AI-PET attenuation… Whole Body PET Attenuation Correction Map Synthesizing using 3D Deep Networks 1 Jan 202413 Feb 2024 Task: Whole body attenuation map generation using 3D U-Net generative adversarial networks (GANs) Description: The model is initially trained as a 3D U-Net to learn the mapping from non attenuation…
AI-cardiac… TAI-GAN: Temporally and Anatomically Informed GAN for early-to-late frame conversion in dynamic cardiac PET motion correction 1 Jan 20249 May 2024 Task: To synthesize a reference late cardiac Rb-82 PET image frame from a set of respective early PET image frames for improved inter-frame registration, motion correction and myocardial blood flow…
AI-NeuroImaging… AI-imputed tau-PET: Synthesizing PET images of tau pathology from cross-modal neuroimaging using deep learning 1 Jan 202423 Feb 2024 Task: To impute tau-PET images from more widely available cross-modality imaging inputs Description: The AI-imputed tau-PET model is a 3D Dense-U-Net Convolutional Neural Network (CNN) that imputes synthetic tau-PET images…
AI-PET synthesis… CycleGAN-QSDL: Quasi-supervised deep learning for super-resolution PET 1 Jan 202419 Feb 2024 Task: Generate synthetic high-resolution PET images from low-resolution PET images Description: QSDL is a quasi-supervised deep learning method, which is a new type of weakly-supervised learning methods, to recover high-resolution…
AI-classification… CGAN-based 18F-Florbetaben PET Data Augmentation for Enhanced Classification of Amyloid-beta distributions 1 Jan 202424 Feb 2024 Task 1: Improve Data Augmentation (DA) of a limited training set of 18F-Florbetaben (18F-FBB) PET images by synthesizing additional realistic 18F-FBB PET images using a Conditional Generative Adversarial Network (CGAN)…
AI-PET synthesis… SC-GAN: 3D self-attention conditional GAN with spectral normalization for multi-modal neuroimaging synthesis 1 Jan 202413 Feb 2024 Task: Multimodal (PET & multi-modal MR) 3D medical image synthesis Description: A novel 3D conditional generative adversarial network (GAN) designed and optimized for the application of multimodal 3D neuroimaging synthesis.…