Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks
This work addresses classification efficiency for medical imaging researchers, but it is incremental as it compares existing methods on a specific dataset.
The study compared using pre-trained convolutional neural networks (CNNs) versus training from scratch for histopathology image classification on the Kimia Path24 dataset, finding that pre-trained networks were competitive and fine-tuning improved Inception but not VGG16.
We explore the problem of classification within a medical image data-set based on a feature vector extracted from the deepest layer of pre-trained Convolution Neural Networks. We have used feature vectors from several pre-trained structures, including networks with/without transfer learning to evaluate the performance of pre-trained deep features versus CNNs which have been trained by that specific dataset as well as the impact of transfer learning with a small number of samples. All experiments are done on Kimia Path24 dataset which consists of 27,055 histopathology training patches in 24 tissue texture classes along with 1,325 test patches for evaluation. The result shows that pre-trained networks are quite competitive against training from scratch. As well, fine-tuning does not seem to add any tangible improvement for VGG16 to justify additional training while we observed considerable improvement in retrieval and classification accuracy when we fine-tuned the Inception structure.