Two-Stream UNET Networks for Semantic Segmentation in Medical Images
This work addresses segmentation challenges in medical imaging, offering an incremental improvement for handling imperfect datasets.
The authors tackled the problem of overfitting in medical image segmentation by proposing a two-stream UNET architecture that uses intensity and gradient vector flow as inputs, achieving competitive results with state-of-the-art methods on popular benchmarks.
Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing medical datasets hinder training deeper and larger models because of overfitting. To this end, we propose a novel two-stream UNET architecture for automatic end-to-end medical image segmentation, in which intensity value and gradient vector flow (GVF) are two inputs for each stream, respectively. We demonstrate that two-stream CNNs with more low-level features greatly benefit semantic segmentation for imperfect medical image datasets. Our proposed two-stream networks are trained and evaluated on the popular medical image segmentation benchmarks, and the results are competitive with the state of the art. The code will be released soon.