SeCo-INR: Semantically Conditioned Implicit Neural Representations for Improved Medical Image Super-Resolution

TL;DR

SeCo-INR introduces a novel method that leverages semantic segmentation priors to condition implicit neural representations, significantly improving the accuracy and realism of medical image super-resolution.

Contribution

The paper presents a new framework that conditions INRs on local semantic priors, enhancing super-resolution performance in medical imaging.

Findings

Higher quantitative scores than state-of-the-art methods

More realistic super-resolution outputs

Effective use of semantic priors for model conditioning

Abstract

Implicit Neural Representations (INRs) have recently advanced the field of deep learning due to their ability to learn continuous representations of signals without the need for large training datasets. Although INR methods have been studied for medical image super-resolution, their adaptability to localized priors in medical images has not been extensively explored. Medical images contain rich anatomical divisions that could provide valuable local prior information to enhance the accuracy and robustness of INRs. In this work, we propose a novel framework, referred to as the Semantically Conditioned INR (SeCo-INR), that conditions an INR using local priors from a medical image, enabling accurate model fitting and interpolation capabilities to achieve super-resolution. Our framework learns a continuous representation of the semantic segmentation features of a medical image and utilizes it to derive the optimal INR for each semantic region of the image. We tested our framework using several medical imaging modalities and achieved higher quantitative scores and more realistic super-resolution outputs compared to state-of-the-art methods.