Literature DB >> 21626918

Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification.

Sheng Chen1, Kenji Suzuki, Heber MacMahon.   

Abstract

PURPOSE: To develop a computer-aided detection (CADe) scheme for nodules in chest radiographs (CXRs) with a high sensitivity and a low false-positive (FP) rate.
METHODS: The authors developed a CADe scheme consisting of five major steps, which were developed for improving the overall performance of CADe schemes. First, to segment the lung fields accurately, the authors developed a multisegment active shape model. Then, a two-stage nodule-enhancement technique was developed for improving the conspicuity of nodules. Initial nodule candidates were detected and segmented by using the clustering watershed algorithm. Thirty-one shape-, gray-level-, surface-, and gradient-based features were extracted from each segmented candidate for determining the feature space, including one of the new features based on the Canny edge detector to eliminate a major FP source caused by rib crossings. Finally, a nonlinear support vector machine (SVM) with a Gaussian kernel was employed for classification of the nodule candidates.
RESULTS: To evaluate and compare the scheme to other published CADe schemes, the authors used a publicly available database containing 140 nodules in 140 CXRs and 93 normal CXRs. The CADe scheme based on the SVM classifier achieved sensitivities of 78.6% (110/140) and 71.4% (100/140) with averages of 5.0 (1165/233) FPs/image and 2.0 (466/233) FPs/image, respectively, in a leave-one-out cross-validation test, whereas the CADe scheme based on a linear discriminant analysis classifier had a sensitivity of 60.7% (85/140) at an FP rate of 5.0 FPs/image. For nodules classified as "very subtle" and "extremely subtle," a sensitivity of 57.1% (24/42) was achieved at an FP rate of 5.0 FPs/image. When the authors used a database developed at the University of Chicago, the sensitivities was 83.3% (40/48) and 77.1% (37/48) at an FP rate of 5.0 (240/48) FPs/image and 2.0 (96/48) FPs/image, respectively.
CONCLUSIONS: These results compare favorably to those described for other commercial and non-commercial CADe nodule detection systems.

Mesh:

Year:  2011        PMID: 21626918      PMCID: PMC3069992          DOI: 10.1118/1.3561504

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  43 in total

1.  Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size.

Authors:  B Sahiner; H P Chan; N Petrick; R F Wagner; L Hadjiiski
Journal:  Med Phys       Date:  2000-07       Impact factor: 4.071

2.  Computer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique.

Authors:  Q Li; S Katsuragawa; K Doi
Journal:  Med Phys       Date:  2001-10       Impact factor: 4.071

3.  Local contralateral subtraction based on bilateral symmetry of lung for reduction of false positives in computerized detection of pulmonary nodules.

Authors:  Hiroyuki Yoshida
Journal:  IEEE Trans Biomed Eng       Date:  2004-05       Impact factor: 4.538

4.  Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification.

Authors:  Junji Shiraishi; Qiang Li; Kenji Suzuki; Roger Engelmann; Kunio Doi
Journal:  Med Phys       Date:  2006-07       Impact factor: 4.071

5.  Minimal shape and intensity cost path segmentation.

Authors:  Dieter Seghers; Dirk Loeckx; Frederik Maes; Dirk Vandermeulen; Paul Suetens
Journal:  IEEE Trans Med Imaging       Date:  2007-08       Impact factor: 10.048

6.  Classifier performance prediction for computer-aided diagnosis using a limited dataset.

Authors:  Berkman Sahiner; Heang-Ping Chan; Lubomir Hadjiiski
Journal:  Med Phys       Date:  2008-04       Impact factor: 4.071

7.  Glossary of terms for CT of the lungs: recommendations of the Nomenclature Committee of the Fleischner Society.

Authors:  J H Austin; N L Müller; P J Friedman; D M Hansell; D P Naidich; M Remy-Jardin; W R Webb; E A Zerhouni
Journal:  Radiology       Date:  1996-08       Impact factor: 11.105

8.  Missed bronchogenic carcinoma: radiographic findings in 27 patients with a potentially resectable lesion evident in retrospect.

Authors:  J H Austin; B M Romney; L S Goldsmith
Journal:  Radiology       Date:  1992-01       Impact factor: 11.105

9.  Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules.

Authors:  N F Vittitoe; J A Baker; C E Floyd
Journal:  Acad Radiol       Date:  1997-02       Impact factor: 3.173

10.  Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data.

Authors:  D P Chakraborty
Journal:  Med Phys       Date:  1989 Jul-Aug       Impact factor: 4.071

View more
  19 in total

1.  A computerized scheme for lung nodule detection in multiprojection chest radiography.

Authors:  Wei Guo; Qiang Li; Sarah J Boyce; H Page McAdams; Junji Shiraishi; Kunio Doi; Ehsan Samei
Journal:  Med Phys       Date:  2012-04       Impact factor: 4.071

2.  Machine Learning in Computer-aided Diagnosis of the Thorax and Colon in CT: A Survey.

Authors:  Kenji Suzuki
Journal:  IEICE Trans Inf Syst       Date:  2013-04-01

Review 3.  Overview of deep learning in medical imaging.

Authors:  Kenji Suzuki
Journal:  Radiol Phys Technol       Date:  2017-07-08

4.  A parameterized logarithmic image processing method with Laplacian of Gaussian filtering for lung nodule enhancement in chest radiographs.

Authors:  Sheng Chen; Liping Yao; Bao Chen
Journal:  Med Biol Eng Comput       Date:  2016-03-25       Impact factor: 2.602

5.  Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images.

Authors:  Chengsheng Mao; Yiheng Pan; Zexian Zeng; Liang Yao; Yuan Luo
Journal:  Proceedings (IEEE Int Conf Bioinformatics Biomed)       Date:  2019-01-24

6.  Utilizing Synthetic Nodules for Improving Nodule Detection in Chest Radiographs.

Authors:  Minki Chung; Seo Taek Kong; Beomhee Park; Younjoon Chung; Kyu-Hwan Jung; Joon Beom Seo
Journal:  J Digit Imaging       Date:  2022-03-18       Impact factor: 4.903

7.  A review of computer-aided diagnosis in thoracic and colonic imaging.

Authors:  Kenji Suzuki
Journal:  Quant Imaging Med Surg       Date:  2012-09

8.  Lung cancer with scattered consolidation: detection of new independent radiological category of peripheral lung cancer on thin-section computed tomography.

Authors:  Takeshi Matsunaga; Kenji Suzuki; Aritoshi Hattori; Mariko Fukui; Yoshitaka Kitamura; Yoshikazu Miyasaka; Kazuya Takamochi; Shiaki Oh
Journal:  Interact Cardiovasc Thorac Surg       Date:  2012-12-17

9.  Computerized detection of lung nodules by means of "virtual dual-energy" radiography.

Authors:  Sheng Chen; Kenji Suzuki
Journal:  IEEE Trans Biomed Eng       Date:  2012-11-15       Impact factor: 4.538

10.  Pixel-based machine learning in medical imaging.

Authors:  Kenji Suzuki
Journal:  Int J Biomed Imaging       Date:  2012-02-28
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.