Volumetric Attention for 3D Medical Image Segmentation and Detection

Abstract

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.

arXiv commentAccepted by MICCAI 2019

References in corpus (2)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields

Cited by in corpus (8)

• Reinventing 2D Convolutions for 3D Images
• PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images
• Asymmetric 3D Context Fusion for Universal Lesion Detection
• AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes
• Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images
• RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training
• BeSt-LeS: Benchmarking Stroke Lesion Segmentation using Deep Supervision
• The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection