Organ At Risk Segmentation with Multiple Modality
This work addresses the need for more accurate segmentation in clinical settings where doctors use multiple imaging modalities, though it is incremental by building on existing segmentation and GAN techniques.
The paper tackles the problem of organ at risk segmentation in biomedical imaging by leveraging multiple modalities, proposing a GAN-based method to synthesize MR images from CT scans and using instance segmentation to include tumor regions, achieving improved performance on a dataset of 136 nasopharyngeal cancer cases.
With the development of image segmentation in computer vision, biomedical image segmentation have achieved remarkable progress on brain tumor segmentation and Organ At Risk (OAR) segmentation. However, most of the research only uses single modality such as Computed Tomography (CT) scans while in real world scenario doctors often use multiple modalities to get more accurate result. To better leverage different modalities, we have collected a large dataset consists of 136 cases with CT and MR images which diagnosed with nasopharyngeal cancer. In this paper, we propose to use Generative Adversarial Network to perform CT to MR transformation to synthesize MR images instead of aligning two modalities. The synthesized MR can be jointly trained with CT to achieve better performance. In addition, we use instance segmentation model to extend the OAR segmentation task to segment both organs and tumor region. The collected dataset will be made public soon.