Improve Cross-Modality Segmentation by Treating T1-Weighted MRI Images as Inverted CT Scans

Abstract

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.

6 pages, 3 figures, updated data and methodology, conclusion unchanged

References in corpus (12)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• TotalSegmentator: robust segmentation of 104 anatomical structures in CT images
• Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
• Metrics reloaded: Recommendations for image analysis validation
• Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
• MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images
• Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
• Crossbar-Net: A Novel Convolutional Network for Kidney Tumor Segmentation in CT Images
• TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI
• Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation
• MRSegmentator: Multi-Modality Segmentation of 40 Classes in MRI and CT
• VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank