Dataset Information

Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

ABSTRACT:

Purpose

We developed a machine learning-based classifier for in vivo amyloid positron emission tomography (PET) staging, quantified cortical uptake of the PET tracer by using a machine learning method, and investigated the impact of these amyloid PET parameters on clinical and structural outcomes.

Methods

A total of 337 ¹⁸F-florbetaben PET scans obtained at Samsung Medical Center were assessed. We defined a feature vector representing the change in PET tracer uptake from grey to white matter. Using support vector machine (SVM) regression and SVM classification, we quantified the cortical uptake as predicted regional cortical tracer uptake (pRCTU) and categorised the scans as positive and negative. Positive scans were further classified into two stages according to the striatal uptake. We compared outcome parameters among stages and further assessed the association between the pRCTU and outcome variables. Finally, we performed path analysis to determine mediation effects between PET variables.

Results

The classification accuracy was 97.3% for cortical amyloid positivity and 91.1% for striatal positivity. The left frontal and precuneus/posterior cingulate regions, as well as the anterior portion of the striatum, were important in determination of stages. The clinical scores and magnetic resonance imaging parameters showed negative associations with PET stage. However, except for the hippocampal volume, most outcomes were associated with the stage through the complete mediation effect of pRCTU.

Conclusion

Using a machine learning algorithm, we achieved high accuracy for in vivo amyloid PET staging. The in vivo amyloid stage was associated with cognitive function and cerebral atrophy mostly through the mediation effect of cortical amyloid.

SUBMITTER: Kim JP

PROVIDER: S-EPMC7299909 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

Kim Jun Pyo JP Kim Jeonghun J Kim Yeshin Y Moon Seung Hwan SH Park Yu Hyun YH Yoo Sole S Jang Hyemin H Kim Hee Jin HJ Na Duk L DL Seo Sang Won SW Seong Joon-Kyung JK

European journal of nuclear medicine and molecular imaging 20191228 8

<h4>Purpose</h4>We developed a machine learning-based classifier for in vivo amyloid positron emission tomography (PET) staging, quantified cortical uptake of the PET tracer by using a machine learning method, and investigated the impact of these amyloid PET parameters on clinical and structural outcomes.<h4>Methods</h4>A total of 337 <sup>18</sup>F-florbetaben PET scans obtained at Samsung Medical Center were assessed. We defined a feature vector representing the change in PET tracer uptake fro ...[more]

PMID: 31884562

Similar Datasets

Project description:Structural MR images concomitantly acquired with PET images can provide crucial anatomic information for precise quantitative analysis. However, in the clinical setting, not all the subjects have corresponding MR images. Here, we developed a model to generate structural MR images from amyloid PET using deep generative networks. We applied our model to quantification of cortical amyloid load without structural MR. Methods: We used florbetapir PET and structural MR data from the Alzheimer Disease Neuroimaging Initiative database. The generative network was trained to generate realistic structural MR images from florbetapir PET images. After the training, the model was applied to the quantification of cortical amyloid load. PET images were spatially normalized to the template space using the generated MR, and then SUV ratio (SUVR) of the target regions was measured by predefined regions of interest. A real MR-based quantification was used as the gold standard to measure the accuracy of our approach. Other MR-less methods-a normal PET template-based, a multiatlas PET template-based, and a PET segmentation-based normalization/quantification-were also tested. We compared the performance of quantification methods using generated MR with that of MR-based and MR-less quantification methods. Results: Generated MR images from florbetapir PET showed signal patterns that were visually similar to the real MR. The structural similarity index between real and generated MR was 0.91 ± 0.04. The mean absolute error of SUVR of cortical composite regions estimated by the generated MR-based method was 0.04 ± 0.03, which was significantly smaller than other MR-less methods (0.29 ± 0.12 for the normal PET template, 0.12 ± 0.07 for the multiatlas PET template, and 0.08 ± 0.06 for the PET segmentation-based methods). Bland-Altman plots revealed that the generated MR-based SUVR quantification was the closest to the SUVRs estimated by the real MR-based method. Conclusion: Structural MR images were successfully generated from amyloid PET images using deep generative networks. Generated MR images could be used as templates for accurate and precise amyloid quantification. This generative method might be used to generate multimodal images of various organs for further quantitative analyses.

Project description:BackgroundA low amount and extent of Aβ deposition at early stages of Alzheimer's disease (AD) may limit the use of previously developed pathology-proven composite SUVR cutoffs. This study aims to characterize the population with earliest abnormal Aβ accumulation using 18F-florbetaben PET. Quantitative thresholds for the early (SUVRearly) and established (SUVRestab) Aβ deposition were developed, and the topography of early Aβ deposition was assessed. Subsequently, Aβ accumulation over time, progression from mild cognitive impairment (MCI) to AD dementia, and tau deposition were assessed in subjects with early and established Aβ deposition.MethodsThe study population consisted of 686 subjects (n = 287 (cognitively normal healthy controls), n = 166 (subjects with subjective cognitive decline (SCD)), n = 129 (subjects with MCI), and n = 101 (subjects with AD dementia)). Three categories in the Aβ-deposition continuum were defined based on the developed SUVR cutoffs: Aβ-negative subjects, subjects with early Aβ deposition ("gray zone"), and subjects with established Aβ pathology.ResultsSUVR using the whole cerebellum as the reference region and centiloid (CL) cutoffs for early and established amyloid pathology were 1.10 (13.5 CL) and 1.24 (35.7 CL), respectively. Cingulate cortices and precuneus, frontal, and inferior lateral temporal cortices were the regions showing the initial pathological tracer retention. Subjects in the "gray zone" or with established Aβ pathology accumulated more amyloid over time than Aβ-negative subjects. After a 4-year clinical follow-up, none of the Aβ-negative or the gray zone subjects progressed to AD dementia while 91% of the MCI subjects with established Aβ pathology progressed. Tau deposition was infrequent in those subjects without established Aβ pathology.ConclusionsThis study supports the utility of using two cutoffs for amyloid PET abnormality defining a "gray zone": a lower cutoff of 13.5 CL indicating emerging Aβ pathology and a higher cutoff of 35.7 CL where amyloid burden levels correspond to established neuropathology findings. These cutoffs define a subset of subjects characterized by pre-AD dementia levels of amyloid burden that precede other biomarkers such as tau deposition or clinical symptoms and accelerated amyloid accumulation. The determination of different amyloid loads, particularly low amyloid levels, is useful in determining who will eventually progress to dementia. Quantitation of amyloid provides a sensitive measure in these low-load cases and may help to identify a group of subjects most likely to benefit from intervention.Trial registrationData used in this manuscript belong to clinical trials registered in ClinicalTrials.gov ( NCT00928304 , NCT00750282 , NCT01138111 , NCT02854033 ) and EudraCT (2014-000798-38).

Project description:The reference standard for spatial normalization of brain positron emission tomography (PET) images involves structural Magnetic Resonance Imaging (MRI) data. However, the lack of such structural information is fairly common in clinical settings. This might lead to lack of proper image quantification and to evaluation based only on visual ratings, which does not allow research studies or clinical trials based on quantification. PET/CT systems are widely available and CT normalization procedures need to be explored. Here we describe and validate a procedure for the spatial normalization of PET images based on the low-dose Computed Tomography (CT) images contextually acquired for attenuation correction in PET/CT systems. We included N?=?34 subjects, spanning from cognitively normal to mild cognitive impairment and dementia, who underwent amyloid-PET/CT (18F-Florbetaben) and structural MRI scans. The proposed pipeline is based on the SPM12 unified segmentation algorithm applied to low-dose CT images. The validation of the normalization pipeline focused on 1) statistical comparisons between regional and global 18F-Florbetaben-PET/CT standardized uptake value ratios (SUVrs) estimated from both CT-based and MRI-based normalized PET images (SUVrCT, SUVrMRI) and 2) estimation of the degrees of overlap between warped gray matter (GM) segmented maps derived from CT- and MRI-based spatial transformations. We found negligible deviations between regional and global SUVrs in the two CT and MRI-based methods. SUVrCT and SUVrMRI global uptake scores showed negligible differences (mean?±?sd 0.01?±?0.03). Notably, the CT- and MRI-based warped GM maps showed excellent overlap (90% within 1?mm). The proposed analysis pipeline, based on low-dose CT images, allows accurate spatial normalization and subsequent PET image quantification. A CT-based analytical pipeline could benefit both research and clinical practice, allowing the recruitment of larger samples and favoring clinical routine analysis.

Project description:High accuracy has been reported in deep learning classification for amyloid brain scans, an important factor in Alzheimer's disease diagnosis. However, the possibility of overfitting should be considered, as this model is fitted with sample data. Therefore, we created and evaluated an [18F]Florbetaben amyloid brain positron emission tomography (PET) scan classification model with a Dong-A University Hospital (DAUH) dataset based on a convolutional neural network (CNN), and performed external validation with the Alzheimer's Disease Neuroimaging Initiative dataset. Spatial normalization, count normalization, and skull stripping preprocessing were performed on the DAUH and external datasets. However, smoothing was only performed on the external dataset. Three types of models were used, depending on their structure: Inception3D, ResNet3D, and VGG3D. After training with 80% of the DAUH dataset, an appropriate model was selected, and the rest of the DAUH dataset was used for model evaluation. The generalization potential of the selected model was then validated using the external dataset. The accuracy of the model evaluation for Inception3D, ResNet3D, and VGG3D was 95.4%, 92.0%, and 97.7%, and the accuracy of the external validation was 76.7%, 67.1%, and 85.3%, respectively. Inception3D and ResNet3D were retrained with the external dataset; then, the area under the curve was compared to determine the binary classification performance with a significance level of less than 0.05. When external validation was performed again after fine tuning, the performance improved to 15.3%p for Inception3D and 16.9%p for ResNet3D. In [18F]Florbetaben amyloid brain PET scan classification using CNN, the generalization potential can be seen through external validation. When there is a significant difference between the model classification performance and the external validation, changing the model structure or fine tuning the model can help improve the classification performance, and the optimal model can also be found by collaborating through a web-based open platform.

Project description:PurposeIn PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers.MethodsIn 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework.ResultsIn the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1-87.8] for identification of suspicious uptake sites, 77% (CI: 70.0-83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage.ConclusionThe evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.

Dataset Information

Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

Purpose

Methods

Results

Conclusion

Publications

Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets