APPIAN: Automated Pipeline for PET Image Analysis

Deep learning model for automatic image quality assessment in PET

BACKGROUND

A variety of external factors might seriously degrade PET image quality and lead to inconsistent results. The aim of this study is to explore a potential PET image quality assessment (QA) method with deep learning (DL).

METHODS

A total of 89 PET images were acquired from Peking Union Medical College Hospital (PUMCH) in China in this study. Ground-truth quality for images was assessed by two senior radiologists and classified into five grades (grade 1, grade 2, grade 3, grade 4, and grade 5). Grade 5 is the best image quality. After preprocessing, the Dense Convolutional Network (DenseNet) was trained to automatically recognize optimal- and poor-quality PET images. Accuracy (ACC), sensitivity, specificity, receiver operating characteristic curve (ROC), and area under the ROC Curve (AUC) were used to evaluate the diagnostic properties of all models. All indicators of models were assessed using fivefold cross-validation. An image quality QA tool was developed based on our deep learning model. A PET QA report can be automatically obtained after inputting PET images.

RESULTS

Four tasks were generated. Task2 showed worst performance in AUC,ACC, specificity and sensitivity among 4 tasks, and task1 showed unstable performance between training and testing and task3 showed low specificity in both training and testing. Task 4 showed the best diagnostic properties and discriminative performance between poor image quality (grade 1, grade 2) and good quality (grade 3, grade 4, grade 5) images. The automated quality assessment of task 4 showed ACC = 0.77, specificity = 0.71, and sensitivity = 0.83, in the train set; ACC = 0.85, specificity = 0.79, and sensitivity = 0.91, in the test set, respectively. The ROC measuring performance of task 4 had an AUC of 0.86 in the train set and 0.91 in the test set. The image QA tool could output basic information of images, scan and reconstruction parameters, typical instances of PET images, and deep learning score.

CONCLUSIONS

This study highlights the feasibility of the assessment of image quality in PET images using a deep learning model, which may assist with accelerating clinical research by reliably assessing image quality.

The impact of subthreshold levels of amyloid deposition on conversion to dementia in patients with amyloid-negative amnestic mild cognitive impairment

BACKGROUND

About 40-50% of patients with amnestic mild cognitive impairment (MCI) are found to have no significant Alzheimer's pathology based on amyloid PET positivity. Notably, conversion to dementia in this population is known to occur much less often than in amyloid-positive MCI. However, the relationship between MCI and brain amyloid deposition remains largely unknown. Therefore, we investigated the influence of subthreshold levels of amyloid deposition on conversion to dementia in amnestic MCI patients with negative amyloid PET scans.

METHODS

This study was a retrospective cohort study of patients with amyloid-negative amnestic MCI who visited the memory clinic of Asan Medical Center. All participants underwent detailed neuropsychological testing, brain magnetic resonance imaging, and [18F]-florbetaben (FBB) positron emission tomography scan (PET). Conversion to dementia was determined by a neurologist based on a clinical interview with a detailed neuropsychological test or a decline in the Korean version of the Mini-Mental State Examination score of more than 4 points per year combined with impaired activities of daily living. Regional cortical amyloid levels were calculated, and a receiver operating characteristic (ROC) curve for conversion to dementia was obtained. To increase the reliability of the results of the study, we analyzed the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset together.

RESULTS

During the follow-up period, 36% (39/107) of patients converted to dementia from amnestic MCI. The dementia converter group displayed increased standardized uptake value ratio (SUVR) values of FBB on PET in the bilateral temporal, parietal, posterior cingulate, occipital, and left precuneus cortices as well as increased global SUVR. Among volume of interests, the left parietal SUVR predicted conversion to dementia with the highest accuracy in the ROC analysis (area under the curve [AUC] = 0.762, P < 0.001). The combination of precuneus, parietal cortex, and FBB composite SUVRs also showed a higher accuracy in predicting conversion to dementia than other models (AUC = 0.763). Of the results of ADNI data, the SUVR of the left precuneus SUVR showed the highest AUC (AUC = 0.596, P = 0.006).

CONCLUSION

Our findings suggest that subthreshold amyloid levels may contribute to conversion to dementia in patients with amyloid-negative amnestic MCI.

Automated Data Quality Control in FDOPA brain PET Imaging using Deep Learning

INTRODUCTION

With biomedical imaging research increasingly using large datasets, it becomes critical to find operator-free methods to quality control the data collected and the associated analysis. Attempts to use artificial intelligence (AI) to perform automated quality control (QC) for both single-site and multi-site datasets have been explored in some neuroimaging techniques (e.g. EEG or MRI), although these methods struggle to find replication in other domains. The aim of this study is to test the feasibility of an automated QC pipeline for brain [¹⁸F]-FDOPA PET imaging as a biomarker for the dopamine system.

METHODS

Two different Convolutional Neural Networks (CNNs) were used and combined to assess spatial misalignment to a standard template and the signal-to-noise ratio (SNR) relative to 200 static [¹⁸F]-FDOPA PET images that had been manually quality controlled from three different PET/CT scanners. The scans were combined with an additional 400 scans, in which misalignment (200 scans) and low SNR (200 scans) were simulated. A cross-validation was performed, where 80% of the data were used for training and 20% for validation. Two additional datasets of [¹⁸F]-FDOPA PET images (50 and 100 scans respectively with at least 80% of good quality images) were used for out-of-sample validation.

RESULTS

The CNN performance was excellent in the training dataset (accuracy for motion: 0.86 ± 0.01, accuracy for SNR: 0.69 ± 0.01), leading to 100% accurate QC classification when applied to the two out-of-sample datasets. Data dimensionality reduction affected the generalizability of the CNNs, especially when the classifiers were applied to the out-of-sample data from 3D to 1D datasets.

CONCLUSIONS

This feasibility study shows that it is possible to perform automatic QC of [¹⁸F]-FDOPA PET imaging with CNNs. The approach has the potential to be extended to other PET tracers in both brain and non-brain applications, but it is dependent on the availability of large datasets necessary for the algorithm training.

MP3: Medical Software for Processing Multi-Parametric Images Pipelines

This article presents an open source software able to convert, display, and process medical images. It differentiates itself from the existing software by its ability to design complex processing pipelines and to wisely execute them on a large databases. An MP3 pipeline can contain unlimited homemade or ready-made processes and can be carried out with a parallel execution system. As a viewer, MP3 allows display of up to four images together and to draw Regions Of Interest (ROI). Two applications showing the strengths of the software are presented as examples: a preclinical study involving Magnetic Resonance Imaging (MRI) data and a clinical one involving Computed Tomography (CT) images. MP3 is downloadable at https://github.com/nifm-gin/MP3.

Kinfitr - an open-source tool for reproducible PET modelling: validation and evaluation of test-retest reliability

BACKGROUND

In positron emission tomography (PET) imaging, binding is typically estimated by fitting pharmacokinetic models to the series of measurements of radioactivity in the target tissue following intravenous injection of a radioligand. However, there are multiple different models to choose from and numerous analytical decisions that must be made when modelling PET data. Therefore, it is important that analysis tools be adapted to the specific circumstances, and that analyses be documented in a transparent manner. Kinfitr, written in the open-source programming language R, is a tool developed for flexible and reproducible kinetic modelling of PET data, i.e. performing all steps using code which can be publicly shared in analysis notebooks. In this study, we compared outcomes obtained using kinfitr with those obtained using PMOD: a widely used commercial tool.

RESULTS

Using previously collected test-retest data obtained with four different radioligands, a total of six different kinetic models were fitted to time-activity curves derived from different brain regions. We observed good correspondence between the two kinetic modelling tools both for binding estimates and for microparameters. Likewise, no substantial differences were observed in the test-retest reliability estimates between the two tools.

CONCLUSIONS

In summary, we showed excellent agreement between the open-source R package kinfitr, and the widely used commercial application PMOD. We, therefore, conclude that kinfitr is a valid and reliable tool for kinetic modelling of PET data.

Magia: Robust Automated Image Processing and Kinetic Modeling Toolbox for PET Neuroinformatics

Processing of positron emission tomography (PET) data typically involves manual work, causing inter-operator variance. Here we introduce the Magia toolbox that enables processing of brain PET data with minimal user intervention. We investigated the accuracy of Magia with four tracers: [11C]carfentanil, [11C]raclopride, [11C]MADAM, and [11C]PiB. We used data from 30 control subjects for each tracer. Five operators manually delineated reference regions for each subject. The data were processed using Magia using the manually and automatically generated reference regions. We first assessed inter-operator variance resulting from the manual delineation of reference regions. We then compared the differences between the manually and automatically produced reference regions and the subsequently obtained binding potentials and standardized-uptake-value-ratios. The results show that manually produced reference regions can be remarkably different from each other, leading to substantial differences also in outcome measures. While the Magia-derived reference regions were anatomically different from the manual ones, Magia produced outcome measures highly consistent with the average of the manually obtained estimates. For [11C]carfentanil and [11C]PiB there was no bias, while for [11C]raclopride and [11C]MADAM Magia produced 3-5% higher binding potentials. Based on these results and considering the high inter-operator variance of the manual method, we conclude that Magia can be reliably used to process brain PET data.