An Investigation of Recent Deep Learning Techniques Applied to Blood Cell Image Analysis
This project has investigated the performances of Capsule Networks in comparison to Convolutional Neural Networks (CNNs) on white blood cell image classification at CellaVision. The Capsule Network models that were investigated are EM Routing Capsule Networks (EMCNs) [Hinton et al., 2018] and Dynamic Routing Capsule Networks (DCNs) [Hinton et al., 2017]. The models were compared with regards to convergence rate, speed, and accuracy performance on varying dataset size and complexity. The results show that DCNs outperform the other models on small datasets with regards to accuracy and convergence rate, whereas the CNNs outperform the other models on bigger datasets with higher complexity. With regards to speed, CNNs outperform the other models on both CPU and GPU, with DCNs being very slow. For ethical reasons, all cell images used for training and testing the models are anonymous and cannot be linked with any person.