Attention Unet++: A Nested Attention-Aware U-Net for Liver CT Image Segmentation

TLDR

Liver cancer has one of the highest mortality rates among cancers. The study aims to develop an automatic liver segmentation model to aid clinicians, as manual segmentation is time‑consuming and error‑prone. Attention UNet++ is a nested attention‑aware U‑Net featuring a deep supervised encoder‑decoder, redesigned dense skip connections, and attention between nested convolutional blocks to select task‑related features, with deep supervision added to accelerate inference of the pruned network. On the MICCAI 2017 LiTS dataset, Attention UNet++ achieved very competitive liver segmentation performance.

Abstract

Liver cancer is one of the cancers with the highest mortality. In order to help doctors diagnose and treat liver lesion, an automatic liver segmentation model is urgently needed due to manually segmentation is time-consuming and error-prone. In this paper, we propose a nested attention-aware segmentation network, named Attention UNet++. Our proposed method has a deep supervised encoder-decoder architecture and a redesigned dense skip connection. Attention UNet++ introduces attention mechanism between nested convolutional blocks so that the features extracted at different levels can be merged with a task-related selection. Besides, due to the introduction of deep supervision, the prediction speed of the pruned network is accelerated at the cost of modest performance degradation. We evaluated proposed model on MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge Dataset. Attention UNet++ achieved very competitive performance for liver segmentation.