Structurally aware bidirectional unpaired image to image translation between CT and MR
This work addresses the problem of expensive and time-consuming medical imaging acquisition for surgical planning by enabling bidirectional translation between CT and MR, though it appears incremental as it builds on existing GAN techniques for unpaired translation.
The paper tackles the challenge of unpaired image-to-image translation from CT to MR, which is difficult due to adding tissue information, by implementing two GAN variations that exploit cycling consistency and structural similarity on a pelvis dataset, resulting in generated images that appear realistic and perform well on metrics, with radiologist verification indicating usability for medical purposes.
Magnetic Resonance (MR) Imaging and Computed Tomography (CT) are the primary diagnostic imaging modalities quite frequently used for surgical planning and analysis. A general problem with medical imaging is that the acquisition process is quite expensive and time-consuming. Deep learning techniques like generative adversarial networks (GANs) can help us to leverage the possibility of an image to image translation between multiple imaging modalities, which in turn helps in saving time and cost. These techniques will help to conduct surgical planning under CT with the feedback of MRI information. While previous studies have shown paired and unpaired image synthesis from MR to CT, image synthesis from CT to MR still remains a challenge, since it involves the addition of extra tissue information. In this manuscript, we have implemented two different variations of Generative Adversarial Networks exploiting the cycling consistency and structural similarity between both CT and MR image modalities on a pelvis dataset, thus facilitating a bidirectional exchange of content and style between these image modalities. The proposed GANs translate the input medical images by different mechanisms, and hence generated images not only appears realistic but also performs well across various comparison metrics, and these images have also been cross verified with a radiologist. The radiologist verification has shown that slight variations in generated MR and CT images may not be exactly the same as their true counterpart but it can be used for medical purposes.