Longitudinal changes in metabolic network activity in early Alzheimer's disease.

INTRODUCTION: The progression of Alzheimer's disease (AD) has been linked to two metabolic networks, the AD-related pattern (ADRP) and the default mode network (DMN). METHODS: Converting and clinically stable cognitively normal subjects (n = 47) and individuals with mild cognitive impairment (n = 96) underwent 2-[18 F]fluoro-2-deoxy-D-glucose (FDG) positron emission tomography (PET) three or more times over 6 years (nscans  = 705). Expression levels for ADRP and DMN were measured in each subject and time point, and the resulting changes were correlated with cognitive performance. The role of network expression in predicting conversion to dementia was also evaluated. RESULTS: Longitudinal increases in ADRP expression were observed in converters, while age-related DMN loss was seen in converters and nonconverters. Cognitive decline correlated with increases in ADRP and declines in DMN, but conversion to dementia was predicted only by baseline ADRP levels. DISCUSSION: The results point to the potential utility of ADRP as an imaging biomarker of AD progression.

Multi-center Integrating Radiomics, Structured Reports, and Machine Learning Algorithms for Assisted Classification of COVID-19 in Lung Computed Tomography.

Purpose: To evaluate the classification performance of structured report features, radiomics, and machine learning (ML) models to differentiate between Coronavirus Disease 2019 (COVID-19) and other types of pneumonia using chest computed tomography (CT) scans. Methods: Sixty-four COVID-19 subjects and 64 subjects with non-COVID-19 pneumonia were selected. The data was split into two independent cohorts: one for the structured report, radiomic feature selection and model building (n = 73), and another for model validation (n = 55). Physicians performed readings with and without machine learning support. The model's sensitivity and specificity were calculated, and inter-rater reliability was assessed using Cohen's Kappa agreement coefficient. Results: Physicians performed with mean sensitivity and specificity of 83.4 and 64.3%, respectively. When assisted with machine learning, the mean sensitivity and specificity increased to 87.1 and 91.1%, respectively. In addition, machine learning improved the inter-rater reliability from moderate to substantial. Conclusion: Integrating structured reports and radiomics promises assisted classification of COVID-19 in CT chest scans.

A strategy for estimating radiation dose to the blood in outpatient settings in differentiated thyroid cancer therapy with 131I-NaI.

BACKGROUND: Although standard operational procedures for pre-therapeutic dosimetry already exist for the determination of the maximum safe activity to treat differentiated thyroid cancer patients, empiric activity administration of 131I is still the most frequent way of treatment. In this way, the absorbed dose to the blood/bone marrow remains unknown. PURPOSE: In this work, we present a strategy to estimate radiation dose to the blood in an outpatient setting. METHODS: A mobile application was developed, which together with an off-the-shelf compact semiconductor radiation detector allows the determination of whole-body time-integrated activity coefficients. The methodology was tested in a cohort of 79 differentiated cancer patients who received therapeutic 131I activities. Post-therapeutic whole-body time-integrated activity coefficients were compared against pre-therapeutic estimates in a subset of 13 patients. RESULTS: The 95% limits of agreement between pre whole-body and post whole-body time integrated activity coefficients were [-14.4; 6.6] h when considering outliers and [-6.2; 3.6] h without outliers. A high dispersion in blood dose coefficients was found, with a four-fold difference between the highest and lower values. Blood doses were significantly higher for patients treated with dosimetrically guided activities than for empirical activities (median dose = 118 vs. 49 cGy, respectively). Blood dose coefficients were significantly lower for patients prepared with recombinant human thyroid stimulating hormone (rhTSH) than for patients prepared with thyroid hormone withdrawal. A low correlation between blood dose and administered activity was found in empirically treated patients (R2 = 0.26). CONCLUSIONS: We successfully implemented a post-therapeutic internal dosimetry methodology for differentiated thyroid cancer therapy with 131I, which allows to estimate dose to the blood from outpatient measurements with mobile devices. The proposed methodology avoids the need of daily visits to the nuclear medicine department, thus reducing the burden for the patient and for the staff.

A machine-learning regional clustering approach to understand ventilator-induced lung injury: a proof-of-concept experimental study.

BACKGROUND: The spatiotemporal progression and patterns of tissue deformation in ventilator-induced lung injury (VILI) remain understudied. Our aim was to identify lung clusters based on their regional mechanical behavior over space and time in lungs subjected to VILI using machine-learning techniques. RESULTS: Ten anesthetized pigs (27 ± 2 kg) were studied. Eight subjects were analyzed. End-inspiratory and end-expiratory lung computed tomography scans were performed at the beginning and after 12 h of one-hit VILI model. Regional image-based biomechanical analysis was used to determine end-expiratory aeration, tidal recruitment, and volumetric strain for both early and late stages. Clustering analysis was performed using principal component analysis and K-Means algorithms. We identified three different clusters of lung tissue: Stable, Recruitable Unstable, and Non-Recruitable Unstable. End-expiratory aeration, tidal recruitment, and volumetric strain were significantly different between clusters at early stage. At late stage, we found a step loss of end-expiratory aeration among clusters, lowest in Stable, followed by Unstable Recruitable, and highest in the Unstable Non-Recruitable cluster. Volumetric strain remaining unchanged in the Stable cluster, with slight increases in the Recruitable cluster, and strong reduction in the Unstable Non-Recruitable cluster. CONCLUSIONS: VILI is a regional and dynamic phenomenon. Using unbiased machine-learning techniques we can identify the coexistence of three functional lung tissue compartments with different spatiotemporal regional biomechanical behavior.

Synthetic Attenuation Correction Maps for SPECT Imaging Using Deep Learning: A Study on Myocardial Perfusion Imaging.

(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used 99mTc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.

Development of a deep learning network for Alzheimer's disease classification with evaluation of imaging modality and longitudinal data.

Objective. Neuroimaging uncovers important information about disease in the brain. Yet in Alzheimer's disease (AD), there remains a clear clinical need for reliable tools to extract diagnoses from neuroimages. Significant work has been done to develop deep learning (DL) networks using neuroimaging for AD diagnosis. However, no particular model has emerged as optimal. Due to a lack of direct comparisons and evaluations on independent data, there is no consensus on which modality is best for diagnostic models or whether longitudinal information enhances performance. The purpose of this work was (1) to develop a generalizable DL model to distinguish neuroimaging scans of AD patients from controls and (2) to evaluate the influence of imaging modality and longitudinal data on performance.Approach. We trained a 2-class convolutional neural network (CNN) with and without a cascaded recurrent neural network (RNN). We used datasets of 772 (NAD = 364,Ncontrol= 408) 3D18F-FDG PET scans and 780 (NAD = 280,Ncontrol= 500) T1-weighted volumetric-3D MR images (containing 131 and 144 patients with multiple timepoints) from the Alzheimer's Disease Neuroimaging Initiative, plus an independent set of 104 (NAD = 63,NNC = 41)18F-FDG PET scans (one per patient) for validation.Main Results. ROC analysis showed that PET-trained models outperformed MRI-trained, achieving maximum AUC with the CNN + RNN model of 0.93 ± 0.08, with accuracy 82.5 ± 8.9%. Adding longitudinal information offered significant improvement to performance on18F-FDG PET, but not on T1-MRI. CNN model validation with an independent18F-FDG PET dataset achieved AUC of 0.99. Layer-wise relevance propagation heatmaps added CNN interpretability.Significance. The development of a high-performing tool for AD diagnosis, with the direct evaluation of key influences, reveals the advantage of using18F-FDG PET and longitudinal data over MRI and single timepoint analysis. This has significant implications for the potential of neuroimaging for future research on AD diagnosis and clinical management of suspected AD patients.

Image intensity histograms as imaging biomarkers: application to immune-related colitis.

Purpose.To investigate image intensity histograms as a potential source of useful imaging biomarkers in both a clinical example of detecting immune-related colitis (irColitis) in18F-FDG PET/CT images of immunotherapy patients and an idealized case of classifying digital reference objects (DRO).Methods.Retrospective analysis of bowel18F-FDG uptake in N = 40 patients receiving immune checkpoint inhibitors was conducted. A CNN trained to segment the bowel was used to generate the histogram of bowel18F-FDG uptake, and percentiles of the histogram were considered as potential metrics for detecting inflammation associated with irColitis. A model of the colon was also considered using cylindrical DRO. Classification of DRO with different intensity distributions was undertaken under varying geometry and noise settings.Results.The most predictive biomarker of irColitis was the 95th percentile of the bowel SUV histogram (SUV95%). Patients later diagnosed with irColitis had a significantly higher increase in SUV95%from baseline to first on-treatment PET than patients who did not experience irColitis (p = 0.02). An increase in SUV95%> + 40% separated pre-irColitis change from normal variability with a sensitivity of 75% and specificity of 88%. Furthermore, histogram percentiles were ideal metrics for classifying 'hot center' and 'cold center' DRO, and were robust to varying DRO geometry and noise, and to the presence of spoiler volumes unrelated to the detection task.Conclusions.The 95th percentile of the bowel SUV histogram was the optimal metric for detecting irColitis on18F-FDG PET/CT. Image intensity histograms are a promising source of imaging biomarkers for clinical tasks.

Improved PET quantification and harmonization by adaptive denoising.

PURPOSE: Quantification in positron emission tomography (PET) is subject to bias due to physical and technical limitations. The goal of quantitative harmonization is to achieve comparable measurements between different scanners, thus enabling multicenter clinical trials. Clinical guidelines, such as those from the European Association of Nuclear Medicine (EANM), recommend harmonizing PET reconstructions to bring contrast recovery coefficients (CRCs) within specifications. However, these harmonized reconstructions can show quantitative biases. In this work we improve harmonization by using a novel adaptive filtering scheme. Our goal was to obtain low quantification bias and high peak signal to noise ratio (PSNR) values at the same time. METHODS: a novel three-stage adaptive denoising filter was implemented. Filter parameters were optimized to achieve both high PSNR in a digital brain phantom and low quantitative bias of maximum CRC values (CRCmax) obtained from a National Electrical Manufacturers Association (NEMA) PET image quality phantom. The NEMA phantom was scanned on several PET/CT scanners and reconstructed without postfilters. The optimal filter settings found for a training dataset were then applied to testing reconstructions from other scanners. Harmonization limits were defined using the 95% confidence intervals across reconstructions. RESULTS: Average CRCmax values close to unity (± 5%) were achieved for spheres with diameter equal or greater than 13 mm for the training dataset. PSNR values were comparable to other state-of-the-art filter results. Using the same optimal filter settings for the testing datasets, similar quantitative results were found. Lesion conspicuity was improved on clinical scans when compared with EANM reconstructions, with no visible artifacts. CONCLUSIONS: Our three-stage adaptive filter achieved state-of-the-art quantitative performance for PET imaging. Harmonization tolerances with lower bias and variance than EANM guidelines were achieved for a variety of scanner models. CRCmax values were close to unity and the quantification variability was reduced when compared with standard reconstructions.

Impact of scanner harmonization on PET-based treatment response assessment in metastatic melanoma.

Patients with metastatic melanoma often receive 18F-FDG PET/CT scans on different scanners throughout their monitoring period. In this study, we quantified the impact of scanner harmonization on longitudinal changes in PET standardized uptake values using various harmonization and normalization methods, including an anthropomorphic PET phantom. Twenty metastatic melanoma patients received at least two FDG PET/CT scans, each on two different scanners with an average of 4 months (range: 2-8) between. Scans from a General Electric (GE) Discovery 710 PET CT-1 were harmonized to the GE Discovery VCT using image reconstruction settings matching recovery coefficients in an anthropomorphic phantom with bone equivalent inserts and wall-less synthetic lesions. In patient images, SUVmax was measured for each melanoma lesion and time-point. Lesions were classified as progressing, stable, or responding based on pre-defined threshold of ±30% change in SUVmax. For comparison, harmonization was also performed using simpler methods, including harmonization using a NEMA phantom, post-reconstruction filtering, reference region normalization of SUVmax, and use of SUVpeak instead of SUVmax. In the 20 patients, 90 lesions across two time-points were available for treatment response assessment. Treatment response classification changed in 47% (42/90) of cases after harmonization with anthropomorphic phantom. Before harmonization, 37% (33/90) of the lesions were classified as stable (changing less than 30% between two time-points), while the fraction of stable lesions increased to 58% (52/90) after harmonization. Harmonization with the NEMA phantom agreed with harmonization with the anthropomorphic phantom in 91% (82/90) of cases. Post-reconstruction filtering agreed with anthropomorphic phantom-based harmonization in 83% (75/90) cases. The utilization of reference regions for normalization or SUVpeak was unable to correct for changes as identified by the anthropomorphic phantom-based harmonization. Overall, PET scanner harmonization has a major impact on individual lesion treatment response classification in metastatic melanoma patients. Harmonization using the NEMA phantom yielded similar results to harmonization using anthropomorphic phantom, while the only acceptable post-reconstruction technique was post-reconstruction filtering. Phantom-based harmonization is therefore strongly recommended when comparing lesion uptake across time-points when the images have been acquired on different PET scanners.

Protocols for Harmonized Quantification and Noise Reduction in Low-Dose Oncologic 18F-FDG PET/CT Imaging.

Oncologic 18F-FDG PET/CT acquisition and reconstruction protocols need to be optimized for both quantitative and detection tasks. To date, most studies have focused on either quantification or noise, leading to quantitative harmonization guidelines or appropriate noise levels. We developed and evaluated protocols that provide harmonized quantitation with optimal amounts of noise as a function of acquisition parameters and body mass. Methods: Multiple image acquisitions (n = 17) of the International Electrotechnical Commission/National Electrical Manufacturers Association PET image-quality phantom were performed with variable counting statistics. Phantom images were reconstructed with 3-dimensional ordered-subset expectation maximization (OSEM3D) and point-spread function (PSF) for harmonized quantification of the contrast recovery coefficient of the maximum pixel value (CRC max ). The lowest counting statistics that resulted in compliance with European Association of Nuclear Medicine recommendations for CRC max and CRC max variability were used as optimization metrics. Image noise in the liver of 48 typical oncologic 18F-FDG PET/CT studies was analyzed with OSEM3D and PSF harmonized reconstructions. We also evaluated 164 additional 18F-FDG PET/CT reconstructed list-mode images to derive analytic expressions that predict image quality and noise variability. Phantom-to-subject translational analysis was used to derive optimized acquisition and reconstruction protocols. Results: For harmonized quantitation levels, PSF reconstructions yielded decreased noise and lower CRC max variability than regular OSEM3D reconstructions, suggesting they could enable a decreased activity regimen for matched performance. Conclusion: PSF reconstruction with a 7-mm postprocessing filter can provide harmonized quantification performance and acceptable image noise levels with injected activity, duration, and mass settings using a 260 MBq⋅s/kg acquisition parameter at scan time. Similarly, OSEM3D with a 5-mm postprocessing filter can provide similar performance with 401 MBq⋅s/kg.

Optimization of oncological ¹8F-FDG PET/CT imaging based on a multiparameter analysis.

PURPOSE: This paper describes a method to achieve consistent clinical image quality in (18)F-FDG scans accounting for patient habitus, dose regimen, image acquisition, and processing techniques. METHODS: Oncological PET/CT scan data for 58 subjects were evaluated retrospectively to derive analytical curves that predict image quality. Patient noise equivalent count rate and coefficient of variation (CV) were used as metrics in their analysis. Optimized acquisition protocols were identified and prospectively applied to 179 subjects. RESULTS: The adoption of different schemes for three body mass ranges (<60 kg, 60-90 kg, >90 kg) allows improved image quality with both point spread function and ordered-subsets expectation maximization-3D reconstruction methods. The application of this methodology showed that CV improved significantly (p < 0.0001) in clinical practice. CONCLUSIONS: Consistent oncological PET/CT image quality on a high-performance scanner was achieved from an analysis of the relations existing between dose regimen, patient habitus, acquisition, and processing techniques. The proposed methodology may be used by PET/CT centers to develop protocols to standardize PET/CT imaging procedures and achieve better patient management and cost-effective operations.

Relación entre los patrones de viabilidad, flujo miocárdico y la anatomía coronaria mediante tomografía por emisión de positrones integrada con tomografía multicorte / Relationship between Myocardial Viability, Myocardial Flow and Coronary Anatomy by Positron Emission Tomography Integrated with Multislice Computed Tomography

Introducción La relación entre la viabilidad, el flujo miocárdico y el grado de estenosis epicárdica en pacientes con enfermedad coronaria y disfunción ventricular izquierda está poco investigada. Objetivo Determinar si los patrones de viabilidad por tomografía por emisión de positrones (PET) y el flujo miocárdico en reposo se relacionan con el grado de estenosis epicárdica. Material y métodos Se evaluó la viabilidad en 27 pacientes mediante el análisis combinado de la perfusión con 13N-amonio (13NH3) y el metabolismo con 18F-fluoro-2-desoxiglucosa (FDG) para identificar cuatro patrones PET: match (hipocaptación concordante de ambos radiotrazadores), mismatch (hipoperfusión con captación preservada de FDG), mismatch inverso (perfusión preservada e hipocaptación de FDG) y perfusión/metabolismo conservados. El flujo absoluto se calculó mediante un modelo bicompartimental. Las estenosis se clasificaron en leves ( 50%), graves (> 70%) y críticas (= 90%). Resultados De 459 segmentos resultaron match el 33%, mismatch el 12%, mismatch inverso el 11% y conservado el 44%. El flujo para mismatch, mismatch inverso y conservado fue mayor que para los segmentos con match (p < 0,01). Quince lesiones fueron leves, 7 moderadas, 20 graves y 39 críticas. No hubo correlación entre el grado de estenosis y los patrones de viabilidad (R < 0,2; p = ns) ni con los valores de flujo (R = 0,12). El análisis por territorio vascular no mostró correlación con el grado de estenosis (p = ns). Conclusiones No hubo correlación entre los patrones PET, el grado de estenosis epicárdica y el flujo mio-cárdico, lo que sugiere que la anatomía coronaria no puede discriminar miocardio viable del necrótico ni predecir el estado del flujo miocárdico en pacientes con disfunción ventricular izquierda.

Background The relationship between myocardial viability, myocardial flow and the degree of epicardial coronary stenosis in patients with coronary artery disease and left ventricular dysfunction is unclear. Objective The purpose of this study is to determine whether positron emission tomography (PET) viability and myocardial flow at rest correlate with the degree of epicardial coronary stenosis. Methods Myocardial viability was evaluated in 27 patients by the combined analysis of 13N-Ammonia (13NH3) perfusion and 18F-fluoro-2-deoxyglucose (FDG) metabolism to identify four PET patterns: match (concordant reduced uptake of both radiotracers), mismatch (hypoperfusion with preserved FDG uptake), reverse mismatch (preserved perfusion and reduced FDG uptake) and preserved uptake of both radiotracers. Myocardial blood flow was calculated using a two-compartment model. Coronary artery stenosis was classified as mild (50%), severe (>70%) and critical (= 90%). Results From 459 analyzed segments, 33% were match, 12% mismatch, 11% reverse-mismatch and 44% preserved. Mismatch, reverse-mismatch and preserved patterns exhibited higher flows than the match pattern (p < 0.01). Fifteen coronary lesions were mild, 7 moderate, 20 severe and 39 critical. There was no correlation between the degree of coronary stenosis and viability patterns (R< 0.2, p=NS) or blood flow values (R=0.12). Analysis by vascular territory did not correlate with the degree of coronary stenosis (p=NS). Conclusions Lack of correlation between PET viability patterns, degree of epicardial stenosis and myocardial blood flow suggest that coronary anatomy can neither differentiate viable from necrotic myocardium nor predict the functional status of myocardial flow in patients with left ventricular dysfunction.