← Research

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

Douwe J. Spaanderman (1), Martijn P. A. Starmans (1), Gonnie C. M. van Erp (1), David F. Hanff (1), Judith H. Sluijter (1), Anne-Rose W. Schut (2, 3), Geert J. L. H. van Leenders (4), Cornelis Verhoef (2), Dirk J. Grunhagen (2), Wiro J. Niessen (5), Jacob J. Visser (1), Stefan Klein (1) ((1) Department of Radiology, Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands, (2) Department of Surgical Oncology, Erasmus MC Cancer Institute, Rotterdam, the Netherlands, (3) Department of Medical Oncology, Erasmus MC Cancer Institute, Rotterdam, the Netherlands, (4) Department of Pathology, Erasmus MC Cancer Institute, Rotterdam, the Netherlands, (5) Faculty of Medical Sciences, University of Groningen, Groningen, The Netherlands)

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.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace