An independent evaluation of a new method for automated interpretation of lung scintigrams using artificial neural networks

Abstract. The purpose of this study was to evaluate a new automated method for the interpretation of lung perfusion scintigrams using patients from a hospital other than that where the method was developed, and then to compare the performance of the technique against that of experienced physicians. A total of 1,087 scintigrams from patients with suspected pulmonary embolism comprised the training group. The test group consisted of scintigrams from 140 patients collected in a hospital different to that from which the training group had been drawn. An artificial neural network was trained using 18 automatically obtained features from each set of perfusion scintigrams. The image processing techniques included alignment to templates, construction of quotient images based on the perfusion/template images, and finally calculation of features describing segmental perfusion defects in the quotient images. The templates represented lungs of normal size and shape without any pathological changes. The performance of the neural network was compared with that of three experienced physicians who read the same test scintigrams according to the modified PIOPED criteria using, in addition to perfusion images, ventilation images when available and chest radiographs for all patients. Performances were measured as area under the receiver operating characteristic curve. The performance of the neural network evaluated in the test group was 0.88 (95% confidence limits 0.81–0.94). The performance of the three experienced experts was in the range 0.87–0.93 when using the perfusion images, chest radiographs and ventilation images when available. Perfusion scintigrams can be interpreted regarding the diagnosis of pulmonary embolism by the use of an automated method also in a hospital other than that where it was developed. The performance of this method is similar to that of experienced physicians even though the physicians, in addition to perfusion images, also had access to ventilation images for most patients and chest radiographs for all patients. These results show the high potential for the method as a clinical decision support system.

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

[2]  A. Alavi,et al.  Lung scanning in the diagnosis of pulmonary embolism: the emperor redressed. , 1991, Seminars in nuclear medicine.

[3]  P E Christian,et al.  Image analysis and categorization of ventilation-perfusion scans for the diagnosis of pulmonary embolism using an expert system. , 1994, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[4]  Georgia D. Tourassi,et al.  Artificial neural network for diagnosis of acute pulmonary embolism: Effect of case and observer selection , 1995 .

[5]  Anders Heyden,et al.  Automated interpretation of ventilation-perfusion lung scintigrams for the diagnosis of pulmonary embolism using artificial neural networks , 2000, European Journal of Nuclear Medicine.

[6]  A. Alavi,et al.  Value of ventilation/perfusion scans versus perfusion scans alone in acute pulmonary embolism. , 1992, The American journal of cardiology.

[7]  L Edenbrandt,et al.  Improved classifications of myocardial bull's-eye scintigrams with computer-based decision support system. , 1999, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[8]  M. Rubenfire,et al.  Neural network in the clinical diagnosis of acute pulmonary embolism. , 1993, Chest.

[9]  Kevin W. Bowyer,et al.  Generating ROC curves for artificial neural networks , 1994, IEEE Transactions on Medical Imaging.

[10]  C. Floyd,et al.  Acute pulmonary embolism: artificial neural network approach for diagnosis. , 1993, Radiology.

[11]  Thorsteinn S. Rögnvaldsson,et al.  JETNET 3.0—A versatile artificial neural network package , 1994 .

[12]  J A Scott,et al.  Do diagnostic algorithms always produce a uniform lung scan interpretation? , 1993, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[13]  J. Scott,et al.  Neural network analysis of ventilation-perfusion lung scans. , 1993, Radiology.

[14]  Charles H. Mandell,et al.  Scintillation camera lung imaging: An anatomic atlas and guide , 1976 .

[15]  H. Sostman,et al.  Value of perfusion lung scan in the diagnosis of pulmonary embolism: results of the Prospective Investigative Study of Acute Pulmonary Embolism Diagnosis (PISA-PED). , 1996, American journal of respiratory and critical care medicine.

[16]  K. Mare,et al.  Observer agreement and accuracy for lung scintigraphy: A comparison with pulmonary angiography , 1997, Nuclear medicine communications.

[17]  J. Scott,et al.  Neural networks in ventilation-perfusion imaging. Part II. Effects of interpretive variability. , 1996, Radiology.

[18]  D. Chen,et al.  Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. , 1999, Radiology.

[19]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[20]  B. Efron.  Computers and the Theory of Statistics: Thinking the Unthinkable , 1979 .

[21]  J. Scott,et al.  Using artificial neural network analysis of global ventilation-perfusion scan morphometry as a diagnostic tool. , 1999, AJR. American journal of roentgenology.