Mediastinal lymph node malignancy detection in computed tomography images using fully convolutional network

Abstract Differential diagnosis of malignant and benign mediastinal lymph nodes (LNs) through invasive pathological tests is a complex and painful procedure because of sophisticated anatomical locations of LNs in the chest. The image based automatic machine learning techniques have been attempted in the past for malignancy detection. But these conventional methods suffer from complex selection of hand-crafted features and trade-off between performance parameters due to them. Today deep learning approaches are outperforming conventional machine learning techniques and able to overcome these issues. However, the existing convolutional neural network (CNN) based models also are prone to overfitting because of fully connected (FC) layers. Therefore, in this paper authors have proposed a fully convolutional network (FCN) based deep learning model for lymph nodes malignancy detection in computed tomography (CT) images. Moreover, the proposed FCN has been customized with batch normalization and advanced activation function Leaky ReLU to accelerate the training and to overcome the problem of dying ReLU, respectively. The performance of the proposed FCN has been also tuned to its best for smaller data size using data augmentation methods. The generalization of the proposed model is tested using the network parameter variation. To understand the reliability of the proposed model, it has also been compared with state-of-art related deep learning networks. The proposed FCN model has achieved an average accuracy, sensitivity, specificity, and area under curve as 90.28%, 90.63%, 89.95%, and 0.90, respectively. Our results also confirms the successful usabilility of augmentation methods for working on smaller datasets and deep learning approaches.

[1]  Yoshua Bengio,et al.  Object Recognition with Gradient-Based Learning , 1999, Shape, Contour and Grouping in Computer Vision.

[2]  Kyoungjune Pak,et al.  A decision tree model for predicting mediastinal lymph node metastasis in non-small cell lung cancer with F-18 FDG PET/CT , 2018, PloS one.

[3]  Douglas C McCrory,et al.  Invasive staging of non-small cell lung cancer: a review of the current evidence. , 2003, Chest.

[4]  Tuan D. Pham,et al.  Complementary features for radiomic analysis of malignant and benign mediastinal lymph nodes , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[5]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[6]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[7]  Chengzhu Yu,et al.  The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[8]  Zhonghua Chen,et al.  Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images , 2017, EJNMMI Research.

[9]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[11]  T. Pham,et al.  Texture Analysis and Synthesis of Malignant and Benign Mediastinal Lymph Nodes in Patients with Lung Cancer on Computed Tomography , 2017, Scientific Reports.

[12]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[13]  Ronald M. Summers,et al.  Detection and station mapping of mediastinal lymph nodes on thoracic computed tomography using spatial prior from multi-atlas label fusion , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[14]  B. Tong,et al.  Computed tomography screening for lung cancer: where are we now? , 2013, North Carolina medical journal.

[15]  Kenneth O. Stanley,et al.  Revising the evolutionary computation abstraction: minimal criteria novelty search , 2010, GECCO '10.

[16]  Balaji Ganeshan,et al.  CT texture analysis can help differentiate between malignant and benign lymph nodes in the mediastinum in patients suspected for lung cancer , 2016, Acta radiologica.

[17]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[18]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[19]  Daniel L. Rubin,et al.  Differential Data Augmentation Techniques for Medical Imaging Classification Tasks , 2017, AMIA.

[20]  Dorin Comaniciu,et al.  Lymph Node Detection and Segmentation in Chest Ct Data Using Discriminative Learning and a Spatial Prior , 2022 .

[21]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

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

[23]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  J. Sleeman The lymph node as a bridgehead in the metastatic dissemination of tumors. , 2000, Recent results in cancer research. Fortschritte der Krebsforschung. Progres dans les recherches sur le cancer.

[25]  Rodney W. Johnson,et al.  Comments on and correction to 'Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy' (Jan 80 26-37) , 1983, IEEE Trans. Inf. Theory.

[26]  Patrick M. Pilarski,et al.  First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning , 2014 .

[27]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[28]  R. Thornhill,et al.  Quantitative CT texture and shape analysis: Can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer? , 2015, European Radiology.

[29]  V. Raina,et al.  Lung cancer: Prevalent trends & emerging concepts , 2015, The Indian journal of medical research.

[30]  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.

[31]  Martin J. Wainwright,et al.  Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions , 2011, ICML.

[32]  Shrish Verma,et al.  Severity Assessment of Lymph Nodes in CT Images using Deep Learning Paradigm , 2018, 2018 Second International Conference on Computing Methodologies and Communication (ICCMC).

[33]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[34]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

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

[36]  W. Wong,et al.  The calculation of posterior distributions by data augmentation , 1987 .

[37]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[38]  Michael Detmar,et al.  Mechanisms of lymphatic metastasis. , 2014, The Journal of clinical investigation.

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

[40]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[41]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[42]  Synho Do,et al.  How much data is needed to train a medical image deep learning system to achieve necessary high accuracy , 2015, 1511.06348.

[43]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.