Segmentation of Liver Lesions with Reduced Complexity Deep Models
This work addresses the problem of high computational cost in medical image segmentation for clinicians, but it is incremental as it builds on existing U-Net methods with efficiency improvements.
The authors tackled liver lesion segmentation from CT images by proposing a computationally efficient architecture that reduces model complexity, achieving competitive results on the LiTS Challenge dataset while cutting learnable parameters by a factor of 13.8 compared to U-Net.
We propose a computationally efficient architecture that learns to segment lesions from CT images of the liver. The proposed architecture uses bilinear interpolation with sub-pixel convolution at the last layer to upscale the course feature in bottle neck architecture. Since bilinear interpolation and sub-pixel convolution do not have any learnable parameter, our overall model is faster and occupies less memory footprint than the traditional U-net. We evaluate our proposed architecture on the highly competitive dataset of 2017 Liver Tumor Segmentation (LiTS) Challenge. Our method achieves competitive results while reducing the number of learnable parameters roughly by a factor of 13.8 compared to the original UNet model.