How can a massive training artificial neural network (MTANN) be trained with a small number of cases in the distinction between nodules and vessels in thoracic CT?

RATIONALE AND OBJECTIVES To demonstrate that a massive training artificial neural network (MTANN) can be adequately trained with a small number of cases in the distinction between nodules and vessels (non-nodules) in thoracic computed tomography (CT) images. MATERIALS AND METHODS An MTANN is a trainable, highly nonlinear filter consisting of a linear-output multilayer artificial neural network model. For enhancement of nodules and suppression of vessels, we used 10 nodules and 10 non-nodule images as training cases for MTANNs. The MTANN is trained with a large number of input subregions selected from the training cases and the corresponding pixels in teaching images that contain Gaussian distributions for nodules and zero for non-nodules. We trained three MTANNs with different numbers (1, 9, and 361) of training samples (pairs of the subregion and the teaching pixel) selected from the training cases. In order to investigate the basic characteristics of the trained MTANNs, we applied the MTANNs to simulated CT images containing various-sized model nodules (spheres) with different contrasts and various-sized model vessels (cylinders) with different orientations. In addition, we applied the trained MTANNs to nontraining actual clinical cases with 59 nodules and 1,726 non-nodules. RESULTS In the output images for the simulated CT images by use of the MTANNs trained with small numbers (one and nine) of subregions, model vessels were clearly visible and were not removed; thus, the MTANNs were not trained properly. However, in the output image of the MTANN trained with a large number of subregions, various-sized model nodules with different contrasts were represented by light nodular distributions, whereas various-sized model vessels with different orientations were dark and thus were almost removed. This result indicates that the MTANN was able to learn, from a very small number of actual nodule and non-nodule cases, the distinction between nodules (spherelike objects) and vessels (cylinder-like objects). In nontraining clinical cases, the MTANN was able to distinguish actual nodules from actual vessels in CT images. For 59 actual nodules and 1,726 non-nodules, the performance of the MTANN decreased as the number of training samples (subregions) in each case decreased. CONCLUSIONS The MTANN can be trained with a very small number of training cases (10 nodules and 10 non-nodules) in the distinction between nodules and non-nodules (vessels) in CT images. Massive training by scanning of training cases to produce a large number of training samples (input subregions and teaching pixels) would contributed to a high generalization ability of the MTANN.

[1]  A. Jemal,et al.  Cancer Statistics, 2005 , 2005, CA: a cancer journal for clinicians.

[2]  H Rusinek,et al.  Pulmonary nodule detection: low-dose versus conventional CT. , 1998, Radiology.

[3]  S. Swensen,et al.  CT screening for lung cancer. , 2002, Seminars in roentgenology.

[4]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[5]  S. Armato,et al.  Automated detection of lung nodules in CT scans: preliminary results. , 2001, Medical physics.

[6]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[7]  K. Doi,et al.  Computerized scheme for automated detection of lung nodules in low-dose computed tomography images for lung cancer screening. , 2004, Academic radiology.

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

[9]  Michael F. McNitt-Gray,et al.  Patient-specific models for lung nodule detection and surveillance in CT images , 2001, IEEE Transactions on Medical Imaging.

[10]  Kenji Suzuki,et al.  Neural Edge Enhancer for Supervised Edge Enhancement from Noisy Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

[12]  M. Giger,et al.  Computerized Detection of Pulmonary Nodules in Computed Tomography Images , 1994, Investigative radiology.

[13]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

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

[15]  Kenji Suzuki,et al.  A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis , 2001, Neural Processing Letters.

[16]  R. F. Wagner,et al.  Classifier design for computer-aided diagnosis: effects of finite sample size on the mean performance of classical and neural network classifiers. , 1999, Medical physics.

[17]  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.

[18]  Berkman Sahiner,et al.  Lung nodule detection on thoracic computed tomography images: preliminary evaluation of a computer-aided diagnosis system. , 2002, Medical physics.

[19]  Kunio Doi,et al.  Effect of a small number of training cases on the performance of massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose CT , 2003, SPIE Medical Imaging.

[20]  Kenji Suzuki,et al.  Recognition of Coronary Arterial Stenosis Using Neural Network on DSA System , 1995, Systems and Computers in Japan.

[21]  Margrit Betke,et al.  Chest CT: automated nodule detection and assessment of change over time--preliminary experience. , 2001, Radiology.

[22]  Hiroshi Fujita,et al.  Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique , 2001, IEEE Transactions on Medical Imaging.

[23]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[24]  K Doi,et al.  Analysis of methods for reducing false positives in the automated detection of clustered microcalcifications in mammograms. , 1998, Medical physics.

[25]  M. Kallergi.  Computer-aided diagnosis of mammographic microcalcification clusters. , 2004, Medical physics.

[26]  OS Miettinen,et al.  Early Lung Cancer Action Project , 1999, The Lancet.

[27]  Isao Horiba,et al.  Efficient approximation of a neural filter for quantum noise removal in X-ray images , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[28]  K. Doi,et al.  False-positive reduction in computer-aided diagnostic scheme for detecting nodules in chest radiographs by means of massive training artificial neural network. , 2005, Academic radiology.

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

[30]  Kunio Doi,et al.  Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network , 2005, IEEE Transactions on Medical Imaging.

[31]  M. Giger,et al.  Malignant and benign clustered microcalcifications: automated feature analysis and classification. , 1996, Radiology.

[32]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[33]  S. Armato,et al.  Lung cancer: performance of automated lung nodule detection applied to cancers missed in a CT screening program. , 2002, Radiology.

[34]  S. Swensen,et al.  Lung cancer screening with CT: Mayo Clinic experience. , 2003, Radiology.

[35]  C. Henschke.  Early lung cancer action project , 2000, Cancer.

[36]  Ken-ichi Suzuki,et al.  Neural Filter with Selection of Input Features and Its Application to Image Quality Improvement of Medical Image Sequences , 2002 .

[37]  Kenji Suzuki,et al.  Extraction of left ventricular contours from left ventriculograms by means of a neural edge detector , 2004, IEEE Transactions on Medical Imaging.

[38]  Lubomir M. Hadjiiski,et al.  Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size. , 2000, Medical physics.

[39]  Geoffrey E. Hinton,et al.  Learning representations of back-propagation errors , 1986 .

[40]  J. Gurney,et al.  Missed lung cancer at CT: imaging findings in nine patients. , 1996, Radiology.

[41]  Kenji Suzuki,et al.  Efficient approximation of neural filters for removing quantum noise from images , 2002, IEEE Trans. Signal Process..

[42]  K L Lam,et al.  Computerized classification of malignant and benign microcalcifications on mammograms: texture analysis using an artificial neural network. , 1997, Physics in medicine and biology.

[43]  Feng Li,et al.  Mass screening for lung cancer with mobile spiral computed tomography scanner , 1998, The Lancet.

[44]  S. Armato,et al.  Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. , 2003, Medical physics.

[45]  O. Miettinen,et al.  CT screening for lung cancer: suspiciousness of nodules according to size on baseline scans. , 2004, Radiology.

[46]  Kenji Suzuki,et al.  Determining the receptive field of a neural filter , 2004, Journal of neural engineering.

[47]  S. Armato,et al.  Lung cancers missed at low-dose helical CT screening in a general population: comparison of clinical, histopathologic, and imaging findings. , 2002, Radiology.

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

[49]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.