DeepAI AI Chat
Log In Sign Up

Improving the Segmentation of Anatomical Structures in Chest Radiographs using U-Net with an ImageNet Pre-trained Encoder

by   Maayan Frid-Adar, et al.

Accurate segmentation of anatomical structures in chest radiographs is essential for many computer-aided diagnosis tasks. In this paper we investigate the latest fully-convolutional architectures for the task of multi-class segmentation of the lungs field, heart and clavicles in a chest radiograph. In addition, we explore the influence of using different loss functions in the training process of a neural network for semantic segmentation. We evaluate all models on a common benchmark of 247 X-ray images from the JSRT database and ground-truth segmentation masks from the SCR dataset. Our best performing architecture, is a modified U-Net that benefits from pre-trained encoder weights. This model outperformed the current state-of-the-art methods tested on the same benchmark, with Jaccard overlap scores of 96.1 for heart and 85.5


page 5

page 7


Fully Convolutional Architectures for Multi-Class Segmentation in Chest Radiographs

The success of deep convolutional neural networks on image classificatio...

EfficientSeg: An Efficient Semantic Segmentation Network

Deep neural network training without pre-trained weights and few data is...

Anatomy X-Net: A Semi-Supervised Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification

Thoracic disease detection from chest radiographs using deep learning me...

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...

Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline

Chest x-rays are the most common radiology studies for diagnosing lung a...

VinDr-RibCXR: A Benchmark Dataset for Automatic Segmentation and Labeling of Individual Ribs on Chest X-rays

We introduce a new benchmark dataset, namely VinDr-RibCXR, for automatic...