Generative Adversarial Network-Enhanced Ultra-Low-Dose [18F]-PI-2620 τ PET/MRI in Aging and Neurodegenerative Populations.

BACKGROUND AND PURPOSE: With the utility of hybrid τ PET/MR imaging in the screening, diagnosis, and follow-up of individuals with neurodegenerative diseases, we investigated whether deep learning techniques can be used in enhancing ultra-low-dose [18F]-PI-2620 τ PET/MR images to produce diagnostic-quality images. MATERIALS AND METHODS: Forty-four healthy aging participants and patients with neurodegenerative diseases were recruited for this study, and [18F]-PI-2620 τ PET/MR data were simultaneously acquired. A generative adversarial network was trained to enhance ultra-low-dose τ images, which were reconstructed from a random sampling of 1/20 (approximately 5% of original count level) of the original full-dose data. MR images were also used as additional input channels. Region-based analyses as well as a reader study were conducted to assess the image quality of the enhanced images compared with their full-dose counterparts. RESULTS: The enhanced ultra-low-dose τ images showed apparent noise reduction compared with the ultra-low-dose images. The regional standard uptake value ratios showed that while, in general, there is an underestimation for both image types, especially in regions with higher uptake, when focusing on the healthy-but-amyloid-positive population (with relatively lower τ uptake), this bias was reduced in the enhanced ultra-low-dose images. The radiotracer uptake patterns in the enhanced images were read accurately compared with their full-dose counterparts. CONCLUSIONS: The clinical readings of deep learning-enhanced ultra-low-dose τ PET images were consistent with those performed with full-dose imaging, suggesting the possibility of reducing the dose and enabling more frequent examinations for dementia monitoring.

Promoting evidence-based practices for breast cancer care through web-based collaborative learning.

The Knowledge Summaries for Comprehensive Breast Cancer Control (KSBCs) are a series of 14 publications aligned with World Health Organization guidance on evidence-based breast cancer control and accepted frameworks for action. To study utilization of the KSBCs in the development of locally relevant breast cancer control policies and programs in limited resource settings, the National Cancer Institute Center for Global Health, the University of Washington and the Fred Hutchinson Cancer Research Center developed the Project ECHO® for KSBCs (KSBC ECHO). Project ECHO is an online model which employs case-based learning, while promoting multi-directional learning and network-building. The program was evaluated using a pre-post study design to assess if this online collaborative learning platform can be an effective model for dissemination and utilization of the KSBCs to inform breast cancer control programs and policy advocacy in limited resource settings. A total of 28 KSBC ECHO participants (57%) responded to the baseline and endpoint program evaluation surveys. Across all 28 respondents, analysis of the data indicates that knowledge increase was statistically significant overall: average knowledge gain was 0.77, 95% CI [0.44 - 1.08] and p value < 0.0001. A majority of responding team leads reported that the core ECHO components (case/didactic presentations, discussion) contributed to a great extent to strengthening their project proposal/goals. Program evaluation survey responses indicate that utilization of this online platform provided an opportunity for individual knowledge gain, multi-directional information exchange, network-building, and strengthening of the proposed breast cancer control projects based in limited resource settings.