ABSTRACT
In this paper, we present a system for segmentation and classification of breast cancer ROI images by integrating the idea of hierarchical processing of segmentation and classification tasks. The system is composed of a segmentation module and a GCN module, where the GCN module is designed to improve the performance of the classification result. The segmentation module is used to obtain the segmentation masks of the image patches of the ROI image, which are spliced to generate the segmenion result of the ROI image. The GCN module is used to capture the spatial and semantic dependencies among image patches of the ROI image, by constructing the graph using the segmentation masks of the image patches. Based on the learned features by the GCN module, the classification result of the ROI image can be obtained. Experimental results on the grand challenge on BreAst Cancer Histology images (BACH) 2018 dataset [17] show that, the proposed segmentation and classification method outperforms the winner of BACH 2018 significantly, which demonstrates the effectiveness of the proposed method.
- Ahmed Fakhry, Tao Zeng, Shuiwang Ji: Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation. IEEE Trans. Med. Imaging 36(2): 447--456 (2017)Google ScholarCross Ref
- Richard E. Fine: Diagnostic Techniques. B. C. Decker, Inc., Ontario, 2nd edn. (2006)Google Scholar
- Anant Madabhushi, George Lee: Image Analysis and Machine Learning in Digital Pathology: Challenges and Opportunities. Medical Image Analysis 33: 170--175 (2016)Google ScholarCross Ref
- Joann G Elmore, Gary M Longton, Patricia A Carney, Berta M Geller, Tracy Onega, Anna N A Tosteson, Heidi D Nelson, Margaret S Pepe, Kimberly H Allison, Stuart J Schnitt, Frances P O'Malley, Donald L Weaver: Diagnostic concordance among pathologists interpreting breast biopsy specimens. JAMA (2015)Google Scholar
- Dinggang Shen, Guorong Wu, and Heung-Il Suk, Deep Learning in Medical Image Analysis, Annual Review of Biomedical Engineering 19: 221--248 (2017).Google Scholar
- Christoph Haarburger, Michael Baumgartner, Mirjam Broeckmann, Hannah Schneider, Simone Schwabing, Christiane Kuhl, Dorit Merhof: Multi Scale Curriculum CNN for Context-Aware Breast MRI Malignancy Classification. MICCAI (2019)Google Scholar
- William Lotter, Greg Sorensen, David Cox: A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification. MICCAI (2017)Google Scholar
- Mohammad Hossein Askari Hemmat, Sina Honari, Lucas Rouhier, Christian S. Perone, Julien Cohen-Adad, Yvon Savaria, Jean-Pierre David: U-Net Fixed-Point Quantization for Medical Image Segmentation. ISBI (2019)Google Scholar
- Jonathan Long, Evan Shelhamer, Trevor Darrell: Fully Convolutional Networks for Semantic Segmentation. CVPR 2015: 3431--3440.Google Scholar
- Ruoyu Li, Jiawen Yao, Xinliang Zhu, Yeqing Li, Junzhou Huang: Graph CNN for Survival Analysis on Whole Slide Pathological Images. MICCAI (2018)Google Scholar
- Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo: Multi-Label Image Recognition with Graph Convolutional Networks. CVPR (2019)Google Scholar
- Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia: Pyramid Scene Parsing Network. CVPR (2017)Google Scholar
- Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, Hannaneh Hajishirzi: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation. ECCV (2018)Google Scholar
- Sachin Mehta, Mohammad Rastegari, Linda Shapiro, Hannaneh Hajishirzi: ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network. arXiv:1811.11431Google Scholar
- Olaf Ronneberger, Philipp Fischer, Thomas Brox: U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI (2015)Google Scholar
- Sachin Mehta, Ezgi Mercan, Jamen Bartlett, Donald Weave, Joann G Elmore, Linda Shapiro: Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images. MICCAI (2018)Google Scholar
- Guilherme Aresta, Teresa Araújo, Scotty Kwok, Sai Saketh Chennamsetty, Mohammed Safwan, et al.: BACH: grand challenge on breast cancer histology images. MIA (2019)Google Scholar
- Scotty Kwok: Multiclass Classification of Breast Cancer in Whole-Slide Images. Lecture Notes in Computer Science, volume 10882. doi:10.1007/978-3-319-93000-8_106.Google Scholar
- Sai Saketh Chennamsetty, Mohammed Safwan, Varghese Alex: Classification of Breast Cancer Histology Image using Ensemble of Pre-trained Neural Networks. Image Analysis and Recognition. doi:10.1007/978-3-319-93000-8-91.Google Scholar
- Bahram Marami, Marcel Prastawa, Monica Chan, Michael Donovan, Gerardo Fernandez, Jack Zeineh:Ensemble Network for Region Identification in Breast Histopathology Slides. Image Analysis and Recognition. doi:10.1007/978-3-319-93000-8_98.Google Scholar
- Nadia Brancati, Maria Frucci, Daniel Riccio: Multi-classification of Breast Cancer Histology Images by Using a Fine-Tuning Strategy LNCS, volume 10882.doi:10.1007/978-3-319-93000-8_87.Google Scholar
Index Terms
- Improving Histopathological Image Segmentation and Classification using Graph Convolution Network
Recommendations
A Two-Branch Neural Network for Non-Small-Cell Lung Cancer Classification and Segmentation
Artificial Neural Networks and Machine Learning – ICANN 2021AbstractImmunotherapy has great potential in the treatment of Non-Small-Cell Lung Cancer (NSCLC). The treatment decision for patients is based on the pathologist’s analysis of NSCLC biopsy images. Using deep learning (DL) methods to automatically segment ...
Classification of Breast Cancer Histopathological Images Using KAZE Features
Bioinformatics and Biomedical EngineeringAbstractBreast cancer (BC) is a public health problem of first importance, being the second most common cancer worldwide. BC represents 30.4% of all new cancer cases in the European female population. The diagnosis and differential diagnosis of BC is ...
Gland segmentation in colorectal cancer histopathological images using U-net inspired convolutional network
AbstractThe accurate gland segmentation from digitized H&E (hematoxylin and eosin) histology images with a wide range of histologic grades of cancer is quite challenging. The methodologies proposed in recent researches have performed well in segmenting ...
Comments