Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography.

In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765 sections), which contained 71 confirmed nodules including 66 biopsy-confirmed primary cancers, from a lung cancer screening program. The Multi-MTANN was applied to 58 true positives (nodules from 54 patients) and 1726 false positives (non-nodules) reported by our current scheme in a validation test; these were different from the training set. The results indicated that 83% (1424/1726) of non-nodules were removed with a reduction of one true positive (nodule), i.e., a classification sensitivity of 98.3% (57 of 58 nodules). By using the Multi-MTANN, the false-positive rate of our current scheme was improved from 0.98 to 0.18 false positives per section (from 27.4 to 4.8 per patient) at an overall sensitivity of 80.3% (57/71).

[1]  E. W. Shrigley.  Medical Physics , 1944, British medical journal.

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

[3]  B J Flehinger,et al.  Non-small-cell lung cancer: results of the New York screening program. , 1984, Radiology.

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

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

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

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

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

[9]  Kaoru Arakawa,et al.  A nonlinear digital filter using multi-layered neural networks , 1990, IEEE International Conference on Communications, Including Supercomm Technical Sessions.

[10]  D. Chakraborty,et al.  Free-response methodology: alternate analysis and a new observer-performance experiment. , 1990, Radiology.

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

[12]  Jaakko Astola,et al.  A new class of nonlinear filters-neural filters , 1993, IEEE Trans. Signal Process..

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

[14]  Shinji Yamamoto,et al.  Image processing for computer-aided diagnosis of lung cancer by CT (LSCT) , 1994, Systems and Computers in Japan.

[15]  Jaakko Astola,et al.  Adaptive multistage weighted order statistic filters based on the backpropagation algorithm , 1994, IEEE Trans. Signal Process..

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

[17]  Noboru Niki,et al.  Computer Assisted Lung Cancer Diagnosis Based on Helical Images , 1995, ICSC.

[18]  Nirwan Ansari,et al.  Speeding up the generalized adaptive neural filters , 1996, IEEE Trans. Image Process..

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

[20]  H. Ohmatsu,et al.  Peripheral lung cancer: screening and detection with low-dose spiral CT versus radiography. , 1996, Radiology.

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

[22]  N. Sugie,et al.  A Recurrent Neural Filter for Reducing Noise in Medical X-Ray Image Sequences , 1998, ICONIP.

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

[24]  Shinji Yamamoto,et al.  Image processing for computer-aided diagnosis of lung cancer screening system by CT (LSCT) , 1998, Medical Imaging.

[25]  Kenji Suzuki,et al.  Designing the optimal structure of a neural filter , 1998, Neural Networks for Signal Processing VIII. Proceedings of the 1998 IEEE Signal Processing Society Workshop (Cat. No.98TH8378).

[26]  S. Armato,et al.  Computerized detection of pulmonary nodules on CT scans. , 1999, Radiographics : a review publication of the Radiological Society of North America, Inc.

[27]  Kunio Doi,et al.  Three-dimensional approach to lung nodule detection in helical CT , 1999, Medical Imaging.

[28]  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).

[29]  O. Miettinen,et al.  Early Lung Cancer Action Project: overall design and findings from baseline screening , 1999, The Lancet.

[30]  Heber MacMahon,et al.  Analysis of a three-dimensional lung nodule detection method for thoracic CT scans , 2000, Medical Imaging: Image Processing.

[31]  Kenji Suzuki,et al.  Training under achievement quotient criterion , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[32]  Kenji Suzuki,et al.  Edge detection from noisy images using a neural edge detector , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[33]  S. Sone,et al.  Results of three-year mass screening programme for lung cancer using mobile low-dose spiral computed tomography scanner , 2001, British Journal of Cancer.

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

[35]  Kenji Suzuki,et al.  Computer-aided diagnosis system for coronary artery stenosis using a neural network , 2001, SPIE Medical Imaging.

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

[37]  Kenji Suzuki,et al.  Neural Edge Detector - A Good Mimic of Conventional One Yet Robuster against Noise , 2001, IWANN.

[38]  Kenji Suzuki,et al.  Extraction of the contours of left ventricular cavity according with those traced by medical doctors from left ventriculograms using a neural edge detector , 2001, SPIE Medical Imaging.

[39]  Kenji Suzuki,et al.  Simple unit-pruning with gain-changing training , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

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

[41]  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.

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

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

[44]  Ahmedin Jemal,et al.  Cancer Statistics, 2002 , 2002, CA: a cancer journal for clinicians.

[45]  Kenji Suzuki,et al.  Contour extraction of left ventricular cavity from digital subtraction angiograms using a neural edge detector , 2003, Systems and Computers in Japan.

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