Transfer Learning of Pre- Trained Inception-V3 Model for Colorectal Cancer Lymph Node Metastasis Classification

Colorectal cancer (CRC) lymph node (LN) metastasis is a critical index for CRC pathological staging. Surgeons determine the treatment plan based on magnetic resonance imaging (MRI) of CRC LN. However, current methods need to manually extract features, the accuracy depends on the feature extraction. In the paper, we present a method which use pre-train Inception-v3 model to classify CRC LN, the model could automatically extract feature from MRI of CRC LN. Experiments verified the performance of the model. A high classification accuracy is obtained, which is better than the results in the previous studies. The results suggest that the method can improve the accuracy of classification of CRC LN.

[1]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[2]  Geerard L Beets,et al.  Rectal cancer: review with emphasis on MR imaging. , 2004, Radiology.

[3]  J. Jass.  Classification of colorectal cancer based on correlation of clinical, morphological and molecular features , 2007, Histopathology.

[4]  Q. Chan,et al.  Quantitative Assessment of Diffusion-Weighted MR Imaging in Patients with Primary Rectal Cancer: Correlation with FDG-PET/CT , 2010, Molecular Imaging and Biology.

[5]  V. Khoo,et al.  The utility of multimodality imaging with CT and MRI in defining rectal tumour volumes for radiotherapy treatment planning: a pilot study , 2010, Journal of medical imaging and radiation oncology.

[6]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[7]  C. Mathers,et al.  Estimates of worldwide burden of cancer in 2008: GLOBOCAN 2008 , 2010, International journal of cancer.

[8]  L. Guerra,et al.  Response to neoadjuvant therapy in locally advanced rectal cancer: assessment with diffusion-weighted MR imaging and 18FDG PET/CT , 2012, Abdominal Imaging.

[9]  Philippe Lambin,et al.  FDG-PET provides the best correlation with the tumor specimen compared to MRI and CT in rectal cancer. , 2011, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[10]  T. Leiner,et al.  Accuracy of Gadofosveset-enhanced MRI for Nodal Staging and Restaging in Rectal Cancer , 2011, Annals of surgery.

[11]  J. Skibber,et al.  Pretreatment High-Resolution Rectal MRI and Treatment Response to Neoadjuvant Chemoradiation , 2012, Diseases of the colon and rectum.

[12]  H. Ueno,et al.  Optimal colorectal cancer staging criteria in TNM classification. , 2012, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[13]  C. Mathers,et al.  GLOBOCAN 2012 v1.0, Cancer Incidence and Mortality Worldwide: IARC CancerBase No. 11 [Internet]. Lyon, France: International Agency for Research on Cancer , 2013 .

[14]  G. Poston,et al.  TNM staging of colorectal cancer should be reconsidered by T stage weighting. , 2014, World journal of gastroenterology.

[15]  G. Choi,et al.  Accuracy of Preoperative MRI in Predicting Pathology Stage in Rectal Cancers: Node-for-Node Matched Histopathology Validation of MRI Features , 2014, Diseases of the colon and rectum.

[16]  A. Rogers,et al.  Multicenter Evaluation of Rectal cancer ReImaging pOst Neoadjuvant (MERRION) Therapy , 2014, Annals of surgery.

[17]  Songhua Zhan,et al.  Prediction of Nodal Involvement in Primary Rectal Carcinoma without Invasion to Pelvic Structures: Accuracy of Preoperative CT, MR, and DWIBS Assessments Relative to Histopathologic Findings , 2014, PloS one.

[18]  M Partridge,et al.  Effect on therapeutic ratio of planning a boosted radiotherapy dose to the dominant intraprostatic tumour lesion within the prostate based on multifunctional MR parameters. , 2014, The British journal of radiology.

[19]  L. Giovanella,et al.  Diagnostic Performance of Positron Emission Tomography/Computed Tomography Using Fluorine-18 Fluorodeoxyglucose in Detecting Locoregional Nodal Involvement in Patients with Anal Canal Cancer: A Systematic Review and Meta-Analysis , 2014, TheScientificWorldJournal.

[20]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

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

[22]  Satoshi Suzuki,et al.  A Transfer Learning Method with Deep Convolutional Neural Network for Diffuse Lung Disease Classification , 2015, ICONIP.

[23]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

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

[25]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[26]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[28]  David Dagan Feng,et al.  Transfer learning of a convolutional neural network for HEp-2 cell image classification , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[29]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[30]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[31]  Kenichi Sugihara,et al.  Prediction of lateral pelvic lymph node metastasis from lower rectal cancer using magnetic resonance imaging and risk factors for metastasis: Multicenter study of the Lymph Node Committee of the Japanese Society for Cancer of the Colon and Rectum , 2017, International Journal of Colorectal Disease.

[32]  Wenming Cao,et al.  Liver Fibrosis Classification Based on Transfer Learning and FCNet for Ultrasound Images , 2017, IEEE Access.

[33]  L. Zhou,et al.  Correlation analysis of MR/CT on colorectal cancer lymph node metastasis characteristics and prognosis. , 2017, European review for medical and pharmacological sciences.

[34]  Ling Ma,et al.  Deep learning based classification for head and neck cancer detection with hyperspectral imaging in an animal model , 2017, Medical Imaging.

[35]  Xiaoling Xia,et al.  Inception-v3 for flower classification , 2017, 2017 2nd International Conference on Image, Vision and Computing (ICIVC).

[36]  Amit Sethi,et al.  Classification of Breast Cancer Histology using Deep Learning , 2018, ICIAR.

[37]  Hiroshi Inoue,et al.  Data Augmentation by Pairing Samples for Images Classification , 2018, ArXiv.

[38]  Dmitrii Bychkov,et al.  Deep learning based tissue analysis predicts outcome in colorectal cancer , 2018, Scientific Reports.

[39]  Yan Cui,et al.  Transfer Learning for Molecular Cancer Classification Using Deep Neural Networks , 2019, IEEE/ACM Transactions on Computational Biology and Bioinformatics.