Using 3D Convolutional Networks with Shortcut Connections for Improved Lung Nodules Classification

Lung cancer is the leading cause of cancer-related death worldwide. Due to the difficulty of artificial extraction of medical image features and the development of artificial intelligence in the field of medical image, various deep learning methods for lung nodules classification have been proposed to help doctors diagnose and detect lung cancer in the early stage. The traditional 2D CNN cannot make use of the 3D spatial characteristics of CT data, while the 3D CNN has many parameters, which leads to low model efficiency. Residual Network (ResNet) is a residual structure using skip connection that makes deep classification network easier to train. Therefore, motivated by the work of 3D CNN and ResNet, in this paper, a VGG based 3D residual connection network, called VGG+ResCon, is proposed to mine the vertical information of tumor CT images and accelerate the training efficiency of the model. Besides, after enhancing the dataset, focal loss is used to replace the traditional cross-entropy as the loss function, which solves the problem of uneven distribution of positive and negative samples of medical data (more negative samples than positive samples). And it also makes the model more focused on difficult-to-classify samples. This methodology was evaluated on the LUng Nodule Analysis 2016 (LUNA16) dataset, with the best precision of 93.62%, recall of 92.48%, specificity of 96.83% and f1-score of 93.04%. Experimental results demonstrate the effectiveness of the proposed method in classifying malignant and benign pulmonary nodules.

[1]  Ghassan Hamarneh,et al.  Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers , 2016, MLMI@MICCAI.

[2]  Lin Wu,et al.  Deep Instance-Level Hard Negative Mining Model for Histopathology Images , 2019, MICCAI.

[3]  Taro Tezuka,et al.  Classification of Lung Nodules Using Deep Learning , 2017 .

[4]  Masayuki Mukunoki,et al.  Combined Object Detection and Segmentation , 2013 .

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

[6]  Wei Shen,et al.  Multi-scale Convolutional Neural Networks for Lung Nodule Classification , 2015, IPMI.

[7]  Wen-Huang Cheng,et al.  Computer-aided classification of lung nodules on computed tomography images via deep learning technique , 2015, OncoTargets and therapy.

[8]  Qaisar Abbas,et al.  Lung-Deep: A Computerized Tool for Detection of Lung Nodule Patterns using Deep Learning Algorithms Detection of Lung Nodules Patterns , 2017 .

[9]  Naif Alajlan,et al.  Dense Convolutional Networks With Focal Loss and Image Generation for Electrocardiogram Classification , 2019, IEEE Access.

[10]  Qingmao Hu,et al.  Lung nodule classification using deep feature fusion in chest radiography , 2017, Comput. Medical Imaging Graph..

[11]  Catalin I. Fetita,et al.  Increasing CAD system efficacy for lung texture analysis using a convolutional network , 2016, SPIE Medical Imaging.

[12]  Michael Brudno,et al.  Size and Texture-Based Classification of Lung Tumors with 3D CNNs , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[13]  Alexander Wong,et al.  Lung Nodule Classification Using Deep Features in CT Images , 2015, 2015 12th Conference on Computer and Robot Vision.

[14]  Wei Shen,et al.  Learning from Experts: Developing Transferable Deep Features for Patient-Level Lung Cancer Prediction , 2016, MICCAI.

[15]  Nassir Navab,et al.  GANs for Medical Image Analysis , 2018, Artif. Intell. Medicine.

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

[17]  Julien Cohen-Adad,et al.  Grey Matter Segmentation in Spinal Cord MRIs via 3D Convolutional Encoder Networks with Shortcut Connections , 2017, DLMIA/ML-CDS@MICCAI.

[18]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[19]  Qi Dou.  Multi-level Contextual 3D CNNs for False Positive Reduction in Pulmonary Nodule Detection , 2017 .

[20]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Sreedhar Kollem,et al.  A Review of Image Denoising and Segmentation Methods Based on Medical Images , 2019, International Journal of Machine Learning and Computing.

[23]  Lei Zhang,et al.  Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Hui Chen,et al.  Classification of Pulmonary Nodules Using Neural Network Ensemble , 2011, ISNN.

[25]  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.

[26]  Yaozong Gao,et al.  Estimating CT Image from MRI Data Using 3D Fully Convolutional Networks , 2016, LABELS/DLMIA@MICCAI.

[27]  Xiaohui Xie,et al.  DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification , 2017, bioRxiv.

[28]  Sheila Ramaswamy,et al.  Pulmonary Nodule Classification with Convolutional Neural Networks , 2016 .

[29]  Murat Cakiroglu,et al.  Artificial neural network-based classification system for lung nodules on computed tomography scans , 2014, 2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[30]  Wei Shen,et al.  Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification , 2017, Pattern Recognit..