A computational study on convolutional feature combination strategies for grade classification in colon cancer using fluorescence microscopy data.

Proceedings of SPIE(2017)

引用 4|浏览24
暂无评分
摘要
The cancer diagnostic workflow is typically performed by highly specialized and trained pathologists, for which analysis is expensive both in terms of time and money. This work focuses on grade classification in colon cancer. The analysis is performed over 3 protein markers; namely E-cadherin, beta actin and colagenIV. In addition, we also use a virtual Hematoxylin & Eosin (H&E) stain. This study involves a comparison of various ways in which we can manipulate the information over the 4 different images of the tissue samples and come up with a coherent and unified response based on the data at our disposal. Pre-trained convolutional neural networks (CNNs) is the method of choice for feature extraction. The AlexNet architecture trained on the ImageNet database is used for this purpose. We extract a 4096 dimensional feature vector corresponding to the 6th layer in the network. Linear SVM is used to classify the data. The information from the 4 different images pertaining to a particular tissue sample; are combined using the following techniques: soft voting, hard voting, multiplication, addition, linear combination, concatenation and multi-channel feature extraction. We observe that we obtain better results in general than when we use a linear combination of the feature representations. We use 5-fold cross validation to perform the experiments. The best results are obtained when the various features are linearly combined together resulting in a mean accuracy of 91.27%.
更多
查看译文
关键词
Machine learning,pre-trained convolutional neural networks,support vector machines,feature combination
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要