Minimally Interactive Segmentation of Soft-Tissue Tumors on CT and MRI using Deep Learning

TL;DR

This paper introduces a minimally interactive deep learning method for segmenting soft-tissue tumors on CT and MRI, requiring only six user clicks, achieving high accuracy and robust generalization across multiple tumor types and imaging modalities.

Contribution

The study presents a novel minimally interactive segmentation approach that uses six user clicks and a CNN, demonstrating high accuracy and strong generalization on diverse datasets.

Findings

Achieved DSC of 0.85 on training data for CT

Achieved DSC of 0.84 on training data for MRI

Maintained high DSC on unseen tumor types and modalities

Abstract

Segmentations are crucial in medical imaging to obtain morphological, volumetric, and radiomics biomarkers. Manual segmentation is accurate but not feasible in the radiologist's clinical workflow, while automatic segmentation generally obtains sub-par performance. We therefore developed a minimally interactive deep learning-based segmentation method for soft-tissue tumors (STTs) on CT and MRI. The method requires the user to click six points near the tumor's extreme boundaries. These six points are transformed into a distance map and serve, with the image, as input for a Convolutional Neural Network. For training and validation, a multicenter dataset containing 514 patients and nine STT types in seven anatomical locations was used, resulting in a Dice Similarity Coefficient (DSC) of 0.85$\pm$0.11 (mean $\pm$ standard deviation (SD)) for CT and 0.84$\pm$0.12 for T1-weighted MRI, when compared to manual segmentations made by expert radiologists. Next, the method was externally validated on a dataset including five unseen STT phenotypes in extremities, achieving 0.81$\pm$0.08 for CT, 0.84$\pm$0.09 for T1-weighted MRI, and 0.88\pm0.08 for previously unseen T2-weighted fat-saturated (FS) MRI. In conclusion, our minimally interactive segmentation method effectively segments different types of STTs on CT and MRI, with robust generalization to previously unseen phenotypes and imaging modalities.