Reduction of false positives in computerized detection of lung nodules in chest radiographs using artificial neural networks, discriminant analysis, and a rule-based scheme

A computer-aided diagnosis (CAD) scheme is being developed to identify image regions considered suspicious for lung nodules in chest radiographs to assist radiologists in making correct diagnoses. Automated classifiers—an artificial neural network, discriminant analysis, and a rule-based scheme—are used to reduce the number of false-positive detections of the CAD scheme. The CAD scheme first detects nodule candidates from chest radiographs based on a difference image technique. Nine image features characterizing nodules are extracted automatically for each of the nodule candidates. The extracted image features are then used as input data to the classifiers for distinguishing actual nodules from the false-positive detections. The performances of the classifiers are evaluated by receiver-operating characteristic analysis. On the basis of the database of 30 normal and 30 abnormal chest images, the neural network achieves an AZ value (area under the receiver-operating-characteristic curve) of 0.79 in detecting lung nodules, as tested by the round-robin method. The neural network, after being trained with a training database, is able to eliminate more than 83% of the false-positive detections reported by the CAD scheme. Moreover, the combination of the trained neural network and a rule-based scheme eliminates 96% of the false-positive detections of the CAD scheme.

[1]  K Doi,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: automated delineation of posterior ribs in chest images. , 1991, Medical physics.

[2]  Maryellen L. Giger,et al.  Computerized scheme for the detection of pulmonary nodules. A nonlinear filtering technique. , 1992 .

[3]  C E Metz,et al.  Quantification of failure to demonstrate statistical significance. The usefulness of confidence intervals. , 1993, Investigative radiology.

[4]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[5]  J M Boone,et al.  Neural networks in radiology: an introduction and evaluation in a signal detection task. , 1990, Medical physics.

[6]  Matthew T. Freedman,et al.  Automatic lung nodule detection using profile matching and back-propagation neural network techniques , 1993, Journal of Digital Imaging.

[7]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms: applications of artificial neural networks. , 1992, Medical physics.

[8]  M.L. Giger.  Computerized scheme for the detection of pulmonary nodules , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[9]  C E Floyd,et al.  An artificial neural network for lesion detection on single-photon emission computed tomographic images. , 1992, Investigative radiology.

[10]  J Y Lo,et al.  Observer Evaluation of Scatter Subtraction for Digital Portable Chest Radiographs , 1993, Investigative radiology.

[11]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.

[12]  C. Metz,et al.  A New Approach for Testing the Significance of Differences Between ROC Curves Measured from Correlated Data , 1984 .

[13]  G. W. Gross,et al.  Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs. , 1990, Investigative radiology.

[14]  M Oudkerk,et al.  Liver metastases from colorectal carcinoma: detection with continuous CT angiography. , 1992, Radiology.

[15]  Maryellen L. Giger,et al.  Simulation studies of data classification by artificial neural networks: Potential applications in medical imaging and decision making , 2009, Journal of Digital Imaging.

[16]  M L Giger,et al.  Pulmonary nodules: computer-aided detection in digital chest images. , 1990, Radiographics : a review publication of the Radiological Society of North America, Inc.

[17]  M. Giger,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields. , 1988, Medical physics.

[18]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[19]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[20]  P. Friedman,et al.  Radiologic errors in patients with lung cancer. , 1981, The Western journal of medicine.

[21]  Y. Wu,et al.  Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: pilot study. , 1990, Radiology.

[22]  Matthew T. Freedman,et al.  Shape feature analysis using artificial neural networks for improvements of hybrid lung nodule detection system , 1993, Medical Imaging.

[23]  M. Giger,et al.  Computerized detection of pulmonary nodules in digital chest images: use of morphological filters in reducing false-positive detections. , 1990, Medical physics.

[24]  M. Giger,et al.  Potential usefulness of computerized nodule detection in screening programs for lung cancer. , 1992, Investigative radiology.

[25]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[26]  Robert M. Nishikawa,et al.  Application of artificial neural networks in mammography for the diagnosis of breast cancer , 1992, Other Conferences.

[27]  Kunio Doi,et al.  Development Of A New Digital Radiographic Image Processing System , 1982, Other Conferences.

[28]  S Katsuragawa,et al.  Image feature analysis and computer-aided diagnosis in digital radiography: detection and characterization of interstitial lung disease in digital chest radiographs. , 1988, Medical physics.

[29]  M L Giger,et al.  Image feature analysis of false-positive diagnoses produced by automated detection of lung nodules. , 1992, Investigative radiology.