Machine Learning algorithm development for lung cancer subtype identification and survival prediction
Survival analysis is related to death in biological organisms and failure in mechanical systems. In survival analysis, cox proportional hazards model is one of the most commonly used multivariate approaches to analyze the survival time data in medical research. It is a semi-parametric method that does not need a specific baseline hazard function and has the capability to effectively handle censoring problem. In our project, a Cox proportional hazards model based on important features is fitted by component-wise likelihood based boosting. Significant image markers can be discovered using the bootstrap analysis and the survival prediction performance of the model will be evaluated.
In the project, we first aim to investigate important and novel image features for both computer aided diagnosis and prognosis of lung cancer. In our plan, the framework include cell detection, segmentation, feature extraction, classification, and survival analysis for NLST NSCLC Histopathology images. A complete set of cellular features are extracted and several advanced machine learning classification approaches are compared using image features extracted in previous steps. If it works successfully, we can find representative feature variable for NSCLC subtype classification.
We conduct survival analysis based on a Cox model and also apply several survival analysis approaches to evaluate the discovered image features. By these evaluation, a set of prognostic image markers that are highly correlated to NSCLC patients’ survival analysis will be found. Using these image markers, we can accurately predict NSCLC patients’ survival. Together with clinical information, it provides significant clinical values for patients’ prognosis.
In summary, our project based on NLST data aims to design a system to assist doctors for more objective and accurate diagnoses and prognoses of lung cancer.
Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks.
Yao J, Zhu X, Jonnagaddala J, Hawkins N, Huang J
Med Image Anal. 2020 Oct; Volume 65: Pages 101789 PUBMED
Graph CNN for Survival Analysis on Whole Slide Pathological Images
Ruoyu Li Jiawen Yao Xinliang Zhu Yeqing Li Junzhou Huang
MICCAI 2018. 2018 Sep 26; Volume 11071: Pages pp 174-182
WSISA: Making Survival Prediction from Whole Slide Histopathological Images
Xinliang Zhu Univerisity of Texas at Arlington, Tencent AI Lab Jiawen Yao Univerisity of Texas at Arlington, Tencent AI Lab Feiyun Zhu Univerisity of Texas at Arlington, Tencent AI Lab Junzhou Huang Univerisity of Texas at Arlington, Tencent AI Lab
IEEE. 2017; Pages pp. 6855-6863
Deep convolutional neural network for survival analysis with pathological images
Xinliang Zhu Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA Jiawen Yao Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA Junzhou Huang Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA
IEEE. 2016; Pages pp. 544-547
Detecting 10,000 Cells in One Second
Zheng Xu Junzhou Huang
MICCAI 2016. 2016 Oct 2; Volume 9901: Pages pp 676-684
Imaging Biomarker Discovery for Lung Cancer Survival Prediction
Jiawen Yao Sheng Wang Xinliang Zhu Junzhou Huang
MICCAI 2016. 2016 Oct 2; Volume 9901: Pages pp 649-657
An effective approach for robust lung cancer cell detection.
Hao Pan Zheng Xu Junzhou Huang
Patch-MI 2015. 2016 Jan 8; Volume 9467: Pages pp 87-94
Efficient lung cancer cell detection with deep convolution neural network.
Zheng Xu Junzhou Huang
Patch-MI 2015. 2016 Jan 8; Volume 9467: Pages pp. 79-86
Fast Regions-of-Interest Detection in Whole Slide Histopathology Images
Ruoyu Li Junzhou Huang
Patch-MI 2015. 2016 Jan 8; Volume 9467
Computer-Assisted Diagnosis of Lung Cancer Using Quantitative Topology Features
Jiawen Yao Dheeraj Ganti Xin Luo Guanghua Xiao Yang Xie Shirley Yan Junzhou Huang
MLMI 2015. 2015 Oct 2; Volume 9352: Pages pp 288-295