Application of an artificial neural network to high-resolution CT: usefulness in differential diagnosis of diffuse lung disease.

OBJECTIVE The purpose of our study was to evaluate the diagnostic performance of an artificial neural network (ANN) in differentiating among certain diffuse lung diseases using high-resolution CT (HRCT) and the effect of ANN output on radiologists' diagnostic performance. MATERIALS AND METHODS We selected 130 clinical cases of diffuse lung disease. We used a single three-layer, feed-forward ANN with a back-propagation algorithm. The ANN was designed to differentiate among 11 diffuse lung diseases by using 10 clinical parameters and 23 HRCT features. Therefore, the ANN consisted of 33 input units and 11 output units. Subjective ratings for 23 HRCT features were provided independently by eight radiologists. All clinical cases were used for training and testing of the ANN by implementing a round-robin technique. In the observer test, a subset of 45 cases was selected from the database of 130 cases. HRCT images were viewed by eight radiologists first without and then with ANN output. The radiologists' performance was evaluated with receiver operating characteristic (ROC) analysis with a continuous rating scale. RESULTS The average area under the ROC curve for ANN performance obtained with all clinical parameters and HRCT features was 0.956. The diagnostic performance of four chest radiologists and four general radiologists was increased from 0.986 to 0.992 (p = 0.071) and 0.958 and 0.971 (p < 0.001), respectively, when they used the ANN output based on their own feature ratings. CONCLUSION The ANN can provide a useful output as a second opinion to improve general radiologists' diagnostic performance in the differential diagnosis of certain diffuse lung diseases using HRCT.

[1]  J. Tashjian,et al.  High-Resolution CT of the Lung. 2nd ed , 1996 .

[2]  E. Maffei,et al.  High-resolution CT in diagnosis of diffuse infiltrative lung disease. , 2005, Seminars in ultrasound, CT, and MR.

[3]  K. Doi,et al.  Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. , 2002, AJR. American journal of roentgenology.

[4]  J. Gurney,et al.  Solitary pulmonary nodules: determining the likelihood of malignancy with neural network analysis. , 1995, Radiology.

[5]  C J Vyborny,et al.  Artificial neural networks in chest radiography: application to the differential diagnosis of interstitial lung disease. , 1999, Academic radiology.

[6]  K Doi,et al.  Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis. , 1990, Investigative radiology.

[7]  P. Grenier,et al.  Chronic diffuse interstitial lung disease: diagnostic value of chest radiography and high-resolution CT. , 1991, Radiology.

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

[9]  Kunio Doi,et al.  Use of an artificial neural network to determine the diagnostic value of specific clinical and radiologic parameters in the diagnosis of interstitial lung disease on chest radiographs. , 2002, Academic radiology.

[10]  S Katsuragawa,et al.  Computer-aided diagnosis for detection of interstitial opacities on chest radiographs. , 1998, AJR. American journal of roentgenology.

[11]  K. Doi,et al.  Effect of a computer-aided diagnosis scheme on radiologists' performance in detection of lung nodules on radiographs. , 1996, Radiology.

[12]  Kunio Doi,et al.  Computer-aided diagnosis in thoracic CT. , 2005, Seminars in ultrasound, CT, and MR.

[13]  Y Nakajima,et al.  Bronchiolitis obliterans with organizing pneumonia versus chronic eosinophilic pneumonia: high-resolution CT findings in 81 patients. , 2001, AJR. American journal of roentgenology.

[14]  N. Müller,et al.  High-resolution computed tomography in acute diffuse lung disease in the immunocompromised patient. , 1994, Radiologic clinics of North America.

[15]  H. Itoh,et al.  The diagnostic accuracy of high-resolution computed tomography in diffuse infiltrative lung diseases. , 1993, Chest.

[16]  K. Murata,et al.  Pulmonary parenchymal disease: evaluation with high-resolution CT. , 1989, Radiology.

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

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

[19]  C Chastang,et al.  Chronic diffuse infiltrative lung disease: determination of the diagnostic value of clinical data, chest radiography, and CT and Bayesian analysis. , 1994, Radiology.

[20]  N L Müller,et al.  Clinical value of high-resolution CT in chronic diffuse lung disease. , 1991, AJR. American journal of roentgenology.

[21]  C. Metz,et al.  Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. , 1998, Statistics in medicine.

[22]  K Nakamura,et al.  Computerized analysis of the likelihood of malignancy in solitary pulmonary nodules with use of artificial neural networks. , 2000, Radiology.

[23]  M. Kitaichi,et al.  Bronchiolitis obliterans organizing pneumonia. Clinical features and differential diagnosis. , 1992, Chest.

[24]  S. Swensen,et al.  Diffuse lung disease: diagnostic accuracy of CT in patients undergoing surgical biopsy of the lung. , 1997, Radiology.

[25]  S. Swensen,et al.  High-resolution CT of the lungs: findings in various pulmonary diseases. , 1992, AJR. American journal of roentgenology.

[26]  N. Müller,et al.  Chronic diffuse infiltrative lung disease: comparison of diagnostic accuracy of high-resolution and conventional CT. , 1991, AJR. American journal of roentgenology.

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

[28]  X. Xu,et al.  Study on the treatment of tracheobronchial stenosis using expandable metallic stents. , 2001, Journal of Nippon Medical School = Nippon Ika Daigaku zasshi.

[29]  J. Remy,et al.  Assessment of diffuse infiltrative lung disease: comparison of conventional CT and high-resolution CT. , 1991, Radiology.

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

[31]  K Nakamura,et al.  Effect of an artificial neural network on radiologists' performance in the differential diagnosis of interstitial lung disease using chest radiographs. , 1999, AJR. American journal of roentgenology.