Volumetric Attention for 3D Medical Image Segmentation and Detection
This addresses the problem of limited training data in medical imaging by enabling better 3D context use, though it is incremental as it builds on existing 2D methods.
The paper tackled 3D medical image segmentation and detection by proposing a volumetric attention module, which achieved state-of-the-art performance with a 3.9-point improvement on the LiTS Challenge and a 69.1 sensitivity on the DeepLesion dataset, outperforming previous best results by 6.6 points.
A volumetric attention(VA) module for 3D medical image segmentation and detection is proposed. VA attention is inspired by recent advances in video processing, enables 2.5D networks to leverage context information along the z direction, and allows the use of pretrained 2D detection models when training data is limited, as is often the case for medical applications. Its integration in the Mask R-CNN is shown to enable state-of-the-art performance on the Liver Tumor Segmentation (LiTS) Challenge, outperforming the previous challenge winner by 3.9 points and achieving top performance on the LiTS leader board at the time of paper submission. Detection experiments on the DeepLesion dataset also show that the addition of VA to existing object detectors enables a 69.1 sensitivity at 0.5 false positive per image, outperforming the best published results by 6.6 points.