

SBR, putamen-to-caudate (P/C) ratio, and both P and C asymmetries were highly correlated between the two software with Pearson’s ‘r’ correlation coefficients ranging from .706 to .887. Correlation coefficients with the MDS-UPDRS III score were higher with caudate than with putamen SBR values with both software, and in general higher with BasGanV2 than with Datquant®. Datquant® correspondence with expert reading was 84.1% (94.0% by additionally considering the P/C ratio as a further index). BasGanV2 correspondence with expert reading was 80.8% (86.1% by additionally considering the P/C ratio).

Conclusions

Both Datquant® and BasGanV2 work reasonably well and similarly one another in semi-quantification of DAT SPECT. Both tools have their own strength and pitfalls that must be known in detail by users in order to obtain the best help in visual reading and reporting of DAT SPECT.

Multimodal dopamine transporter (DAT) imaging and magnetic resonance imaging (MRI) to characterise early Parkinson's disease

Idiopathic Parkinson's disease (PD), the second most common neurodegenerative disorder, is characterised by the progressive loss of dopaminergic nigrostriatal terminals. Currently, in early idiopathic PD, dopamine transporter (DAT)-specific imaging assesses the extent of striatal dopaminergic deficits, and conventional magnetic resonance imaging (MRI) of the brain excludes the presence of significant ischaemic load in the basal ganglia as well as signs indicative of other forms of Parkinsonism. In this article, we discuss the use of multimodal DAT-specific and MRI protocols for insight into the early pathological features of idiopathic PD, including: structural MRI, diffusion tensor imaging, nigrosomal iron imaging and neuromelanin-sensitive MRI sequences. These measures may be acquired serially or simultaneously in a hybrid scanner. From current evidence, it appears that both nigrosomal iron imaging and neuromelanin-sensitive MRI combined with DAT-specific imaging are useful to assist clinicians in diagnosing PD, while conventional structural MRI and diffusion tensor imaging protocols are better suited to a research context focused on characterising early PD pathology. We believe that in the future multimodal imaging will be able to characterise prodromal PD and stratify the clinical stages of PD progression.

EANM practice guideline/SNMMI procedure standard for dopaminergic imaging in Parkinsonian syndromes 1.0

Purpose

This joint practice guideline or procedure standard was developed collaboratively by the European Association of Nuclear Medicine (EANM) and the Society of Nuclear Medicine and Molecular Imaging (SNMMI). The goal of this guideline is to assist nuclear medicine practitioners in recommending, performing, interpreting, and reporting the results of dopaminergic imaging in parkinsonian syndromes.

Methods

Currently nuclear medicine investigations can assess both presynaptic and postsynaptic function of dopaminergic synapses. To date both EANM and SNMMI have published procedural guidelines for dopamine transporter imaging with single photon emission computed tomography (SPECT) (in 2009 and 2011, respectively). An EANM guideline for D2 SPECT imaging is also available (2009). Since the publication of these previous guidelines, new lines of evidence have been made available on semiquantification, harmonization, comparison with normal datasets, and longitudinal analyses of dopamine transporter imaging with SPECT. Similarly, details on acquisition protocols and simplified quantification methods are now available for dopamine transporter imaging with PET, including recently developed fluorinated tracers. Finally, [¹⁸F]fluorodopa PET is now used in some centers for the differential diagnosis of parkinsonism, although procedural guidelines aiming to define standard procedures for [¹⁸F]fluorodopa imaging in this setting are still lacking.

Conclusion

All these emerging issues are addressed in the present procedural guidelines for dopaminergic imaging in parkinsonian syndromes.

Will traditional biopsy be substituted by radiomics and liquid biopsy for breast cancer diagnosis and characterisation?

The diagnosis of breast cancer currently relies on radiological and clinical evaluation, confirmed by histopathological examination. However, such approach has some limitations as the suboptimal sensitivity, the long turnaround time for recall tests, the invasiveness of the procedure and the risk that some features of target lesions may remain undetected, making re-biopsy a necessity. Recent technological advances in the field of artificial intelligence hold promise in addressing such medical challenges not only in cancer diagnosis, but also in treatment assessment, and monitoring of disease progression. In the perspective of a truly personalised medicine, based on the early diagnosis and individually tailored treatments, two new technologies, namely radiomics and liquid biopsy, are rising as means to obtain information from diagnosis to molecular profiling and response assessment, without the need of a biopsied tissue sample. Radiomics works through the extraction of quantitative peculiar features of cancer from radiological data, while liquid biopsy gets the whole of the malignancy's biology from something as easy as a blood sample. Both techniques hopefully will identify diagnostic and prognostic information of breast cancer potentially reducing the need for invasive (and often difficult to perform) biopsies and favouring an approach that is as personalised as possible for each patient. Nevertheless, such techniques will not substitute tissue biopsy in the near future, and even in further times they will require the aid of other parameters to be correctly interpreted and acted upon.

Improvement of classification performance of Parkinson's disease using shape features for machine learning on dopamine transporter single photon emission computed tomography

OBJECTIVE

To assess the classification performance between Parkinson's disease (PD) and normal control (NC) when semi-quantitative indicators and shape features obtained on dopamine transporter (DAT) single photon emission computed tomography (SPECT) are combined as a feature of machine learning (ML).

METHODS

A total of 100 cases of both PD and normal control (NC) from the Parkinson's Progression Markers Initiative database were evaluated. A summed image was generated and regions of interests were set to the left and right striata. Area, equivalent diameter, major axis length, minor axis length, perimeter and circularity were calculated as shape features. Striatum binding ratios (SBRputamen and SBRcaudate) were used as comparison features. The classification performance of the PD and NC groups according to receiver operating characteristic analysis of the shape features was compared in terms of SBRs. Furthermore, we compared the classification performance of ML when shape features or SBRs were used alone and in combination.

RESULTS

The shape features (except minor axis length) and SBRs indicated significant differences between the NC and PD groups (p < 0.05). The top five areas under the curves (AUC) were as follows: circularity (0.972), SBRputamen (0.972), major axis length (0.945), SBRcaudate (0.928) and perimeter (0.896). When classification was done using ML, AUC was as follows: circularity and SBRs (0.995), circularity alone (0.990), and SBRs (0.973). The classification performance was significantly improved by combining SBRs and circularity than by SBRs alone (p = 0.018).

CONCLUSION

We found that the circularity obtained from DAT-SPECT images could help in distinguishing NC and PD. Furthermore, the classification performance of ML was significantly improved using circularity in SBRs together.

Analysis of quantitative [I-123] mIBG SPECT/CT in a phantom and in patients with neuroblastoma

Purpose

To determine the accuracy of quantitative SPECT, intersystem and interpatient standardized uptake value (SUV) calculation consistency for a manufacturer-independent quantitative SPECT/CT reconstruction algorithm, and the range of SUVs of normal and neoplastic tissue.

Methods

A NEMA body phantom with 6 spheres (ranging 10–37 mm) was filled with a known activity-to-volume ratio and used to determine the contrast recovery coefficient (CRC) for each visible sphere, and the measured SUV accuracy of those spheres and background water solution. One hundred eleven 123I-metaiodobenzylguanidine ([I-123] mIBG) SPECT/CT examinations from 43 patients were reconstructed using SUV SPECT® (HERMES Medical Solutions Inc.); 42 examinations were acquired using a GE Infinia Hawkeye 4 SPECT/CT, and 69 were acquired on a Siemens Symbia Intevo SPECT/CT. Inter scanner SUV analysis of 9 regions of normal [I-123] mIBG tissue uptake was conducted. Intrapatient mean SUV variability was calculated by measuring normal liver uptake within patients scanned on both cameras. The intensity of uptake by neoplastic tissue in the images was quantified using maximum SUV and, if present, compared over time.

Results

The phantom results of the visible spheres and background resulted in accuracy calculations better than 5–10% with CRC correction. Interscanner SUV variability showed no statistical difference (average p value 0.559; range 0.066–1.0) among the 9 normal tissues analyzed. Intrapatient liver mean SUV varied ≤ 16% as calculated for 28 patients (87 examinations) studied on both scanners. In one patient, a thoracic tumor evaluated over 10 time points (18 months) underwent a 74% (3.1/12.0) reduction in maximum SUV with treatment.

Conclusion

The results demonstrate quantitative accuracy to better than 10%, and both consistent SUV calculation between 2 different SPECT/CT scanners for 9 tissues, and low intrapatient measurement variability for quantitative SPECT/CT analysis in a pediatric population with neuroblastoma. Quantitative SPECT/CT offers the opportunity for objective analysis of tumor response using [I-123] mIBG by normalizing the uptake to injected dose and patient weight, as is done for PET.

Texture features of magnetic resonance images: A marker of slight cognitive deficits in Parkinson's disease

BACKGROUND

Cognitive impairment is a frequent nonmotor symptom of Parkinson's disease. Depending on severity, patients are considered to have mild cognitive impairment or dementia. However, among the cognitively intact patients, some may have deficits in a less severe range. The early detection of such subtle symptoms may be important for the initiation of care strategies.

OBJECTIVE

To identify imaging markers of early cognitive symptoms, potentially before usual signs, such as atrophy, become manifest.

METHODS

A total of 102 patients with Parkinson's disease and 17 age-matched cognitively intact healthy controls underwent extensive neuropsychological assessment and T1-weighted magnetic resonance imaging. Parkinson's disease patients were separated into 3 groups according to their cognitive status: intact, with slight slowing, and with mild deficits in executive functions. Texture features as measured by first-order and second-order statistics were computed in the following 6 brain regions: the hippocampus, thalamus, amygdala, putamen, caudate nucleus, and pallidum. They were tested between the groups, and their correlation with cognition was examined. Volumetric measurements were made for comparison.

RESULTS

Texture analysis showed significant between-group differences for 2 features-skewness and entropy in the hippocampus, the thalamus, and the amygdala-and the volume analysis revealed no between-group difference. These features were significantly correlated with cognitive performance.

CONCLUSION

These results support the assumption that signal alterations associated with Parkinson's disease-related cognitive decline can be captured very early by texture analysis. As these changes appear to reflect clinical phenomena, texture analysis may be a promising marker for helping cognitive phenotyping in Parkinson's disease. © 2019 International Parkinson and Movement Disorder Society.

Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine

One of the most promising areas of health innovation is the application of artificial intelligence (AI), primarily in medical imaging. This article provides basic definitions of terms such as “machine/deep learning” and analyses the integration of AI into radiology. Publications on AI have drastically increased from about 100–150 per year in 2007–2008 to 700–800 per year in 2016–2017. Magnetic resonance imaging and computed tomography collectively account for more than 50% of current articles. Neuroradiology appears in about one-third of the papers, followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdomen, each representing 6–9% of articles. With an irreversible increase in the amount of data and the possibility to use AI to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Radiologists, who were on the forefront of the digital era in medicine, can guide the introduction of AI into healthcare. Yet, they will not be replaced because radiology includes communication of diagnosis, consideration of patient’s values and preferences, medical judgment, quality assurance, education, policy-making, and interventional procedures. The higher efficiency provided by AI will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.

Dopamine transporter availability reflects gastrointestinal dysautonomia in early Parkinson disease

BACKGROUND

Constipation is a prodromal feature of Parkinson's disease (PD) and the gastrointestinal (GI) tract is implicated in the pathogenesis of PD. However, no studies have demonstrated ante-mortem relationships between nigrostriatal dysfunction and GI dysautonomia in PD.

METHODS

The Scale for Outcomes in Parkinson's disease for Autonomic Symptoms (SCOPA-AUT) assesses dysautonomia in the multi-center Parkinson's Progression Marker Initiative (PPMI). We used linear mixed-effects models and reliable change indices (RCIs) to examine longitudinal associations between dysautonomia and dopamine transporter (DAT) striatal binding ratios (SBRs) measured by single-photon emission computerized tomography in PPMI participants over four years (n = 397 at baseline).

RESULTS

Adjusted mixed-models of longitudinal data showed that constipation-but not orthostatic hypotension or urinary dysfunction-was associated with reduced SBR in both caudate (P < 0.001) and putamen (P = 0.040). In both regions, SBR reductions between baseline and 4-year follow-up were significant and measurable (P < 0.0001), with larger decline and variance in the caudate nucleus. Four-year change in caudate-but not putaminal-SBR was significantly associated with RCI-indicated progression of GI dysautonomia (P = 0.031), but not other types of dysautonomia. These associations remained after adjusting for the use of medications or supplements to control constipation. Consistent with prior PPMI reports, motor impairment progression was not associated with SBR reduction.

CONCLUSIONS

GI dysautonomia correlates with reductions in DAT availability; constipation is most closely associated with caudate-DAT reduction. Worsening GI-dysautonomia and reduced bowel movements may accompany advancing nigral degeneration or changes in nigrostriatal dopamine function.

Advances in PET Methodology

Recent advances in disease understanding, instrumentation technology, and computationally demanding image analysis approaches are opening new frontiers in the investigation of movement disorders and brain disease in general. A key aspect is the recognition of the need to determine molecular correlates to early functional and metabolic connectivity alterations, which are increasingly recognized as useful signatures of specific clinical disease phenotypes. Such multi-modal approaches are highly likely to provide new information on pathogenic mechanisms and to help the identification of novel therapeutic targets. This chapter describes recent methodological developments in PET starting with a very brief overview of radiotracers relevant to movement disorders while emphasizing the development of instrumentation, algorithms and imaging analysis methods relevant to multi-modal investigation of movement disorders.

Radiomics in Nuclear Medicine Applied to Radiation Therapy: Methods, Pitfalls, and Challenges

Radiomics is a recent area of research in precision medicine and is based on the extraction of a large variety of features from medical images. In the field of radiation oncology, comprehensive image analysis is crucial to personalization of treatments. A better characterization of local heterogeneity and the shape of the tumor, depicting individual cancer aggressiveness, could guide dose planning and suggest volumes in which a higher dose is needed for better tumor control. In addition, noninvasive imaging features that could predict treatment outcome from baseline scans could help the radiation oncologist to determine the best treatment strategies and to stratify patients as at low risk or high risk of recurrence. Nuclear medicine molecular imaging reflects information regarding biological processes in the tumor thanks to a wide range of radiotracers. Many studies involving ¹⁸F-fluorodeoxyglucose positron emission tomography suggest an added value of radiomics compared with the use of conventional PET metrics such as standardized uptake value for both tumor diagnosis and prediction of recurrence or treatment outcome. However, these promising results should not hide technical difficulties that still currently prevent the approach from being widely studied or clinically used. These difficulties mostly pertain to the variability of the imaging features as a function of the acquisition device and protocol, the robustness of the models with respect to that variability, and the interpretation of the radiomic models. Addressing the impact of the variability in acquisition and reconstruction protocols is needed, as is harmonizing the radiomic feature calculation methods, to ensure the reproducibility of studies in a multicenter context and their implementation in a clinical workflow. In this review, we explain the potential impact of positron emission tomography radiomics for radiation therapy and underline the various aspects that need to be carefully addressed to make the most of this promising approach.

Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT

OBJECTIVES

To investigate the impact of parameter settings as used for the generation of radiomics features on their robustness and disease differentiation (nasopharyngeal carcinoma (NPC) versus chronic nasopharyngitis (CN) in FDG PET/CT imaging).

METHODS

We studied 106 patients (69/37 NPC/CN, pathology confirmed), and extracted 57 radiomics features under different parameter settings. Robustness was assessed by the intra-class correlation coefficient (ICC). Logistic regression with leave-one-out cross validation was used to generate classification probabilities, and diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).

RESULTS

Varying averaging strategies and symmetry, 4/26 GLCM features showed poor range of pairwise ICCs of 0.02-0.98, while depicting good AUCs of 0.82-0.91. Varying distances, 5/26 GLCM features showed ICCs of 0.82-0.99 while corresponding AUCs were 0.52-0.91. 6/13 GLRLM features showed both high AUC (0.81-0.89) and high ICC (0.85-0.99) regarding to averaging strategies. 7/13 GLSZM features showed AUCs of 0.81-0.90 while having ICCs of 0.01-0.99 under different neighbourhoods. 2/5 NGTDM features showed AUCs of 0.81-0.85 while having ICCs of 0.19-0.89 for different window sizes. Differentiating a subset of NPC (stages I-II) form CN, both SumEntropy and SZLGE achieved significantly higher AUCs than metabolically active tumour volume (AUC: 0.91 vs. 0.72, p<0.01).

CONCLUSIONS

Radiomics features depicting poor absolute-scale robustness regarding to parameter settings can still lead to good diagnostic performance. As such, robustness of radiomics features should not be overemphasized for removal of features towards assessment of clinical tasks. For differentiating NPC from CN, some radiomics features (e.g. SumEntropy, SZLGE, LGZE) outperformed conventional metrics.

KEY POINTS

• Poor robustness did not necessarily translate into poor differentiation performance. • Absolute-scale robustness of radiomics features should not be overemphasized. • Radiomics features SumEntropy, SZLGE and LGZE outperformed conventional metrics.

Neuroimaging in Parkinson's disease: focus on substantia nigra and nigro-striatal projection

PURPOSE OF REVIEW

The diagnosis of Parkinson disease is based on clinical features; however, unmet need is an imaging signature for Parkinson disease and the early differential diagnosis with atypical parkinsonisms. A summary of the molecular imaging and MRI recent evidences for Parkinson disease diagnosis will be presented in this review.

RECENT FINDINGS

The nigro-striatal dysfunction explored by dopamine transporter imaging is not a mandatory diagnostic criterion for Parkinson disease, recent evidence supported its utility as in-vivo proof of degenerative parkinsonisms, and there might be compensatory mechanisms leading to an early overestimation. The visualization of abnormalities in substantia nigra by MRI has been recently described as sensitive and specific tool for Parkinson disease diagnosis, even in preclinical conditions, whereas it is not useful for distinguishing between Parkinson disease and atypical parkinsonisms. The relationship between the nigral anatomical changes, evaluated as structural alterations or neuromelanin signal decrease and the dopaminergic nigro-striatal function needs to be further clarified.

SUMMARY

With the hopeful advent of potential neuroprotective drugs for PD, it is crucial to have imaging measures that are able to detect at risk subjects. Moreover it is desirable to increase the knowledge about which measure better predicts the probability and the time of clinical conversion to PD.

Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

BACKGROUND

Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times.

RESULTS

The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively.

CONCLUSIONS

Classification performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.

Patterns of grey matter loss associated with motor subscores in early Parkinson's disease

Classical motor symptoms of Parkinson's disease (PD) such as tremor, rigidity, bradykinesia, and axial symptoms are graded in the Movement Disorders Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) III. It is yet to be ascertained whether parkinsonian motor symptoms are associated with different anatomical patterns of neurodegeneration as reflected by brain grey matter (GM) alteration. This study aimed to investigate associations between motor subscores and brain GM at voxel level. High resolution structural MRI T1 scans from the Parkinson's Progression Markers Initiative (PPMI) repository were employed to estimate brain GM intensity of PD subjects. Correlations between GM intensity and total MDS-UPDRS III and its four subscores were computed. The total MDS-UPDRS III score was significantly negatively correlated bilaterally with putamen and caudate GM density. Lower anterior striatal GM intensity was significantly associated with higher rigidity subscores, whereas left-sided anterior striatal and precentral cortical GM reduction were correlated with severity of axial symptoms. No significant morphometric associations were demonstrated for tremor subscores. In conclusion, we provide evidence for neuroanatomical patterns underpinning motor symptoms in early PD.

Improved prediction of outcome in Parkinson's disease using radiomics analysis of longitudinal DAT SPECT images

No disease modifying therapies for Parkinson's disease (PD) have been found effective to date. To properly power clinical trials for discovery of such therapies, the ability to predict outcome in PD is critical, and there is a significant need for discovery of prognostic biomarkers of PD. Dopamine transporter (DAT) SPECT imaging is widely used for diagnostic purposes in PD. In the present work, we aimed to evaluate whether longitudinal DAT SPECT imaging can significantly improve prediction of outcome in PD patients. In particular, we investigated whether radiomics analysis of DAT SPECT images, in addition to use of conventional non-imaging and imaging measures, could be used to predict motor severity at year 4 in PD subjects. We selected 64 PD subjects (38 male, 26 female; age at baseline (year 0): 61.9 ± 7.3, range [46,78]) from the Parkinson's Progressive Marker Initiative (PPMI) database. Inclusion criteria included (i) having had at least 2 SPECT scans at years 0 and 1 acquired on a similar scanner, (ii) having undergone a high-resolution 3 T MRI scan, and (iii) having motor assessment (MDS-UPDRS-III) available in year 4 used as outcome measure. Image analysis included automatic region-of-interest (ROI) extraction on MRI images, registration of SPECT images onto the corresponding MRI images, and extraction of radiomic features. Non-imaging predictors included demographics, disease duration as well as motor and non-motor clinical measures in years 0 and 1. The image predictors included 92 radiomic features extracted from the caudate, putamen, and ventral striatum of DAT SPECT images at years 0 and 1 to quantify heterogeneity and texture in uptake. Random forest (RF) analysis with 5000 trees was used to combine both non-imaging and imaging variables to predict motor outcome (UPDRS-III: 27.3 ± 14.7, range [3,77]). The RF prediction was evaluated using leave-one-out cross-validation. Our results demonstrated that addition of radiomic features to conventional measures significantly improved (p < 0.001) prediction of outcome, reducing the absolute error of predicting MDS-UPDRS-III from 9.00 ± 0.88 to 4.12 ± 0.43. This shows that radiomics analysis of DAT SPECT images has a significant potential towards development of effective prognostic biomarkers in PD.

The impact of image reconstruction settings on 18F-FDG PET radiomic features: multi-scanner phantom and patient studies

OBJECTIVES

The purpose of this study was to investigate the robustness of different PET/CT image radiomic features over a wide range of different reconstruction settings.

METHODS

Phantom and patient studies were conducted, including two PET/CT scanners. Different reconstruction algorithms and parameters including number of sub-iterations, number of subsets, full width at half maximum (FWHM) of Gaussian filter, scan time per bed position and matrix size were studied. Lesions were delineated and one hundred radiomic features were extracted. All radiomics features were categorized based on coefficient of variation (COV).

RESULTS

Forty seven percent features showed COV ≤ 5% and 10% of which showed COV > 20%. All geometry based, 44% and 41% of intensity based and texture based features were found as robust respectively. In regard to matrix size, 56% and 6% of all features were found non-robust (COV > 20%) and robust (COV ≤ 5%) respectively.

CONCLUSIONS

Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent, and different settings have different effects on different features. Radiomic features with low COV can be considered as good candidates for reproducible tumour quantification in multi-center studies.

KEY POINTS

• PET/CT image radiomics is a quantitative approach assessing different aspects of tumour uptake. • Radiomic features robustness is an important issue over different image reconstruction settings. • Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent. • Robust radiomic features can be considered as good candidates for tumour quantification.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

After seminal papers over the period 2009 - 2011, the use of texture analysis of PET/CT images for quantification of intratumour uptake heterogeneity has received increasing attention in the last 4 years. Results are difficult to compare due to the heterogeneity of studies and lack of standardization. There are also numerous challenges to address. In this review we provide critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images, identify issues and challenges, and offer recommendations for the use of texture analysis in clinical research. Numerous potentially confounding issues have been identified, related to the complex workflow for the calculation of textural features, and the dependency of features on various factors such as acquisition, image reconstruction, preprocessing, functional volume segmentation, and methods of establishing and quantifying correspondences with genomic and clinical metrics of interest. A lack of understanding of what the features may represent in terms of the underlying pathophysiological processes and the variability of technical implementation practices makes comparing results in the literature challenging, if not impossible. Since progress as a field requires pooling results, there is an urgent need for standardization and recommendations/guidelines to enable the field to move forward. We provide a list of correct formulae for usual features and recommendations regarding implementation. Studies on larger cohorts with robust statistical analysis and machine learning approaches are promising directions to evaluate the potential of this approach.