HydraMix-Net: A Deep Multi-task Semi-supervised Learning Approach for Cell Detection and Classification

TL;DR

HydraMix-Net is a semi-supervised deep learning model that improves cell detection and classification accuracy in medical images by leveraging unlabelled data through pseudo-labeling, sharpening, and multi-task training.

Contribution

The paper introduces HydraMix-Net, a novel multi-task semi-supervised approach that effectively utilizes unlabelled data for cell detection and classification in medical imaging.

Findings

Achieves 80% accuracy on DLBCL data with limited labelled examples.

Outperforms simple CNN models trained on the same limited data.

Demonstrates effectiveness of pseudo-labeling and multi-task learning in medical image analysis.

Abstract

Semi-supervised techniques have removed the barriers of large scale labelled set by exploiting unlabelled data to improve the performance of a model. In this paper, we propose a semi-supervised deep multi-task classification and localization approach HydraMix-Net in the field of medical imagining where labelling is time consuming and costly. Firstly, the pseudo labels are generated using the model's prediction on the augmented set of unlabelled image with averaging. The high entropy predictions are further sharpened to reduced the entropy and are then mixed with the labelled set for training. The model is trained in multi-task learning manner with noise tolerant joint loss for classification localization and achieves better performance when given limited data in contrast to a simple deep model. On DLBCL data it achieves 80\% accuracy in contrast to simple CNN achieving 70\% accuracy when given only 100 labelled examples.