Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images

Jacobs, Colin; Rikxoort, Eva M. van; Twellmann, Thorsten; Scholten, Ernst Th.; Jong, Pim A. de; Kuhnigk, Jan-Martin; Oudkerk, Matthijs; Koning, Harry J. de; Prokop, Mathias; Schaefer-Prokop, Cornelia; Ginneken, Bram van

doi:10.1016/j.media.2013.12.001

Cited by 237 publications

(145 citation statements)

References 48 publications

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…Semi-automated or fully automated three dimensional volume measurement requires specially provided software and measurement variability is still too high for non-solid and semi-solid nodules, 114 117 although the technology is improving rapidly. [118][119][120] Tumor volume doubling time is often misunderstood. Because small nodules are not usually biopsied, it is not possible to tell whether a long volume doubling time reflects the growth behavior of preinvasive lesions (atypical adenomatous hyperplasia or adenocarcinoma in situ) before it becomes invasive versus the true tumor growth rate.…”

Section: Tumor Volumementioning

confidence: 99%

Screening for lung cancer using low dose computed tomography

Tammemägi

Lam

2014

BMJ

View full text Add to dashboard Cite

Screening for lung cancer with low dose computed tomography can reduce mortality from the disease by 20% in high risk smokers. This review covers the state of the art knowledge on several aspects of implementing a screening program. The most important are to identify people who are at high enough risk to warrant screening and the appropriate management of lung nodules found at screening. An accurate risk prediction model is more efficient than age and pack years of smoking alone at identifying those who will develop lung cancer and die from the disease. Algorithms are available for assessing people who screen positive to determine who needs additional imaging or invasive investigations. Concerns about low dose computed tomography screening include false positive results, overdiagnosis, radiation exposure, and costs. Further work is needed to define the frequency and duration of screening and to refine risk prediction models so that they can be used to assess the risk of lung cancer in special populations. Another important area is the use of computer vision software tools to facilitate high throughput interpretation of low dose computed tomography images so that costs can be reduced and the consistency of scan interpretation can be improved. Sufficient data are available to support the implementation of screening programs at the population level in stages that can be expanded when found to perform well to improve the outcome of patients with lung cancer.

show abstract

Section: Tumor Volumementioning

confidence: 99%

Screening for lung cancer using low dose computed tomography

Tammemägi

Lam

2014

BMJ

View full text Add to dashboard Cite

show abstract

“…The methodology developed by Jacobs et al [6] aims to detect sub solid nodule automatically by means of 128 features based on intensity, shape, texture and context features. This methodology uses Gentle Boost (GB) classifier, Support vector machine (SVM) with radial basis as kernel function, linear discriminant classifier, k-nearest neighbour classifier and nearest mean classifier.…”

Section: Related Workmentioning

confidence: 99%

Fast and adaptive detection of pulmonary nodules in thoracic CT images based on improved fuzzy c-means medical image segmentation and SVM classifier

Govind¹,

Rahul²

2018

IJCA

View full text Add to dashboard Cite

Lung cancer found to be the common cause of death among people all around the world. The chance of survival among people was increased with the early detection of lung cancer. There has been an increase in the survival rate from 14 to 40% when it is detected in its earlier stage. Computed Tomography (CT) can be more efficient than X-ray. To classify the present of lung cancer in an CT-images,a lung cancer detection system using image processing is used. In this method, MATLAB is used as the software tool for processing images.In image processing procedures, process such as image pre-processing, segmentation with procedure called as fuzzy cmeans(FCM) clustering and feature extraction with the help of GLCM matrix and classification by using ANN classifier have been performed. It is intended to get the more accurate results by using various enhancement and segmentation techniques.

show abstract

“…While the focus of most CAD development has been directed toward solid nodules, systems tuned to the detection of ground glass and part solid nodules are emerging (63–65), and have been shown to improve reader performance for all three classes of lung nodule (64). …”

Section: Computer Aided Detection (Cad)mentioning

confidence: 99%

Lung Nodule and Cancer Detection in Computed Tomography Screening

Rubin

2015

Journal of Thoracic Imaging

110

View full text Add to dashboard Cite

Fundamental to the diagnosis of lung cancer in CT scans is the detection and interpretation of lung nodules. As the capabilities of CT scanners have advanced, higher levels of spatial resolution reveal tinier lung abnormalities. While not all detected lung nodules should be reported, radiologists strive to detect all nodules that might have relevance to cancer diagnosis. Although medium to large lung nodules are detected consistently, inter-reader agreement and reader sensitivity for lung nodule detection diminish substantially as nodule size falls below 8–10 mm. The difficulty in establishing an absolute reference standard presents a challenge to the reliability of studies performed to evaluate lung nodule detection. In the interest of improving detection performance, investigators are using eye tracking to analyze the effectiveness with which radiologists search CT scans relative to their ability to recognize nodules within their search path to determine if strategies might exist to improve performance across readers. Beyond the viewing of transverse CT reconstructions, image processing techniques such as thin-slab maximum intensity projections are used to substantially improve reader performance. Finally, the development of computer-aided detection has continued to evolve with the expectation that one day it will serve routinely as a tireless partner to the radiologist to enhance detection performance without significant prolongation of the interpretive process. This review provides an introduction to the current understanding of these varied issues as we enter the era of widespread lung cancer screening.

show abstract

Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images

Cited by 237 publications

References 48 publications

Screening for lung cancer using low dose computed tomography

Screening for lung cancer using low dose computed tomography

Fast and adaptive detection of pulmonary nodules in thoracic CT images based on improved fuzzy c-means medical image segmentation and SVM classifier

Lung Nodule and Cancer Detection in Computed Tomography Screening

Contact Info

Product

Resources

About