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

TL;DR

This paper introduces a simple image inversion technique that enhances CT segmentation models' performance on MRI data, enabling effective cross-modality segmentation without complex transfer models.

Contribution

The study demonstrates that inverting T1-weighted MRI images improves CT-based segmentation models' accuracy on MRI, offering a quick, resource-efficient transfer method.

Findings

Inversion improves MRI segmentation accuracy.

CT models can be adapted to MRI with simple preprocessing.

Effective for renal carcinoma segmentation.

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.