CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images

BackgroundEarly and automatic detection of pulmonary nodules from CT lung screening is the prerequisite for precise management of lung cancer. However, a large number of false positives appear in order to increase the sensitivity, especially for detecting micro-nodules (diameter < 3 mm), which increases the radiologists’ workload and causes unnecessary anxiety for the patients. To decrease the false positive rate, we propose to use CNN models to discriminate between pulmonary micro-nodules and non-nodules from CT image patches.MethodsA total of 13,179 micro-nodules and 21,315 non-nodules marked by radiologists are extracted with three different patch sizes (16 × 16, 32 × 32 and 64 × 64) from LIDC/IDRI database and used in the experiments. Three CNN models with different depths (1, 2 or 4 convolutional layers) are designed; their performances are evaluated by the fivefold cross-validation in term of the accuracy, area under the curve (AUC), F-score and sensitivity. The network parameters are also optimized.ResultsIt is found that the performance of the CNN models is greatly dependent on the patches size and the number of convolutional layers. The CNN model with two convolutional layers presented the best performance in case of 32 × 32 patches size, achieving an accuracy of 88.28%, an AUC of 0.87, a F-score of 83.45% and a sensitivity of 83.82%.ConclusionsThe CNN models with appropriate depth and size of image patches can effectively discriminate between pulmonary micro-nodules and non-nodules, and reduce the false positives and help manage lung cancer precisely.

[1]  J. Austin,et al.  Guidelines for management of small pulmonary nodules detected on CT scans: a statement from the Fleischner Society. , 2005, Radiology.

[2]  T. Hara,et al.  Nodule detection in 3D chest CT images using 2nd order autocorrelation features , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[3]  E. Feuer,et al.  SEER Cancer Statistics Review, 1975-2003 , 2006 .

[4]  Ying Zhang,et al.  Boundary delineation in transrectal ultrasound image for prostate cancer , 2007, Comput. Biol. Medicine.

[5]  N. Fineberg,et al.  Follow-Up of Small (4 mm or Less) Incidentally Detected Nodules by Computed Tomography in Oncology Patients: A Retrospective Review , 2010, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[6]  Jame Abraham,et al.  Reduced lung cancer mortality with low-dose computed tomographic screening , 2011 .

[7]  C. Gatsonis,et al.  Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening , 2012 .

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Rishi Kumar,et al.  Detection of Ground Glass Nodules in Human Lungs Using Lungs CT Scans Images , 2013 .

[10]  Bram van Ginneken,et al.  Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images , 2014, Medical Image Anal..

[11]  Yelong Shen,et al.  Learning semantic representations using convolutional neural networks for web search , 2014, WWW.

[12]  Anselmo Cardoso de Paiva,et al.  Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM , 2014, Eng. Appl. Artif. Intell..

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[16]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[17]  Bram van Ginneken,et al.  Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks , 2016, IEEE Transactions on Medical Imaging.

[18]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[19]  Anselmo Cardoso de Paiva,et al.  3D shape analysis to reduce false positives for lung nodule detection systems , 2017, Medical & Biological Engineering & Computing.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jörg Denzinger,et al.  Lung nodule detection in CT images using deep convolutional neural networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[22]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[23]  Yu Wang,et al.  An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images , 2017, Journal of Medical Systems.

[24]  J Wardle,et al.  Pulmonary nodules and CT screening: the past, present and future , 2016, Thorax.

[25]  C. Bai,et al.  Evaluation of Pulmonary Nodules: Clinical Practice Consensus Guidelines for Asia. , 2016, Chest.

[26]  Hiroshi Fujita,et al.  Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique. , 2016, Medical physics.

[27]  Bin Zheng,et al.  Computer-aided detection of pulmonary nodules using dynamic self-adaptive template matching and a FLDA classifier. , 2016, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[28]  Hao Chen,et al.  Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection , 2017, IEEE Transactions on Biomedical Engineering.

[29]  Zhengrong Liang,et al.  A comparison study on the effect of false positive reduction in deep learning based detection for juxtapleural lung nodules: CNN vs DNN , 2017 .

[30]  Vivek Vaidya,et al.  Lung nodule detection in CT using 3D convolutional neural networks , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[31]  Min Chen,et al.  Detecting Small Signs from Large Images , 2017, 2017 IEEE International Conference on Information Reuse and Integration (IRI).

[32]  Dazhe Zhao,et al.  A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in Lung nodule CAD , 2017, Comput. Methods Programs Biomed..

[33]  Jianhua Li,et al.  Agile convolutional neural network for pulmonary nodule classification using CT images , 2018, International Journal of Computer Assisted Radiology and Surgery.

[34]  Amr Badr,et al.  Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN) , 2017 .

[35]  Nima Tajbakhsh,et al.  Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANNs vs. CNNs , 2017, Pattern Recognit..

[36]  Wei Li,et al.  A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules , 2017, Pattern Recognit..

[37]  Wenqing Sun,et al.  Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis , 2017, Comput. Biol. Medicine.

[38]  M. Azharuddin,et al.  Evaluating pulmonary nodules to detect lung cancer: Does Fleischner criteria really work? , 2017 .

[39]  He Ma,et al.  An Automatic Detection System of Lung Nodule Based on Multigroup Patch-Based Deep Learning Network , 2018, IEEE Journal of Biomedical and Health Informatics.

[40]  Yannick Le Moullec,et al.  Automatic detection of multisize pulmonary nodules in CT images: Large‐scale validation of the false‐positive reduction step , 2018, Medical physics.

[41]  Lanfen Lin,et al.  A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection. , 2018, Medical physics.

[42]  Yun Shi,et al.  3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images , 2018, Remote. Sens..