Leveraging Clinical Characteristics for Improved Deep Learning-Based Kidney Tumor Segmentation on CT

TL;DR

This study demonstrates that incorporating clinical characteristics into deep learning models significantly enhances the accuracy of kidney tumor segmentation on CT scans.

Contribution

The paper introduces a cognizant sampling strategy using clinical data to improve deep learning-based kidney tumor segmentation performance.

Findings

Cognizant sampling improved Dice scores for kidney and tumor segmentation.

The approach significantly outperformed baseline models without clinical data.

Statistical tests confirmed the significance of the improvements.

Abstract

This paper assesses whether using clinical characteristics in addition to imaging can improve automated segmentation of kidney cancer on contrast-enhanced computed tomography (CT). A total of 300 kidney cancer patients with contrast-enhanced CT scans and clinical characteristics were included. A baseline segmentation of the kidney cancer was performed using a 3D U-Net. Input to the U-Net were the contrast-enhanced CT images, output were segmentations of kidney, kidney tumors, and kidney cysts. A cognizant sampling strategy was used to leverage clinical characteristics for improved segmentation. To this end, a Least Absolute Shrinkage and Selection Operator (LASSO) was used. Segmentations were evaluated using Dice and Surface Dice. Improvement in segmentation was assessed using Wilcoxon signed rank test. The baseline 3D U-Net showed a segmentation performance of 0.90 for kidney and kidney masses, i.e., kidney, tumor, and cyst, 0.29 for kidney masses, and 0.28 for kidney tumor, while the 3D U-Net trained with cognizant sampling enhanced the segmentation performance and reached Dice scores of 0.90, 0.39, and 0.38 respectively. To conclude, the cognizant sampling strategy leveraging the clinical characteristics significantly improved kidney cancer segmentation.