Computer-aided detection of early interstitial lung diseases using low-dose CT images

Park, Sang Cheol; Tan, Jun; Wang, Xingwei; Lederman, Dror; Leader, Joseph K.; Kim, Sung Hyun; Zheng, Bin

doi:10.1088/0031-9155/56/4/016

Cited by 64 publications

(37 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interestingly, low-dose computed tomography with a new computer-aided detection scheme may also detect early ILD [90]. Screening for ILD, especially UIP, has been analysed as a by-product in subjects (especially smokers) who underwent systematic low-dose computed tomography for lung cancer screening.…”

Section: The Value Of Velcro Crackles For Early Diagnosismentioning

confidence: 99%

Neglected evidence in idiopathic pulmonary fibrosis: from history to earlier diagnosis

Cordier¹,

Cottin²

2013

Eur Respir J

View full text Add to dashboard Cite

This perspective highlights some evidence that has hitherto been neglected, especially because it may not have been sufficiently explicated in the clinical respiratory medicine literature. Idiopathic pulmonary fibrosis (IPF) has appeared only in the second half of the 20th century and, like lung cancer and chronic obstructive pulmonary disease, may be a direct consequence of the cigarette smoking epidemic. It is a disease of lung ageing, with most affected patients being .70 years of age. The relationship between lung ageing and pulmonary fibrosis is further illustrated in the bleomycin mouse model, in which older males develop more fibrosis than young female mice.Earlier diagnosis of IPF is a prerequisite for significant progress to be made in the long-term outcome and prognosis. We consider that only two different yet complementary and realistic approaches could lead to earlier diagnosis of IPF and possibly to allowing more efficient disease management: 1) investigating any patients with early Velcro crackles at lung auscultation through proactive education of, and commitment from, primary care physicians; and 2) using current large-scale lung cancer screening strategies with lowdose high-resolution computed tomography in smokers for the detection of subclinical interstitial lung disease and especially early IPF. @ERSpublications Only two approaches could lead to earlier diagnosis of IPF and more efficient disease management

show abstract

Section: The Value Of Velcro Crackles For Early Diagnosismentioning

confidence: 99%

Neglected evidence in idiopathic pulmonary fibrosis: from history to earlier diagnosis

Cordier¹,

Cottin²

2013

Eur Respir J

View full text Add to dashboard Cite

show abstract

“…Computer-aided CT image analysis was recently shown to detect subtle changes in lung texture attendant to early asymptomatic ILD using lowdose CT scan studies. 18 Likewise, the current data A-D, Lung CT scan image is shown on the left and the corresponding image after conversion using the computer-generated two-point correlation function approach is shown on the right. A, Conforms to "normal lung."…”

Section: Radiographic Sarcoidosis Features and Corresponding Ltsmentioning

confidence: 99%

Quantitative Computerized Two-Point Correlation Analysis Of Lung CT Scans Correlates With Pulmonary Function In Pulmonary Sarcoidosis

Erdal

Crouser

Clymer³

2011

D21. Sarcoid: Advances in Diagnosis, Staging, and Treatment

View full text Add to dashboard Cite

Pulmonary function testing currently is the standard tool for objectively assessing lung disease severity in pulmonary sarcoidosis 1 and other chronic parenchymal and alveolar lung diseases. [2][3][4][5][6] High-resolution chest CT imaging is highly reproducible and is very sensitive for detecting lung pathology. 7 Unlike pulmonary function tests (PFTs), which are subject to variability in patient effort and ethnicity, technical variables such as laboratory methodology, and different interpretive algorithms, 8 lung CT scan results are highly reproducible. However, the current approach to interpretation of CT scan results, which depend on radiologists, is poorly standardized and qualitative for both clinical and research applications in patients with interstitial lung disease (ILD). 9 At present, there is no convenient, well-standardized, radiologistgenerated CT image analysis approach that provides a quantitative assessment of lung disease. Thus, an effi cient, objective, and quantifi able approach to chest CT image analysis is needed.Previous attempts to quantify the severity of ILD, particularly fi brotic lung disease, based on computeraided CT image analysis were of limited utility. In general, prior studies have reported modest correlations Background : Chest CT scans are commonly used to clinically assess disease severity in patients presenting with pulmonary sarcoidosis. Despite their ability to reliably detect subtle changes in lung disease, the utility of chest CT scans for guiding therapy is limited by the fact that image interpretation by radiologists is qualitative and highly variable. We sought to create a computerized CT image analysis tool that would provide quantitative and clinically relevant information. Methods: We established that a two-point correlation analysis approach reduced the background signal attendant to normal lung structures, such as blood vessels, airways, and lymphatics while highlighting diseased tissue. This approach was applied to multiple lung fi elds to generate an overall lung texture score (LTS) representing the quantity of diseased lung parenchyma. Using deidentifi ed lung CT scan and pulmonary function test (PFT) data from The Ohio State University Medical Center's Information Warehouse, we analyzed 71 consecutive CT scans from patients with sarcoidosis for whom simultaneous matching PFTs were available to determine whether the LTS correlated with standard PFT results. Results: We found a high correlation between LTS and FVC, total lung capacity, and diffusing capacity of the lung for carbon monoxide ( P , .0001 for all comparisons). Moreover, LTS was equivalent to PFTs for the detection of active lung disease. The image analysis protocol was conducted quickly ( , 1 min per study) on a standard laptop computer connected to a publicly available National Institutes of Health ImageJ toolkit. Conclusions: The two-point image analysis tool is highly practical and appears to reliably assess lung disease severity. We predict that this tool will be useful for clinical and resear...

show abstract

“…Computer-aided analysis recognises early interstitial lung diseases with a diagnostic sensitivity of 80.0% and specificity of 85.7% in low-dose CT images [4]. More recently, in an Italian lung cancer screening project, two (0.3%) typical UIP patterns out of 692 heavy smokers were distinguished via low-dose, thin-section CT [5].…”

mentioning

confidence: 99%

Who and what should we rely on in early diagnosis of idiopathic pulmonary fibrosis?

Cottin

Cordier

2012

Eur Respir J

View full text Add to dashboard Cite

Computer-aided detection of early interstitial lung diseases using low-dose CT images

Cited by 64 publications

References 33 publications

Neglected evidence in idiopathic pulmonary fibrosis: from history to earlier diagnosis

Neglected evidence in idiopathic pulmonary fibrosis: from history to earlier diagnosis

Quantitative Computerized Two-Point Correlation Analysis Of Lung CT Scans Correlates With Pulmonary Function In Pulmonary Sarcoidosis

Who and what should we rely on in early diagnosis of idiopathic pulmonary fibrosis?

Contact Info

Product

Resources

About