Application of the iris filter for automatic detection of pulmonary nodules on computed tomography images

Suárez-Cuenca, Jorge Juan; Tahoces, Pablo G.; Souto, Miguel Abel; Lado, Marı́a J.; Rémy‐Jardin, Martine; Rémy, Jacques; Vidal, José Martı́nez

doi:10.1016/j.compbiomed.2009.07.005

Cited by 62 publications

(50 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pixels are classified according to two categories: pixels corresponding to dense tissue and pixels belonging to the lower density regions. Adaptive thresholds that automatically converge to the optimum gray level value for each image were calculated [13] ; it could not be selected a global threshold for all the images , because the gray level values varied on the different CT images, depending on the acquisition parameters. As a result, binary images containing the two previously described regions were obtained.…”

Section: Cad Schemementioning

confidence: 99%

“…Inc., Chicago, IL) [18] . To reduce FP detections, we developed a multistage classifier to discriminate between nodules and FPs [13] .…”

Section: Cad Schemementioning

confidence: 99%

“…It has been shown that CAD for lung nodule detection could increase radiologists' performance [5][6][7] . Different approaches have been proposed for automatic detection of lung cancer on CT around the world: while some have evaluated different marketed CAD systems, other investigators proposed other methods and processing techniques [5][6][7][8][9][10][11][12][13][14][15] .…”

mentioning

confidence: 99%

See 2 more Smart Citations

Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners

Bayarri

Suárez-Cuenca²,

Tahoces³

et al. 2012

JBGC

Self Cite

View full text Add to dashboard Cite

The purpose of this study was to evaluate the diagnostic performance of a computer-aided diagnosis (CAD) system, on the detection of pulmonary nodules in multidetector row computed tomography (MDCT) images, by using two different MDCT scanners. The computerized scheme was based on the iris filter. We have collected CT cases of patients with pulmonary nodules. We have included in the study one hundred and thirty-two calcified and noncalcified nodules, measuring 4-30 mm in diameter. CT examinations were performed by using two different equipments: a CT scanner (SOMATOM Emotion 6), and a dual-source computed tomography system (SOMATOM Definition) (Siemens Medical System, Forchheim, Germany), with the following parameters: collimation, 6x1.0mm (Emotion 6); and 64×0.6mm (Definition); 100-130 kV; 70-110 mAs. Data were reconstructed with a slice thickness of 1.25mm (Emotion 6) and 1mm (Definition). True positive cases were determined by an independent interpretation of the study by three experienced chest radiologists, the panel decision being used as the reference standard. Free-response Receiver Operating Characteristic curves, sensitivity and number of false-positive per scan, were calculated. Our CAD scheme, for the test set of the study, yielded a sensitivity of 80%, with an average of 5.2 FPs per examination. At an average false positive rate of 9 per scan, our CAD scheme achieved sensitivities of 94% for all nodules, 94.5% for solid, 80% for non-solid, 84% for spiculated, and 97% for non-spiculated nodules. These encouraging results suggest that our CAD system, advocated as a second reader, may help radiologists in the detection of lung nodules in MDCT.

show abstract

Section: Cad Schemementioning

confidence: 99%

“…Inc., Chicago, IL) [18] . To reduce FP detections, we developed a multistage classifier to discriminate between nodules and FPs [13] .…”

Section: Cad Schemementioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners

Bayarri

Suárez-Cuenca²,

Tahoces³

et al. 2012

JBGC

Self Cite

View full text Add to dashboard Cite

show abstract

“…After initial segmentation, lung volume has been extracted using several methods, and the extracted lung volume needed to be refined to include juxta-pleural nodules. For these purposes, morphological approaches [8,14], a rolling ball algorithm [5,15], and a chain code representation-based method [9] have been presented.…”

Section: Introductionmentioning

confidence: 99%

“…There are a variety of methods for extracting lung volume from a pulmonary CT scan. In order to segment lung, approaches such as global thresholding [5,6], optimal thresholding [7,8], three-dimensional (3-D)-adaptive fuzzy thresholding [9], rule-based region growing [10], connected component labeling [11], graph-cut algorithm [12], and hybrid segmentation [13] have generally been used. After initial segmentation, lung volume has been extracted using several methods, and the extracted lung volume needed to be refined to include juxta-pleural nodules.…”

Section: Introductionmentioning

confidence: 99%

Automated Pulmonary Nodule Detection System in Computed Tomography Images: A Hierarchical Block Classification Approach

Choi

2013

Entropy

View full text Add to dashboard Cite

A computer-aided detection (CAD) system is helpful for radiologists to detect pulmonary nodules at an early stage. In this paper, we propose a novel pulmonary nodule detection method based on hierarchical block classification. The proposed CAD system consists of three steps. In the first step, input computed tomography images are split into three-dimensional block images, and we apply entropy analysis on the block images to select informative blocks. In the second step, the selected block images are segmented and adjusted for detecting nodule candidates. In the last step, we classify the nodule candidate images into nodules and non-nodules. We extract feature vectors of the objects in the selected blocks. Lastly, the support vector machine is applied to classify the extracted feature vectors. Performance of the proposed system is evaluated on the Lung Image Database Consortium database. The proposed method has reduced the false positives in the nodule candidates significantly. It achieved 95.28% sensitivity with only 2.27 false positives per scan.

show abstract

Superpixel with nanoscale imaging and boosted deep convolutional neural network concept for lung tumor classification

Rani

Jawhar

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Lung tumor is a complex illness caused by irregular lung cell growth. Earlier tumor detection is a key factor in effective treatment planning. When assessing the lung computed tomography, the doctor has many difficulties when determining the precise tumor boundaries. By offering the radiologist a second opinion and helping to improve the sensitivity and accuracy of tumor detection, the use of computer‐aided diagnosis could be near as effective. In this research article, the proposed Lung Tumor Detection Algorithm consists of four phases: image acquisition, preprocessing, segmentation, and classification. The Advance Target Map Superpixel‐based Region Segmentation Algorithm is proposed for segmentation purposes, and then the tumor region is measured using the nanoimaging theory. Using the concept of boosted deep convolutional neural network yields 97.3% precision, image recognition can be achieved. In the types of literature with the current method, which shows the study's proposed efficacy, the implementation of the proposed approach is found dramatically.

show abstract

Application of the iris filter for automatic detection of pulmonary nodules on computed tomography images

Cited by 62 publications

References 15 publications

Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners

Automatic detection of pulmonary nodules: Evaluation of performance using two different MDCT scanners

Automated Pulmonary Nodule Detection System in Computed Tomography Images: A Hierarchical Block Classification Approach

Superpixel with nanoscale imaging and boosted deep convolutional neural network concept for lung tumor classification

Contact Info

Product

Resources

About