A deep CNN based transfer learning method for false positive reduction

A low false positive (FP) rate is of great importance for the use of a Computer Aided Detection (CAD) system to detect pulmonary nodules in thoracic Computed Tomography (CT). However, due to the variations of nodules in appear and size, it is still a very challenging task to obtain a low FP rate. In this paper, we propose a deep Convolutional Neural Network (CNN) based transfer learning method for FP reduction in pulmonary nodule detection on CT slices. We utilized one of the state-of-the-art CNN models, VGG-16 [4], as a feature extractor to obtain nodule features, and used a support vector machine (SVM) for nodule classification. Firstly we transferred all the layers from a pre-trained VGG-16 model in ImageNet to our target networks. Then, we tuned the last fully connected layers to adjust the computer-vision-task-trained CNN model to pulmonary nodule classification task. The initial CNN filter weights were then optimized using the training data, i.e., the pulmonary nodule patch images and corresponding labels through back-propagation so that they better reflected the modalities in the pulmonary nodule image dataset. Finally, features learned in the fine-tuned CNN were used to train a SVM classifier. The output of the trained SVM was used for final classification. Experimental results show that the overall sensitivity of the proposed method was 87.2% with 0.39 FPs per scan, which is higher than 85.4% with 4 FPs per scan obtained by other state of art method.

[1]  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.

[2]  K. Doi,et al.  Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization. , 2005, Radiology.

[3]  Lauge Sørensen,et al.  Quantitative Analysis of Pulmonary Emphysema Using Local Binary Patterns , 2010, IEEE Transactions on Medical Imaging.

[4]  Aly A. Farag,et al.  Evaluation of geometric feature descriptors for detection and classification of lung nodules in low dose CT scans of the chest , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[5]  S. Mukhopadhyay,et al.  Computer-aided Detection and Analysis of Pulmonary Nodule from CT Images: A Survey , 2012 .

[6]  Kenji Suzuki,et al.  Pixel-Based Machine Learning in Medical Imaging , 2012, Int. J. Biomed. Imaging.

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

[8]  Nasir M. Rajpoot,et al.  A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[9]  C. Chandrasekar,et al.  Lung Nodule Detection Using Fuzzy Clustering and Support Vector Machines , 2013 .

[10]  Niccolo Camarlinghi,et al.  Automatic detection of lung nodules in computed tomography images: training and validation of algorithms using public research databases , 2013, The European Physical Journal Plus.

[11]  David Dagan Feng,et al.  Feature-Based Image Patch Approximation for Lung Tissue Classification , 2013, IEEE Transactions on Medical Imaging.

[12]  Kenji Suzuki,et al.  Machine Learning in Computer-Aided Diagnosis of the Thorax and Colon in CT: A Survey , 2013, IEICE Trans. Inf. Syst..

[13]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Lan Chen,et al.  Semantic enhanced cloud environment for surveillance data management using video structural description , 2014, Computing.

[15]  Ronald M. Summers,et al.  A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations , 2014, MICCAI.

[16]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[17]  Nima Tajbakhsh,et al.  Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[18]  Dorin Comaniciu,et al.  3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data , 2015, MICCAI.

[19]  Nima Tajbakhsh,et al.  Computer-Aided Pulmonary Embolism Detection Using a Novel Vessel-Aligned Multi-planar Image Representation and Convolutional Neural Networks , 2015, MICCAI.

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

[21]  Nima Tajbakhsh,et al.  A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos , 2015, IPMI.

[22]  Lin Lu,et al.  Hybrid detection of lung nodules on CT scan images. , 2015, Medical physics.

[23]  Hayit Greenspan,et al.  Deep learning with non-medical training used for chest pathology identification , 2015, Medical Imaging.

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

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

[26]  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.

[27]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[29]  João Manuel R. S. Tavares,et al.  Automatic 3D pulmonary nodule detection in CT images: A survey , 2016, Comput. Methods Programs Biomed..

[30]  D. Xu,et al.  Low-Dose CT Screening for Lung Cancer: Computer-aided Detection of Missed Lung Cancers. , 2016, Radiology.

[31]  G. Saranya,et al.  Lung Nodule Classification Using Deep Features in Ct Images , 2016 .

[32]  Kenji Suzuki,et al.  Machine Learning in Medical Imaging Before and After Introduction of Deep Learning , 2017 .

[33]  Nicholas Ayache,et al.  Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[34]  Kenji Suzuki.  Survey of Deep Learning Applications to Medical Image Analysis , 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]  Kenji Suzuki,et al.  Overview of deep learning in medical imaging , 2017, Radiological Physics and Technology.

[37]  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.

[38]  David Dagan Feng,et al.  Classification of Medical Images in the Biomedical Literature by Jointly Using Deep and Handcrafted Visual Features , 2018, IEEE Journal of Biomedical and Health Informatics.

[39]  Yanning Zhang,et al.  Pulmonary nodule detection in medical images: A survey , 2018, Biomed. Signal Process. Control..

[40]  Yong Ding,et al.  Controllable keyword search scheme supporting multiple users , 2018, Future Gener. Comput. Syst..

[41]  Ronald M. Summers,et al.  Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..