Lung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid Registration

By Sema Candemir, Stefan Jaeger, Kannappan K. Palaniappan, Jonathan P. Musco, Rahul Kumar Singh, Z. Xue, Alexandros Karargyris, Sameer Kiran Antani, George R. Thoma, Clement J. McDonald. IEEE Transactions on Medical Imaging, 2013

653 citations recorded by the source corpus.

The National Library of Medicine (NLM) is developing a digital chest X-ray (CXR) screening system for deployment in resource constrained communities and developing countries worldwide with a focus on early detection of tuberculosis. A critical component in the computer-aided diagnosis of digital CXRs is the automatic detection of the lung regions. In this paper, we present a nonrigid registration-driven robust lung segmentation method using image retrieval-based patient specific adaptive lung models that detects lung boundaries, surpassing state-of-the-art performance. The method consists of three main stages: 1) a content-based image retrieval approach for identifying training images (with masks) most similar to the patient CXR using a partial Radon transform and Bhattacharyya shape similarity measure, 2) creating the initial patient-specific anatomical model of lung shape using SIFT-flow for deformable registration of training masks to the patient CXR, and 3) extracting refined lung boundaries using a graph cuts optimization approach with a customized energy function. Our average accuracy of 95.4% on the public JSRT database is the highest among published results. A similar degree of accuracy of 94.1% and 91.7% on two new CXR datasets from Montgomery County, MD, USA, and India, respectively, demonstrates the robustness of our lung segmentation approach.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/86bf80d54ef110149398c5830606547c0537641f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Computer-aided detection in chest radiography based on artificial intelligence: a survey (2018, background): “Some studies segment the lung fields [28, 29]; others detect the contours of the lung fields [30] or ribs [31]; and a few try to directly detect the diaphragm or the costophrenic angle [32].”
Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges (2022, background): “[173] 2022 Exploit concepts from experience repetition and adversarial generation research Cross-device Centralized Decentralized Simulation GAN FedAvg FedProx FedBN Synchronous Asynchronous Random X-ray data [174], [175] HAM10000 [176]”
Abnormality Detection and Localization in Chest X-Rays using Deep Convolutional Neural Networks (2017, methodology): “In [6] lung segmentation was performed using 247 images from JSRT, 138 images from Montgomery and 397 images from the India dataset with segmentation accuracies of 95.”
Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. (2014, methodology): “Initial classification results for both sets have been presented in (3), and lung segmentation results for the MC set are shown in (5), which can serve as benchmarks for other researchers.”
MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports (2019, background): “The Montgomery County chest X-ray set (MC) and the Shenzhen Hospital X-ray set (SH) are publicly available datasets focusing on classification of tuberculosis 29,30 .”
Multi-Atlas Segmentation of Biomedical Images: A Survey (2014, background): “, 2014e), or a graph-cut-based method (Candemir et al., 2014; Lee et al., 2014b).”
INet: Convolutional Networks for Biomedical Image Segmentation (2021, methodology): “…of the proposed method in the segmentation of biomedical images, we carried out experiments on nine public imaging datasets: three brain (BraTS2013, LMS, BTD) one heart MRI [42]–[44], one liver one spleen CT [44], [45], one lung X-ray [9], one colon endoscopic [46], and one nerve ultrasonic [47].”