Skip to main content
Fig. 1 | European Journal of Hybrid Imaging

Fig. 1

From: Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

Fig. 1

Examples of (a) supervised and (b) unsupervised deep learning approaches employed in molecular imaging for the task of MRI-based synthetic CT generation (a) and PET denoising (b). In supervised learning, the model is trained using a labeled dataset, providing answer keys based on which the accuracy of the model can be evaluated within the training process. In contrast, in unsupervised learning, the algorithm tends to make sense of unlabeled data relying on the extraction of dominant features and patterns on its own

Back to article page