Can I read Metrics to Quantify Global Consistency in Synthetic Medical Images on EtoBox?

Metrics to Quantify Global Consistency in Synthetic Medical Images by Scholz, Daniel; Wiestler, Benedikt; Rueckert, Daniel; Menten, Martin J. is a scholarly article available to read on EtoBox.

What is Metrics to Quantify Global Consistency in Synthetic Medical Images about?

Image synthesis is increasingly being adopted in medical image processing, for example for data augmentation or inter-modality image translation. In these critical applications, the generated images must fulfill a high standard of biological correctness. A particular requirement for these images is global consistency, i.e an image being overall coherent and structured so that all parts of the image fit together in a realistic and meaningful way. Yet, established image quality metrics do not explicitly quantify this property of synthetic images. In this work, we introduce two metrics that can measure the global consistency of synthetic images on a per-image basis. To measure the global consistency, we presume that a realistic image exhibits consistent properties, e.g., a person's body fat in a whole-body MRI, throughout the depicted object or scene. Hence, we quantify global consistency by predicting and comparing explicit attributes of images on patches using supervised trained neural networks. Next, we adapt this strategy to an unlabeled setting by measuring the similarity of implicit image features predicted by a self-supervised trained network. Our results demonstrate that predi

Author

Scholz, Daniel; Wiestler, Benedikt; Rueckert, Daniel; Menten, Martin J.

Published

2023

Language

EN