Tumor Segmentation in Whole Slide Images Using Persistent Homology and Deep Convolutional Features

This paper presents a novel automated tumor segmentation approach for Hematoxylin & Eosin stained histology images. The proposed method enhances the segmentation performance by combining the topological and convolution neural network (CNN) features. Our approach is based on 3 steps: (1) construct enhanced persistent homology profiles by using topological features; (2) train a CNN to extract convolutional features; (3) employ a multi-stage ensemble strategy to combine Random Forest regression models. The experimental results demonstrate that proposed method outperforms the conventional CNN.

[1]  Hao Chen,et al.  Gland segmentation in colon histology images: The glas challenge contest , 2016, Medical Image Anal..

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

[3]  Zeev Farbman,et al.  Edge-preserving decompositions for multi-scale tone and detail manipulation , 2008, SIGGRAPH 2008.

[4]  M. Ferri,et al.  Betti numbers in multidimensional persistent homology are stable functions , 2013 .

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

[6]  G. McLennan,et al.  An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer , 2010, Annals of Biomedical Engineering.

[7]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

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

[9]  Gunnar E. Carlsson,et al.  Topology and data , 2009 .

[10]  B. van Ginneken,et al.  Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis , 2016, Scientific Reports.

[11]  David B. A. Epstein,et al.  Persistent Homology for Fast Tumor Segmentation in Whole Slide Histology Images , 2016, MIUA.

[12]  N. Rajpoot,et al.  HyMaP: A hybrid magnitude-phase approach to unsupervised segmentation of tumor areas in breast cancer histology images , 2013, Journal of pathology informatics.

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

[14]  Victor S. Lempitsky,et al.  Aggregating Local Deep Features for Image Retrieval , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Nasir M. Rajpoot,et al.  A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution , 2014, IEEE Transactions on Biomedical Engineering.