A Histopathological Image Classification Method Based on Model Fusion in the Weight Space
Open Access
- 10 June 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (12) , 7009
Abstract
Automatic classification of histopathological images plays an important role in computer-aided diagnosis systems. The automatic classification model of histopathological images based on deep neural networks has received widespread attention. However, the performance of deep models is affected by many factors, such as training hyperparameters, model structure, dataset quality, and training cost. In order to reduce the impact of the above factors on model training and reduce the training and inference costs of the model, we propose a novel method based on model fusion in the weight space, which is inspired by stochastic weight averaging and model soup. We use the cyclical learning rate (CLR) strategy to fine-tune the ingredient models and propose a ranking strategy based on accuracy and diversity for candidate model selection. Compared to the single model, the weight fusion of ingredient models can obtain a model whose performance is closer to the expected value of the error basin, which may improve the generalization ability of the model. Compared to the ensemble model with n base models, the testing cost of the proposed model is theoretically of that of the ensemble model. Experimental results on two histopathological image datasets show the effectiveness of the proposed model in comparison to baseline ones, including ResNet, VGG, DenseNet, and their ensemble versions.
Keywords
Funding Information
- National Natural Science Foundation of China (81573827, 81373883, 202201020586, 202102080252, 2020KCXTD053)
- Guangzhou City and the School (81573827, 81373883, 202201020586, 202102080252, 2020KCXTD053)
- Science and Technology Projects in Guangzhou (81573827, 81373883, 202201020586, 202102080252, 2020KCXTD053)
- Key Platforms and Scientific Research Projects in Universities in Guangdong Province (81573827, 81373883, 202201020586, 202102080252, 2020KCXTD053)
This publication has 28 references indexed in Scilit:
- Accurate Patient-Specific Machine Learning Models of Glioblastoma Invasion Using Transfer LearningAmerican Journal of Neuroradiology, 2019
- Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology ImagesCell Reports, 2018
- A novel hierarchical selective ensemble classifier with bioinformatics applicationArtificial Intelligence in Medicine, 2017
- Densely Connected Convolutional Networks2017
- Cyclical Learning Rates for Training Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Validation of digital pathology imaging for primary histopathological diagnosisHistopathology, 2015
- Deep learningNature, 2015
- Ensemble pruning via individual contribution ordering2010
- ImageNet: A large-scale hierarchical image database2009