Abstract
Thin-slice medical image reconstruction is crucial for improving diagnostic accuracy, particularly when high-resolution scans are unavailable or costly to acquire. Traditional reconstruction methods often struggle with maintaining image quality and anatomical accuracy. In this work, we propose a generative adversarial network approach for reconstructing high-quality thin-slice medical images.
Our method leverages the power of generative adversarial networks to produce high-resolution images from limited or noisy data. The framework consists of three key components: (1) a generator network that learns to reconstruct high-quality images, (2) a discriminator network that ensures realistic output, and (3) a specialized loss function that preserves anatomical details and structural integrity.
We evaluate our approach on multiple medical imaging datasets, including brain MRI and chest CT scans. Experimental results demonstrate that our GAN-based method significantly improves reconstruction quality compared to traditional approaches. The method shows excellent performance in preserving fine anatomical details and reducing artifacts commonly found in thin-slice imaging.
The proposed framework represents a significant advancement in medical image reconstruction, providing more accurate results that could improve diagnostic quality and patient outcomes.
BibTeX
@inproceedings{li2017reconstruction,
title={Reconstruction of thin-slice medical images using generative adversarial network},
author={Li, Zeju and Wang, Yuanyuan and Yu, Jinhua},
booktitle={International Workshop on Machine Learning in Medical Imaging (MICCAI-MLMI 2017)},
year={2017},
doi={10.1007/978-3-319-67389-9_38}
}