Atlas-based rib-bone detection in chest X-rays

Abstract

This paper investigates using rib-bone atlases for automatic detection of rib-bones in chest X-rays (CXRs). We built a system that takes patient X-ray and model atlases as input and automatically computes the posterior rib borders with high accuracy and efficiency. In addition to conventional atlas, we propose two alternative atlases: (i) automatically computed rib bone models using Computed Tomography (CT) scans, and (ii) dual energy CXRs. We test the proposed approach with each model on 25 CXRs from the Japanese Society of Radiological Technology (JSRT) dataset and another 25 CXRs from the National Library of Medicine CXR dataset. We achieve an area under the ROC curve (AUC) of about 95% for Montgomery and 91% for JSRT datasets. Using the optimal operating point of the ROC curve, we achieve a segmentation accuracy of 88.91 ± 1.8 % for Montgomery and 85.48 ± 3.3 % for JSRT datasets. Our method produces comparable results with the state-of-the-art algorithms. The performance of our method is also excellent on challenging X-rays as it successfully addressed the rib-shape variance between patients and number of visible rib-bones due to patient respiration.

XNet: a convolutional neural network (CNN) implementation for medical x-ray image segmentation suitable for small datasets

“…Despite our dataset being small compared to those used in many machine learning applications, we achieve an overall accuracy significantly higher, and more generalisable, than work using classical image processing techniques. [2][3][4][5][6]12 Additionally, we show that our architecture outperforms leading image segmentation networks developed for other applications. 13 Our paper is structured as follows: after reviewing a selection of the existing literature in Section 2, we discuss our dataset in Section 3 -how we collect and label the data, and the augmentation methods to prevent overfitting; in Section 4 we address the design and structure of our CNN, covering training and testing stages; the results of the network are discussed in Section 5, where we also address the post-processing stage of false positive reduction; a comparison of our results with other works from the classical and machine learning literature is presented in Section 6, after which we discuss future applications and developments in Section 7.…”

“…This work is less sensitive to noise, however, loses some boundary continuity. Similarly, atlas models have been developed for medical image segmentation, and an application to rib cage segmentation is given by Candemir et al 12 From such techniques the authors are able to generate complete segmentations, however, the boundaries remain noisy and the area under the ROC curve (AUC) is highly dependent on the dataset analysed.…”

Lung field segmentation in chest radiographs: a historical review, current status, and expectations from deep learning

“…In addition to the medical images, the dataset includes clinical data consisting of patient's gender, age, height, weight, and social information. The dataset is publicly available and has been used for rib‐bone detection in [51].…”

Software for Full-Color 3D Reconstruction of the Biological Tissues Internal Structure

“…This method can be used for aims of medicine, veterinary medicine, zootechny and related areas where MRI or histological reconstructions do not provide a full-fledged three-dimensional view [3,4,10].…”

“…Very high accuracy up to several microns. 4. Absence of "screening interference" in contrast to non-destructive methods [26].…”