Color radiography in lung nodule detection and characterization: comparison with conventional gray scale radiography.

BMC Med Imaging

Department of Radiology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 135-710, South Korea.

Published: August 2016

Background: To compare the capability of lung nodule detection and characterization between dual-energy radiography with color-representation (DCR) and conventional gray scale chest radiography (GSR).

Methods: A total of 130 paired chest radiographs (DCR and GSR) obtained from 65 patients (14 with normal scans and 51 with pulmonary nodules) were evaluated. After analysis, 45 non-calcified and 21 calcified nodules were identified. DCR was obtained by adding color space within material-decomposed data (blue for high attenuation and red for low attenuation) and by compounding the manipulated data to one color image. Three radiologists marked suggested nodules on radiographic images and assessed the level of confidence of lesion presence and probability of nodule calcification by using a nine-point rating scale. The jackknife active free-response receiver operating characteristics (JAFROC) analysis was used to evaluate lesion detectability, and multi-reader multi-case receiver operating characteristics (MRMC ROC) analysis was used for the evaluation of the accuracy of nodule calcification prediction.

Results: Figures of merit (FOM) from JAFROC was 0.807 for DCR and 0.811 for GSR, respectively; nodule detectability was not significantly different between DCR and GSR (p = 0.93). Areas under curve (AUC) from MRMC ROC were 0.944 for DCR and 0.828 for GSR, respectively; performance of DCR in predicting lung nodule calcification was significantly higher than that of GSR (p = 0.04).

Conclusions: DCR showed similar performance in terms of lung nodule detection compared with GSR. However, DCR does provide a significant benefit in predicting the presence of nodule calcification.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4994314PMC
http://dx.doi.org/10.1186/s12880-016-0155-7DOI Listing

Publication Analysis

Top Keywords

lung nodule
16
nodule calcification
16
nodule detection
12
dcr
9
nodule
8
detection characterization
8
conventional gray
8
gray scale
8
dcr gsr
8
receiver operating
8

Similar Publications

Endometriosis is a systemic, inflammatory, estrogen-dependent condition characterized by endometrial stroma and gland-like lesions outside of the uterus. It causes a range of symptoms, notably chronic pelvic pain, infertility and organ dysfunction. Thoracic endometriosis syndrome (TES) has been described as endometriosis that is found in the lung parenchyma, pleura and diaphragm.

View Article and Find Full Text PDF

Background: A ground glass nodule (GGN) is a radiologically descriptive term for a lung parenchymal area with increased attenuation and preserved bronchial and vascular structures. GGNs are further divided into pure versus subsolid lesions. The differential diagnosis for GGNs is wide and contains a malignant possibility for a lung adenocarcinoma precursor or tumor.

View Article and Find Full Text PDF

The effect of concurrent acetylsalicylic acid on hemorrhagic complications during percutaneous image-guided lung biopsy.

Respir Med Res

December 2024

Department of Thoracic Oncology, Pleural Diseases and Interventional Pulmonology, Marseille, France.

Background: CT-guided trans-thoracic lung biopsy (CT-TTLB) is efficient and widely used to diagnose pulmonary nodules. After pneumothorax, the second most frequent complication is hemoptysis, which can be life-threatening. These patients often have comorbidities and are on acetylsalicylic-acid (ASA) therapy.

View Article and Find Full Text PDF

Robotic bronchoscopy: Evolution of advanced diagnostic technologies for pulmonary lesions.

Best Pract Res Clin Anaesthesiol

March 2024

1400 Holcombe Blvd, FC 13.2000, Houston, TX, 77030, USA. Electronic address:

Lung cancer is among one of the most commonly diagnosed malignancies and is the leading cause of cancer-related mortality in both men and women globally, with an estimated 1.8 million deaths annually. Moreover, it is also the leading cause of cancer related deaths in the United States (U.

View Article and Find Full Text PDF

An optimized support vector machine for lung cancer classification system.

Front Oncol

December 2024

Honorary Research Associate, Department of Operations and Quality Management, Durban University of Technology, Durban, South Africa.

Introduction: Lung cancer is one of the main causes of the rising death rate among the expanding population. For patients with lung cancer to have a higher chance of survival and fewer deaths, early categorization is essential. The goal of thisresearch is to enhance machine learning to increase the precision and quality of lung cancer classification.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!