Feature Fusion Ensemble Architecture With Active Learning For Microscopic Blood Smear Analysis

The blood smear analysis provides vital information and forms the basis to diagnose the diseases. With recent developments, deep learning methods can analyze the microscopic blood sample using image processing and classification tasks with less human effort and increased accuracy. In this work, embarking upon domain-specific feature extraction and active learning, we propose a compact, yet efficient feature fusion ensemble based architecture for WBC sub-class classification and WBC disease identification which can automate and speed up the process of blood smear analysis with the help of digital image slide scanners. The proposed architecture is a three-stage multi-channel architecture with shallow feature inputs, deep feature extractors, and classification stage respectively. The trainable parameters are quite less in our architecture when compared to deeper networks like ResNet 152, VGG19. However, labeling medical data-sets have been very challenging and costly. To mitigate huge labeling requirements and cost, Active Learning is employed to train this architecture and demonstrate much higher accuracy with quite less labeled data. The proposed approach is shown to be quite general and yields better performance in terms of accuracy in WBC classification and Disease identification, with much fewer labeled samples for training, when compared with recent deeper models.