Tau-PET abnormality as a biomarker for Alzheimer's disease staging and early detection: a topological perspective.

Alzheimer's disease can be detected early through biomarkers such as tau positron emission tomography (PET) imaging, which shows abnormal protein accumulations in the brain. The standardized uptake value ratio (SUVR) is often used to quantify tau-PET imaging, but topological information from multiple brain regions is also linked to tau pathology. Here a new method was developed to investigate the correlations between brain regions using subject-level tau networks. Participants with cognitive normal (74), early mild cognitive impairment (35), late mild cognitive impairment (32), and Alzheimer's disease (40) were included. The abnormality network from each scan was constructed to extract topological features, and 7 functional clusters were further analyzed for connectivity strengths. Results showed that the proposed method performed better than conventional SUVR measures for disease staging and prodromal sign detection. For example, when to differ healthy subjects with and without amyloid deposition, topological biomarker is significant with P < 0.01, SUVR is not with P > 0.05. Functionally significant clusters, i.e. medial temporal lobe, default mode network, and visual-related regions, were identified as critical hubs vulnerable to early disease conversion before mild cognitive impairment. These findings were replicated in an independent data cohort, demonstrating the potential to monitor the early sign and progression of Alzheimer's disease from a topological perspective for individual.

Patient-level thyroid cancer classification using attention multiple instance learning on fused multi-scale ultrasound image features.

For patients with thyroid nodules, the ability to detect and diagnose a malignant nodule is the key to creating an appropriate treatment plan. However, assessments of ultrasound images do not accurately represent malignancy, and often require a biopsy to confirm the diagnosis. Deep learning techniques can classify thyroid nodules from ultrasound images, but current methods depend on manually annotated nodule segmentations. Furthermore, the heterogeneity in the level of magnification across ultrasound images presents a significant obstacle to existing methods. We developed a multi-scale, attention-based multiple-instance learning model which fuses both global and local features of different ultrasound frames to achieve patient-level malignancy classification. Our model demonstrates improved performance with an AUROC of 0.785 (p<0.05) and AUPRC of 0.539, significantly surpassing the baseline model trained on clinical features with an AUROC of 0.667 and AUPRC of 0.444. Improved classification performance better triages the need for biopsy.

Comparison between a dual-time-window protocol and other simplified protocols for dynamic total-body 18F-FDG PET imaging.

PURPOSE: Efforts have been made both to avoid invasive blood sampling and to shorten the scan duration for dynamic positron emission tomography (PET) imaging. A total-body scanner, such as the uEXPLORER PET/CT, can relieve these challenges through the following features: First, the whole-body coverage allows for noninvasive input function from the aortic arteries; second, with a dramatic increase in sensitivity, image quality can still be maintained at a high level even with a shorter scan duration than usual. We implemented a dual-time-window (DTW) protocol for a dynamic total-body 18F-FDG PET scan to obtain multiple kinetic parameters. The DTW protocol was then compared to several other simplified quantification methods for total-body FDG imaging that were proposed for conventional setup. METHODS: The research included 28 patient scans performed on an uEXPLORER PET/CT. By discarding the corresponding data in the middle of the existing full 60-min dynamic scan, the DTW protocol was simulated. Nonlinear fitting was used to estimate the missing data in the interval. The full input function was obtained from 15 subjects using a hybrid approach with a population-based image-derived input function. Quantification was carried out in three areas: the cerebral cortex, muscle, and tumor lesion. Micro- and macro-kinetic parameters for different scan durations were estimated by assuming an irreversible two-tissue compartment model. The visual performance of parametric images and region of interest-based quantification in several parameters were evaluated. Furthermore, simplified quantification methods (DTW, Patlak, fractional uptake ratio [FUR], and standardized uptake value [SUV]) were compared for similarity to the reference net influx rate Ki. RESULTS: Ki and K1 derived from the DTW protocol showed overall good consistency (P < 0.01) with the reference from the 60-min dynamic scan with 10-min early scan and 5-min late scan (Ki correlation: 0.971, 0.990, and 0.990; K1 correlation: 0.820, 0.940, and 0.975 in the cerebral cortex, muscle, and tumor lesion, respectively). Similar correlationss were found for other micro-parameters. The DTW protocol had the lowest bias relative to standard Ki than any of the quantification methods, followed by FUR and Patlak. SUV had the weakest correlation with Ki. The whole-body Ki and K1 images generated by the DTW protocol were consistent with the reference parametric images. CONCLUSIONS: Using the DTW protocol, the dynamic total-body FDG scan time can be reduced to 15 min while obtaining accurate Ki and K1 quantification and acceptable visual performance in parametric images. However, the trade-off between quantification accuracy and protocol implementation feasibility must be considered in practice. We recommend that the DTW protocol be used when the clinical task requires reliable visual assessment or quantifying multiple micro-parameters; FUR with a hybrid input function may be a more feasible approach to quantifying regional metabolic rate with a known lesion position or organs of interest.

Identifying the individual metabolic abnormities from a systemic perspective using whole-body PET imaging.

INTRODUCTION: Distinct physiological states arise from complex interactions among the various organs present in the human body. PET is a non-invasive modality with numerous successful applications in oncology, neurology, and cardiology. However, while PET imaging has been applied extensively in detecting focal lesions or diseases, its potential in detecting systemic abnormalities is seldom explored, mostly because total-body imaging was not possible until recently. METHODS: In this context, the present study proposes a framework capable of constructing an individual metabolic abnormality network using a subject's whole-body 18F-FDG SUV image and a normal control database. The developed framework was evaluated in the patients with lung cancer, the one discharged after suffering from Covid-19 disease, and the one that had gastrointestinal bleeding with the underlying cause unknown. RESULTS: The framework could successfully capture the deviation of these patients from healthy subjects at the level of both system and organ. The strength of the altered network edges revealed the abnormal metabolic connection between organs. The overall deviation of the network nodes was observed to be highly correlated to the organ SUV measures. Therefore, the molecular connectivity of glucose metabolism was characterized at a single subject level. CONCLUSION: The proposed framework represents a significant step toward the use of PET imaging for identifying metabolic dysfunction from a systemic perspective. A better understanding of the underlying biological mechanisms and the physiological interpretation of the interregional connections identified in the present study warrant further research.

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 ß-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 ß-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.

An iterative image-based inter-frame motion compensation method for dynamic brain PET imaging.

As a non-invasive imaging tool, positron emission tomography (PET) plays an important role in brain science and disease research. Dynamic acquisition is one way of brain PET imaging. Its wide application in clinical research has often been hindered by practical challenges, such as patient involuntary movement, which could degrade both image quality and the accuracy of the quantification. This is even more obvious in scans of patients with neurodegeneration or mental disorders. Conventional motion compensation methods were either based on images or raw measured data, were shown to be able to reduce the effect of motion on the image quality. As for a dynamic PET scan, motion compensation can be challenging as tracer kinetics and relatively high noise can be present in dynamic frames. In this work, we propose an image-based inter-frame motion compensation approach specifically designed for dynamic brain PET imaging. Our method has an iterative implementation that only requires reconstructed images, based on which the inter-frame subject movement can be estimated and compensated. The method utilized tracer-specific kinetic modelling and can deal with simple and complex movement patterns. The synthesized phantom study showed that the proposed method can compensate for the simulated motion in scans with18F-FDG,18F-Fallypride and18F-AV45. Fifteen dynamic18F-FDG patient scans with motion artifacts were also processed. The quality of the recovered image was superior to the one of the non-corrected images and the corrected images with other image-based methods. The proposed method enables retrospective image quality control for dynamic brain PET imaging, hence facilitating the applications of dynamic PET in clinics and research.