An Ensemble of 2.5D ResUnet Based Models for Segmentation for Kidney and Masses
This addresses medical image segmentation for kidney-related conditions, presenting an incremental improvement with specific efficiency gains.
The authors tackled automatic segmentation of kidney, kidney tumor, and kidney cyst on CT scans, achieving dice values of 0.954, 0.792, and 0.691 respectively on a test set, with an average inference time of 20.65 seconds per scan.
The automatic segmentation of kidney, kidney tumor and kidney cyst on Computed Tomography (CT) scans is a challenging task due to the indistinct lesion boundaries and fuzzy texture. Considering the large range and unbalanced distribution of CT scans' thickness, 2.5D ResUnet are adopted to build an efficient coarse-to-fine semantic segmentation framework in this work. A set of 489 CT scans are used for training and validation, and an independent never-before-used CT scans for testing. Finally, we demonstrate the effectiveness of our proposed method. The dice values on test set are 0.954, 0.792, 0.691, the surface dice values are 0.897, 0.591, 0.541 for kidney, tumor and cyst, respectively. The average inference time of each CT scan is 20.65s and the max GPU memory is 3525MB. The results suggest that a better trade-off between model performance and efficiency.