Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells

TL;DR

This paper introduces a semi-supervised learning framework using a redesigned self-training pipeline with FixMatch to improve white blood cell segmentation, addressing data scarcity and outdated methods in healthcare AI.

Contribution

The paper proposes a novel self-training pipeline incorporating FixMatch for semi-supervised white blood cell segmentation, enhancing performance on multiple datasets.

Findings

Achieved up to 90.69% accuracy on Zheng 1 dataset.

Incorporating FixMatch improves segmentation robustness.

Outperforms existing methods on benchmark datasets.

Abstract

Artificial Intelligence (AI) in healthcare, especially in white blood cell cancer diagnosis, is hindered by two primary challenges: the lack of large-scale labeled datasets for white blood cell (WBC) segmentation and outdated segmentation methods. These challenges inhibit the development of more accurate and modern techniques to diagnose cancer relating to white blood cells. To address the first challenge, a semi-supervised learning framework should be devised to efficiently capitalize on the scarcity of the dataset available. In this work, we address this issue by proposing a novel self-training pipeline with the incorporation of FixMatch. Self-training is a technique that utilizes the model trained on labeled data to generate pseudo-labels for the unlabeled data and then re-train on both of them. FixMatch is a consistency-regularization algorithm to enforce the model's robustness against variations in the input image. We discover that by incorporating FixMatch in the self-training pipeline, the performance improves in the majority of cases. Our performance achieved the best performance with the self-training scheme with consistency on DeepLab-V3 architecture and ResNet-50, reaching 90.69%, 87.37%, and 76.49% on Zheng 1, Zheng 2, and LISC datasets, respectively.