Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis.

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Abstract Text:

Yuichi Matsuki,Katsumi Nakamura,Hideyuki Watanabe,Takatoshi Aoki,Hajime Nakata,Shigehiko Katsuragawa,Kunio Doi,

OBJECTIVE: The purpose of our study was to use an artificial neural network to differentiate benign from malignant pulmonary nodules on high-resolution CT findings and to evaluate the effect of artificial neural network output on the performance of radiologists using receiver operating characteristic analysis. MATERIALS AND METHODS: We selected 155 cases with pulmonary nodules less than 3 cm (99 malignant nodules and 56 benign nodules). An artificial neural network was used to distinguish benign from malignant nodules on the basis of seven clinical parameters and 16 radiologic findings that were extracted by attending radiologists using subjective rating scales. In the observer test, 12 radiologists (four attending radiologists, four radiology fellows, and four radiology residents) were presented with high-resolution CT images, first without and then with the artificial neural network output. Observer performance was evaluated by means of receiver operating characteristic analysis using a continuous rating scale. RESULTS: The artificial neural network showed a high performance in differentiating benign from malignant pulmonary nodules (A(z) = 0.951). The average A(z) value for all radiologists increased by a statistically significant level, from 0.831 to 0.959, with the use of the artificial neural network output. CONCLUSION: Our computerized scheme using the artificial neural network can improve the diagnostic accuracy of radiologists who are differentiating benign from malignant pulmonary nodules on high-resolution CT.

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Publishing Authors By Initials

Y Matsuki,K Nakamura,H Watanabe,T Aoki,H Nakata,S Katsuragawa,K Doi,

For similar tomography, x-ray computed research abstracts see: tomography, x-ray computed research

PUBMED ID PMID:

MEDLINE DATE:

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: AJR. American journal of roentgenology

VOLUME: 178

Page Numbers: 657-63

Journal Abbreviation:

ISSN: 0361-803X

DAY: 15

MONTH: Mar

YEAR: 2002

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 7708173

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Keywords Mesh Terms:

KEYWORDS: Tomography, X-Ray Computed

MESH TERMS: radiography

Chemical & Substance for Abstract: Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis.

AFFILIATION: Department of Radiology, University of Occupational and Environmental Health School of Medicine, Iseigaoka 1-1, Yahatanishi-ku, Kitakyushu-shi, 807-8555, Japan.

Country: United States

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: AJR Am J Roentgenol

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis Related Publications

• A proximal kappaB site in the IL-23 p19 promoter is responsible for RelA- and c-Rel-dependent transcription.
• An Improved Computer-aided Diagnosis Scheme Using the Nearest Neighbor Criterion for Determining Histological Classification of Clustered Microcalcifications.
• Antisense activity of 2',4'-BNA targeted to PPAR gamma in THP-1 and HCT116 cells.
• Comparison of typical evaluation methods for computer-aided diagnostic schemes: Monte Carlo simulation study.
• Computer-aided diagnosis in medical imaging: historical review, current status and future potential.
• Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification.
• Computerized detection of vertebral compression fractures on lateral chest radiographs: preliminary results with a tool for early detection of osteoporosis.
• Conformational restraints induced by modification of configuration of threonine and oxazoline residues in ascidiacyclamide analogues.
• Declines in sex ratio at birth and fetal deaths in Japan, and in U.S. whites but not African Americans.
• Determination of subjective similarity for pairs of masses and pairs of clustered microcalcifications on mammograms: comparison of similarity ranking scores and absolute similarity ratings.
• Development of a computer-aided diagnostic scheme for detection of interval changes in successive whole-body bone scans.
• Effect of temporal subtraction technique on interpretation time and diagnostic accuracy of chest radiography.
• Enhanced synthesis of poly(3-hydroxybutyrate) in recombinant Escherichia coli by means of error-prone PCR mutagenesis, saturation mutagenesis, and in vitro recombination of the type II polyhydroxyalkanoate synthase gene.
• Evaluation of atrial and brain natriuretic polypeptides in association with angiotensin-converting enzyme gene polymorphism in Japanese non-diabetic hemodialysis patients.
• Experimental determination of subjective similarity for pairs of clustered microcalcifications on mammograms: observer study results.
• Gene expression profiles of drug-metabolizing enzymes (DMEs) in rat liver during pregnancy and lactation.
• Improving radiologists' recommendations with computer-aided diagnosis for management of small nodules detected by CT.
• In vitro evolution of a polyhydroxybutyrate synthase by intragenic suppression-type mutagenesis.
• Isolation of nuclei from a tetraploid strain of Saccharomyces cerevisiae.
• Ovarian activity and pregnancy in the Siberian tiger, Panthera tigris altaica, assessed by fecal gonadal steroid hormones analyses.
• Purification and some properties of cathepsin A of large molecular size from pig kidney.
• Purification and some properties of cathepsin A of small molecular size from pig kidney.
• Relationship between body temperature and ovarian cycle in Asian and African elephants.
• SRY-related HMG box 9 regulates the expression of Col4a2 through transactivating its enhancer element in mesangial cells.
• Stabilization of pig kidney cathepsin A by sucrose and chloride ion, and inhibition of the enzyme activity by diisopropyl fluorophosphate and sulfhydryl reagents.
• Substrate specificity of carboxypeptidase from Watermelon.
• Synergistic interaction of Clostridium cellulovorans cellulosomal cellulases and HbpA.
• Usefulness of temporal subtraction images for identification of interval changes in successive whole-body bone scans: JAFROC analysis of radiologists' performance.
• Usefulness of texture analysis for computerized classification of breast lesions on mammograms.
• Wrist flexion contracture: An unusual complication following palmaris longus tendon harvest.