Improving Prognostic Value of CT Deep Radiomic Features in Pancreatic Ductal Adenocarcinoma Using Transfer Learning

Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive cancers with an extremely poor prognosis. Radiomics has shown prognostic ability in multiple types of cancer including PDAC. However, the prognostic value of traditional radiomics pipelines, which are based on hand-crafted radiomic features alone, is limited due to multicollinearity of features and multiple testing problem, and limited performance of conventional machine learning classifiers. Deep learning architectures, such as convolutional neural networks (CNNs), have been shown to outperform traditional techniques in computer vision tasks, such as object detection. However, they require large sample sizes for training which limits their development. As an alternative solution, CNN-based transfer learning has shown the potential for achieving reasonable performance using datasets with small sample sizes. In this work, we developed a CNN-based transfer learning approach for prognostication in PDAC patients for overall survival. The results showed that transfer learning approach outperformed the traditional radiomics model on PDAC data. A transfer learning approach may fill the gap between radiomics and deep learning analytics for cancer prognosis and improve performance beyond what CNNs can achieve using small datasets.

[1]  Geraint Rees,et al.  Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy , 2018, ArXiv.

[2]  M. Falasca,et al.  Pancreatic Ductal Adenocarcinoma: Current and Evolving Therapies , 2017, International journal of molecular sciences.

[3]  X Li,et al.  SU-D-207B-07: Development of a CT-Radiomics Based Early Response Prediction Model During Delivery of Chemoradiation Therapy for Pancreatic Cancer. , 2016, Medical physics.

[4]  A. Eibl Pancreatic ductal adenocarcinoma , 2015, Radiopaedia.org.

[5]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[6]  Andre Dekker,et al.  Radiomics: the process and the challenges. , 2012, Magnetic resonance imaging.

[7]  Samprit Chatterjee,et al.  A Nonparametric Approach to Credit Screening , 1970 .

[8]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[9]  Yan Liu,et al.  A new method of feature fusion and its application in image recognition , 2005, Pattern Recognit..

[10]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Yong Man Ro,et al.  Modality-bridge transfer learning for medical image classification , 2017, 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[12]  Jia Deng,et al.  A large-scale hierarchical image database , 2009, CVPR 2009.

[13]  H. Blum,et al.  Current and evolving therapies for hepatitis C. , 1999, European journal of gastroenterology & hepatology.

[14]  Thomas Lengauer,et al.  Classification with correlated features: unreliability of feature ranking and solutions , 2011, Bioinform..

[15]  Sukhendu Das,et al.  A Survey of Decision Fusion and Feature Fusion Strategies for Pattern Classification , 2010, IETE Technical Review.

[16]  Mari Mino-Kenudson,et al.  Pancreatic ductal adenocarcinoma: long-term survival does not equal cure. , 2012, Surgery.

[17]  Yanqi Huang,et al.  Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer. , 2016, Radiology.

[18]  Masoom A. Haider,et al.  Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer , 2017, Scientific Reports.

[19]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

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

[21]  Masoom A. Haider,et al.  A Local ROI-specific Atlas-based Segmentation of Prostate Gland and Transitional Zone in Diffusion MRI , 2016 .

[22]  E. Rosato,et al.  Long term survival after pancreatic resection for pancreatic adenocarcinoma , 2000, American Journal of Gastroenterology.

[23]  Uri Shaham,et al.  DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network , 2016, BMC Medical Research Methodology.

[24]  Benjamin Haibe-Kains,et al.  Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer , 2015, Scientific Reports.

[25]  Ricardo de Lima Thomaz,et al.  Feature extraction using convolutional neural network for classifying breast density in mammographic images , 2017, Medical Imaging.

[26]  M. Haider,et al.  CT texture analysis: a potential tool for prediction of survival in patients with metastatic clear cell carcinoma treated with sunitinib , 2017, Cancer Imaging.

[27]  Thomas Martinetz,et al.  Deep convolutional neural networks as generic feature extractors , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[28]  Vishwa Parekh,et al.  Radiomics: a new application from established techniques , 2016, Expert review of precision medicine and drug development.

[29]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[30]  Farzad Khalvati,et al.  Prognostic Value of CT Radiomic Features in Resectable Pancreatic Ductal Adenocarcinoma , 2019, Scientific Reports.

[31]  Geraint Rees,et al.  Clinically applicable deep learning for diagnosis and referral in retinal disease , 2018, Nature Medicine.

[32]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[33]  Hariharan Ravishankar,et al.  Understanding the Mechanisms of Deep Transfer Learning for Medical Images , 2016, LABELS/DLMIA@MICCAI.

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

[35]  Masoom A. Haider,et al.  CT texture features are associated with overall survival in pancreatic ductal adenocarcinoma – a quantitative analysis , 2017, BMC Medical Imaging.

[36]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.