Improved amyloid burden quantification with nonspecific estimates using deep learning

Evaluation of ComBat harmonization for reducing across-tracer biases in regional amyloid PET analyses

Background

Differences in amyloid positron emission tomography (PET) radiotracer pharmacokinetics and binding properties lead to discrepancies in amyloid-β uptake estimates. Harmonization of tracer-specific biases is crucial for optimal performance of downstream tasks. Here, we investigated the efficacy of ComBat, a data-driven harmonization model, for reducing tracer-specific biases in regional amyloid PET measurements from [18F]-florbetapir (FBP) and [11C]-Pittsburgh Compound-B (PiB).

Methods

One-hundred-thirteen head-to-head FBP-PiB scan pairs, scanned from the same subject within ninety days, were selected from the Open Access Series of Imaging Studies 3 (OASIS-3) dataset. The Centiloid scale, ComBat with no covariates, ComBat with biological covariates, and GAM-ComBat with biological covariates were used to harmonize both global and regional amyloid standardized uptake value ratios (SUVR). Intraclass correlation coefficient (ICC) and mean standardized absolute error (MsAE) were computed to measure the absolute agreement between tracers. Additionally, longitudinal amyloid SUVRs from an anti-amyloid drug trial were simulated using linear mixed effects modeling. Differences in rates-of-change between simulated treatment and placebo groups were tested, and change in statistical power/Type-I error after harmonization was quantified.

Results

In the head-to-head tracer comparison, the best ICC and MsAE were achieved after harmonizing with ComBat with no covariates for the global summary SUVR. ComBat with no covariates also performed the best in harmonizing regional SUVRs. In the clinical trial simulation, harmonization with both Centiloid and ComBat increased statistical power of detecting true rate-of-change differences between groups and decreased false discovery rate in the absence of a treatment effect. The greatest benefit of harmonization was observed when groups exhibited differing FPB-to-PiB proportions.

Conclusions

ComBat outperformed the Centiloid scale in harmonizing both global and regional amyloid estimates. Additionally, ComBat improved the detection of rate-of-change differences between clinical trial groups. Our findings suggest that ComBat is a viable alternative to Centiloid for harmonizing regional amyloid PET analyses.

Machine learning in the positron emission tomography imaging of Alzheimer's disease

The utilization of machine learning techniques in medicine has exponentially increased over the last decades due to innovations in computer processing, algorithm development, and access to big data. Applications of machine learning techniques to neuroimaging specifically have unveiled various hidden interactions, structures, and mechanisms related to various neurological disorders. One application of interest is the imaging of Alzheimer's disease, the most common cause of progressive dementia. The diagnoses of Alzheimer's disease, mild cognitive impairment, and preclinical Alzheimer's disease have been difficult. Molecular imaging, particularly via PET scans, holds tremendous value in the imaging of Alzheimer's disease. To date, many novel algorithms have been developed with great success that leverage machine learning in the context of Alzheimer's disease. This review article provides an overview of the diverse applications of machine learning to PET imaging of Alzheimer's disease.

International Nuclear Medicine Consensus on the Clinical Use of Amyloid Positron Emission Tomography in Alzheimer's Disease

Alzheimer's disease (AD) is the main cause of dementia, with its diagnosis and management remaining challenging. Amyloid positron emission tomography (PET) has become increasingly important in medical practice for patients with AD. To integrate and update previous guidelines in the field, a task group of experts of several disciplines from multiple countries was assembled, and they revised and approved the content related to the application of amyloid PET in the medical settings of cognitively impaired individuals, focusing on clinical scenarios, patient preparation, administered activities, as well as image acquisition, processing, interpretation and reporting. In addition, expert opinions, practices, and protocols of prominent research institutions performing research on amyloid PET of dementia are integrated. With the increasing availability of amyloid PET imaging, a complete and standard pipeline for the entire examination process is essential for clinical practice. This international consensus and practice guideline will help to promote proper clinical use of amyloid PET imaging in patients with AD.

A Systematic Literature Review on Applications of GAN-Synthesized Images for Brain MRI

With the advances in brain imaging, magnetic resonance imaging (MRI) is evolving as a popular radiological tool in clinical diagnosis. Deep learning (DL) methods can detect abnormalities in brain images without an extensive manual feature extraction process. Generative adversarial network (GAN)-synthesized images have many applications in this field besides augmentation, such as image translation, registration, super-resolution, denoising, motion correction, segmentation, reconstruction, and contrast enhancement. The existing literature was reviewed systematically to understand the role of GAN-synthesized dummy images in brain disease diagnosis. Web of Science and Scopus databases were extensively searched to find relevant studies from the last 6 years to write this systematic literature review (SLR). Predefined inclusion and exclusion criteria helped in filtering the search results. Data extraction is based on related research questions (RQ). This SLR identifies various loss functions used in the above applications and software to process brain MRIs. A comparative study of existing evaluation metrics for GAN-synthesized images helps choose the proper metric for an application. GAN-synthesized images will have a crucial role in the clinical sector in the coming years, and this paper gives a baseline for other researchers in the field.

β-amyloid PET harmonisation across longitudinal studies: Application to AIBL, ADNI and OASIS3

INTRODUCTION

The Centiloid scale was developed to harmonise the quantification of β-amyloid (Aβ) PET images across tracers, scanners, and processing pipelines. However, several groups have reported differences across tracers and scanners even after centiloid conversion. In this study, we aim to evaluate the impact of different pre and post-processing harmonisation steps on the robustness of longitudinal Centiloid data across three large international cohort studies.

METHODS

All Aβ PET data in AIBL (N = 3315), ADNI (N = 3442) and OASIS3 (N = 1398) were quantified using the MRI-based Centiloid standard SPM pipeline and the PET-only pipeline CapAIBL. SUVR were converted into Centiloids using each tracer's respective transform. Global Aβ burden from pre-defined target cortical regions in Centiloid units were quantified for both raw PET scans and PET scans smoothed to a uniform 8 mm full width half maximum (FWHM) effective smoothness. For Florbetapir, we assessed the performance of using both the standard Whole Cerebellum (WCb) and a composite white matter (WM)+WCb reference region. Additionally, our recently proposed quantification based on Non-negative Matrix Factorisation (NMF) was applied to all spatially and SUVR normalised images. Correlation with clinical severity measured by the Mini-Mental State Examination (MMSE) and effect size, as well as tracer agreement in 11C-PiB-18F-Florbetapir pairs and longitudinal consistency were evaluated.

RESULTS

The smoothing to a uniform resolution partially reduced longitudinal variability, but did not improve inter-tracer agreement, effect size or correlation with MMSE. Using a Composite reference region for 18F-Florbetapir improved inter-tracer agreement, effect size, correlation with MMSE, and longitudinal consistency. The best results were however obtained when using the NMF method which outperformed all other quantification approaches in all metrics used.

CONCLUSIONS

FWHM smoothing has limited impact on longitudinal consistency or outliers. A Composite reference region including subcortical WM should be used for computing both cross-sectional and longitudinal Florbetapir Centiloid. NMF improves Centiloid quantification on all metrics examined.

Validation of deep learning-based nonspecific estimates for amyloid burden quantification with longitudinal data

PURPOSE

To validate our previously proposed method of quantifying amyloid-beta (Aβ) load using nonspecific (NS) estimates generated with convolutional neural networks (CNNs) using [¹⁸F]Florbetapir scans from longitudinal and multicenter ADNI data.

METHODS

188 paired MR (T1-weighted and T2-weighted) and PET images were downloaded from the ADNI3 dataset, of which 49 subjects had 2 time-point scans. 40 Aβ- subjects with low specific uptake were selected for training. Multimodal ScaleNet (SN) and monomodal HighRes3DNet (HRN), using either T1-weighted or T2-weighted MR images as inputs) were trained to map structural MR to NS-PET images. The optimized SN and HRN networks were used to estimate the NS for all scans and then subtracted from SUVr images to determine the specific amyloid load (SAβ_L) images. The association of SAβ_L with various cognitive and functional test scores was evaluated using Spearman analysis, as well as the differences in SAβ_L with cognitive test scores for 49 subjects with 2 time-point scans and sensitivity analysis.

RESULTS

SAβ_L derived from both SN and HRN showed higher association with memory-related cognitive test scores compared to SUVr. However, for longitudinal scans, only SAβ_L estimated from multimodal SN consistently performed better than SUVr for all memory-related cognitive test scores.

CONCLUSIONS

Our proposed method of quantifying Aβ load using NS estimated from CNN correlated better than SUVr with cognitive decline for both static and longitudinal data, and was able to estimate NS of [¹⁸F]Florbetapir. We suggest employing multimodal networks with both T1-weighted and T2-weighted MR images for better NS estimation.

Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review

PURPOSE

This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years.

METHODS

The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information.

RESULTS

The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works.

CONCLUSION

GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.

Identifying Mild Alzheimer's Disease With First 30-Min 11C-PiB PET Scan

Introduction

¹¹C-labeled Pittsburgh compound B (¹¹C-PiB) PET imaging can provide information for the diagnosis of Alzheimer's disease (AD) by quantifying the binding of PiB to β-amyloid deposition in the brain. Quantification index, such as standardized uptake value ratio (SUVR) and distribution volume ratio (DVR), has been exploited to effectively distinguish between healthy and subjects with AD. However, these measures require a long wait/scan time, as well as the selection of an optimal reference region. In this study, we propose an alternate measure named amyloid quantification index (AQI), which can be obtained with the first 30-min scan without the selection of the reference region.

Methods

¹¹C-labeled Pittsburgh compound B PET scan data were obtained from the public dataset "OASIS-3". A total of 60 mild subjects with AD and 60 healthy controls were included, with 50 used for training and 10 used for testing in each group. The proposed measure AQI combines information of clearance rate and mid-phase PIB retention in featured brain regions from the first 30-min scan. For each subject in the training set, AQI, SUVR, and DVR were calculated and used for classification by the logistic regression classifier. The receiver operating characteristic (ROC) analysis was performed to evaluate the performance of these measures. Accuracy, sensitivity, and specificity were reported. The Kruskal-Wallis test and effect size were also performed and evaluated for all measures. Then, the performance of three measures was further validated on the testing set using the same method. The correlations between these measures and clinical MMSE and CDR-SOB scores were analyzed.

Results

The Kruskal-Wallis test suggested that AQI, SUVR, and DVR can all differentiate between the healthy and subjects with mild AD (p < 0.001). For the training set, ROC analysis showed that AQI achieved the best classification performance with an accuracy rate of 0.93, higher than 0.88 for SUVR and 0.89 for DVR. The effect size of AQI, SUVR, and DVR were 2.35, 2.12, and 2.06, respectively, indicating that AQI was the most effective among these measures. For the testing set, all three measures achieved less superior performance, while AQI still performed the best with the highest accuracy of 0.85. Some false-negative cases with below-threshold SUVR and DVR values were correctly identified using AQI. All three measures showed significant and comparable correlations with clinical scores (p < 0.01).

Conclusion

Amyloid quantification index combines early-phase kinetic information and a certain degree of β-amyloid deposition, and can provide a better differentiating performance using the data from the first 30-min dynamic scan. Moreover, it was shown that clinically indistinguishable AD cases regarding PiB retention potentially can be correctly identified.

Application of artificial intelligence in brain molecular imaging

Initial development of artificial Intelligence (AI) and machine learning (ML) dates back to the mid-twentieth century. A growing awareness of the potential for AI, as well as increases in computational resources, research, and investment are rapidly advancing AI applications to medical imaging and, specifically, brain molecular imaging. AI/ML can improve imaging operations and decision making, and potentially perform tasks that are not readily possible by physicians, such as predicting disease prognosis, and identifying latent relationships from multi-modal clinical information. The number of applications of image-based AI algorithms, such as convolutional neural network (CNN), is increasing rapidly. The applications for brain molecular imaging (MI) include image denoising, PET and PET/MRI attenuation correction, image segmentation and lesion detection, parametric image formation, and the detection/diagnosis of Alzheimer's disease and other brain disorders. When effectively used, AI will likely improve the quality of patient care, instead of replacing radiologists. A regulatory framework is being developed to facilitate AI adaptation for medical imaging.

Deep learning improves utility of tau PET in the study of Alzheimer's disease

INTRODUCTION

Positron emission tomography (PET) imaging targeting neurofibrillary tau tangles is increasingly used in the study of Alzheimer's disease (AD), but its utility may be limited by conventional quantitative or qualitative evaluation techniques in earlier disease states. Convolutional neural networks (CNNs) are effective in learning spatial patterns for image classification.

METHODS

18F-MK6240 (n = 320) and AV-1451 (n = 446) PET images were pooled from multiple studies. We performed iterations with differing permutations of radioligands, heuristics, and architectures. Performance was compared to a standard region of interest (ROI)-based approach on prediction of memory impairment. We visualized attention of the network to illustrate decision making.

RESULTS

Overall, models had high accuracy (> 80%) with good average sensitivity and specificity (75% and 82%, respectively), and had comparable or higher accuracy to the ROI standard. Visualizations of model attention highlight known characteristics of tau radioligand binding.

DISCUSSION

CNNs could improve tau PET's role in early disease and extend the utility of tau PET across generations of radioligands.

Artificial intelligence with deep learning in nuclear medicine and radiology

The use of deep learning in medical imaging has increased rapidly over the past few years, finding applications throughout the entire radiology pipeline, from improved scanner performance to automatic disease detection and diagnosis. These advancements have resulted in a wide variety of deep learning approaches being developed, solving unique challenges for various imaging modalities. This paper provides a review on these developments from a technical point of view, categorizing the different methodologies and summarizing their implementation. We provide an introduction to the design of neural networks and their training procedure, after which we take an extended look at their uses in medical imaging. We cover the different sections of the radiology pipeline, highlighting some influential works and discussing the merits and limitations of deep learning approaches compared to other traditional methods. As such, this review is intended to provide a broad yet concise overview for the interested reader, facilitating adoption and interdisciplinary research of deep learning in the field of medical imaging.

Prediction of post-stroke cognitive impairment using brain FDG PET: deep learning-based approach

PURPOSE

Post-stroke cognitive impairment can affect up to one third of stroke survivors. Since cognitive function greatly contributes to patients' quality of life, an objective quantitative biomarker for early prediction of dementia after stroke is required. We developed a deep-learning (DL)-based signature using positron emission tomography (PET) to objectively evaluate cognitive decline in patients with stroke.

METHODS

We built a DL model that differentiated Alzheimer's disease (AD) from normal controls (NC) using brain fluorodeoxyglucose (FDG) PET from the Alzheimer's Disease Neuroimaging Initiative database. The model was directly transferred to a prospectively enrolled cohort of patients with stroke to differentiate patients with dementia from those without dementia. The accuracy of the model was evaluated by the area under the curve values of receiver operating characteristic curves (AUC-ROC). We visualized the distribution of DL-based features and brain regions that the model weighted for classification. Correlations between cognitive signature from the DL model and clinical variables were evaluated, and survival analysis for post-stroke dementia was performed in patients with stroke.

RESULTS

The classification of AD vs. NC subjects was performed with AUC-ROC of 0.94 (95% confidence interval [CI], 0.89-0.98). The transferred model discriminated stroke patients with dementia (AUC-ROC = 0.75). The score of cognitive decline signature using FDG PET was positively correlated with age, neutrophil-lymphocyte ratio and platelet-lymphocyte ratio and negatively correlated with body mass index in patients with stroke. We found that the cognitive decline score was an independent risk factor for dementia following stroke (hazard ratio, 10.90; 95% CI, 3.59-33.09; P < 0.0001) after adjustment for other key variables.

CONCLUSION

The DL-based cognitive signature using FDG PET was successfully transferred to an independent stroke cohort. It is suggested that DL-based cognitive evaluation using FDG PET could be utilized as an objective biomarker for cognitive dysfunction in patients with cerebrovascular diseases.