XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation

Abstract

This paper proposes a novel framework for lung segmentation in chest X-rays. It consists of two key contributions, a criss-cross attention based segmentation network and radiorealistic chest X-ray image synthesis (i.e. a synthesized radiograph that appears anatomically realistic) for data augmentation. The criss-cross attention modules capture rich global contextual information in both horizontal and vertical directions for all the pixels thus facilitating accurate lung segmentation. To reduce the manual annotation burden and to train a robust lung segmentor that can be adapted to pathological lungs with hazy lung boundaries, an image-to-image translation module is employed to synthesize radiorealistic abnormal CXRs from the source of normal ones for data augmentation. The lung masks of synthetic abnormal CXRs are propagated from the segmentation results of their normal counterparts, and then serve as pseudo masks for robust segmentor training. In addition, we annotate 100 CXRs with lung masks on a more challenging NIH Chest X-ray dataset containing both posterioranterior and anteroposterior views for evaluation. Extensive experiments validate the robustness and effectiveness of the proposed framework. The code and data can be found from https://github.com/rsummers11/CADLab/tree/master/Lung_Segmentation_XLSor .

arXiv commentAccepted by MIDL 2019

References in corpus (5)

• CCNet: Criss-Cross Attention for Semantic Segmentation
• Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
• SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays
• Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST
• Fine-grained lesion annotation in CT images with knowledge mined from radiology reports

Cited by in corpus (13)

• Deep Learning for Chest X-ray Analysis: A Survey
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Transformers in Healthcare: A Survey
• Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
• Lung Segmentation from Chest X-rays using Variational Data Imputation
• Unsupervised-learning-based method for chest MRI-CT transformation using structure constrained unsupervised generative attention networks
• E${}^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans
• Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
• TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
• Lung Segmentation in Chest X-rays with Res-CR-Net
• CXR-Net: An Artificial Intelligence Pipeline for Quick Covid-19 Screening of Chest X-Rays
• Employing similarity to highlight differences: On the impact of anatomical assumptions in chest X-ray registration methods
• Generative Residual Attention Network for Disease Detection