Improve Cross-Modality Segmentation by Treating T1-Weighted MRI Images as Inverted CT Scans
This provides a quick, resource-efficient method for medical imaging researchers to apply existing CT models to MRI data, though it is incremental compared to complex deep modality-transfer approaches.
The study tackled the problem of transferring CT segmentation models to MRI data by using a simple image inversion technique, achieving significant improvement in segmentation quality for both multi-class and renal carcinoma models on T1-weighted MRI scans.
Computed tomography (CT) segmentation models often contain classes that are not currently supported by magnetic resonance imaging (MRI) segmentation models. In this study, we show that a simple image inversion technique can significantly improve the segmentation quality of CT segmentation models on MRI data. We demonstrate the feasibility for both a general multi-class and a specific renal carcinoma model for segmenting T1-weighted MRI images. Using this technique, we were able to localize and segment clear cell renal cell carcinoma in T1-weighted MRI scans, using a model that was trained on only CT data. Image inversion is straightforward to implement and does not require dedicated graphics processing units, thus providing a quick alternative to complex deep modality-transfer models. Our results demonstrate that existing CT models, including pathology models, might be transferable to the MRI domain with reasonable effort.