Article Figures & Data
Figures
- FIGURE 1.
Schematic representation of GAN producing synthetic images with generator and discriminator neural networks.
- FIGURE 2.
Schematic representation of transformer producing text outputs through encoder/decoder architecture. Each encoder in transformer comprises 2 neural networks: recurrent neural network self-attention network followed by feed-forward network. Each decoder comprises 3 neural networks: recurrent neural network self-attention network, feed-forward network, and then casual attention decoder.
- FIGURE 3.
Schematic representation of learning, encoding, and decoding pathway for ChatGPT. LLM = large language model.
- FIGURE 4.
Schematic representation of diffusion model associated with text-to-image genAI.
- FIGURE 5.
Comparison of variability of quality criteria for text-to-image genAI using DALL-E 3 (top left), Firefly 2 (top right), Stable Diffusion 2.1 (bottom left), and Midjourney 5.2 (bottom right).
- FIGURE 6.
Five serial images from DALL-E 3 in response to prompt for images of typical nuclear medicine technologist. Diversity and inclusivity of medical imaging professions are not represented in these images.
- FIGURE 7.
DALL-E 3 image application in nuclear medicine student education. On left is visual stimuli that could be used for class discussion and debate or to set scene for hands-on simulation practicals. On right is visual stimuli that could be used in class or online to generate discussion and debate around ethical dilemmas.
