Pathological Image Classification Based on Hard Example Guided CNN
Open Access
- 17 June 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 114249-114258
Abstract
The diagnosis of biopsy tissue with hematoxylin and eosin (H&E) stained images has been widely used by pathologists to detect the lesions and assess the malignancy. Nevertheless, the diagnostic result relies on the visual observation of pathologists which may vary from person to person under different circumstances. With the advantage of automatically and adaptively learning features at multiple levels of abstraction, Convolutional Neural Networks (CNNs) have rapidly become promising alternatives for pathological image analysis. Therefore, in this paper, we propose an effective method for tumor classification called Hard Example Guided CNN. Our contribution is twofold: firstly, to optimize image representation, we design the CNN architecture as dual-branch, used for extracting global features and local features simultaneously. Secondly, we propose a re-weight training algorithm, which improves learning accuracy and accelerates the convergence by increasing the weight of hard examples. Extensive experiments on multiple datasets demonstrate the superiority of our proposed classification method.Keywords
Funding Information
- National Natural Science Foundation of China (81972248)
- Natural Science Foundation of Beijing Municipality (7202056, 4182044)
This publication has 22 references indexed in Scilit:
- Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classificationPattern Recognition, 2017
- Breast cancer histopathological image classification using Convolutional Neural Networks2016
- Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers2016
- A deep feature based framework for breast masses classificationNeurocomputing, 2016
- Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep LearningIEEE Transactions on Biomedical Engineering, 2015
- Early Detection of Cancer: Past, Present, and FutureAmerican Society of Clinical Oncology Educational Book, 2015
- On use of partial area under the ROC curve for evaluation of diagnostic performanceStatistics in Medicine, 2013
- A Survey of Decision Fusion and Feature Fusion Strategies for Pattern ClassificationIETE Technical Review, 2010
- To recognize shapes, first learn to generate images2007
- On the momentum term in gradient descent learning algorithmsNeural Networks, 1999