Lung Structures Enhancement in Chest Radiographs via CT based FCNN Training

10/14/2018
by   Ophir Gozes, et al.
0

The abundance of overlapping anatomical structures appearing in chest radiographs can reduce the performance of lung pathology detection by automated algorithms (CAD) as well as the human reader. In this paper, we present a deep learning based image processing technique for enhancing the contrast of soft lung structures in chest radiographs using Fully Convolutional Neural Networks (FCNN). Two 2D FCNN architectures were trained to accomplish the task: The first performs 2D lung segmentation which is used for normalization of the lung area. The second FCNN is trained to extract lung structures. To create the training images, we employed Simulated X-Ray or Digitally Reconstructed Radiographs (DRR) derived from 516 scans belonging to the LIDC-IDRI dataset. By first segmenting the lungs in the CT domain, we are able to create a dataset of 2D lung masks to be used for training the segmentation FCNN. For training the extraction FCNN, we create DRR images of only voxels belonging to the 3D lung segmentation which we call "Lung X-ray" and use them as target images. Once the lung structures are extracted, the original image can be enhanced by fusing the original input x-ray and the synthesized "Lung X-ray". We show that our enhancement technique is applicable to real x-ray data, and display our results on the recently released NIH Chest X-Ray-14 dataset. We see promising results when training a DenseNet-121 based architecture to work directly on the lung enhanced X-ray images.

READ FULL TEXT

page 5

page 6

page 7

page 8

page 9

page 10

page 11

research
03/20/2020

Bone Structures Extraction and Enhancement in Chest Radiographs via CNN Trained on Synthetic Data

In this paper, we present a deep learning-based image processing techniq...
research
12/09/2022

UNet Based Pipeline for Lung Segmentation from Chest X-Ray Images

Biomedical image segmentation is one of the fastest growing fields which...
research
02/18/2020

Automated Cardiothoracic Ratio Calculation and Cardiomegaly Detection using Deep Learning Approach

We propose an algorithm for calculating the cardiothoracic ratio (CTR) f...
research
03/24/2022

X-ray Dissectography Improves Lung Nodule Detection

Although radiographs are the most frequently used worldwide due to their...
research
03/26/2017

SCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays

Chest X-ray (CXR) is one of the most commonly prescribed medical imaging...
research
09/10/2023

Lung Diseases Image Segmentation using Faster R-CNNs

Lung diseases are a leading cause of child mortality in the developing w...
research
07/28/2020

Decompose X-ray Images for Bone and Soft Tissue

Bones are always wrapped by soft tissues. As a result, bones in their X-...

Please sign up or login with your details

Forgot password? Click here to reset