Efficient Annotation for Medical Image Analysis: A One-Pass Selective Annotation Approach

TL;DR

This paper introduces EPOSA, a novel one-pass selective annotation method that reduces annotation effort in medical image analysis by intelligently selecting representative samples using VAE, clustering, and MCMC techniques, while maintaining high model performance.

Contribution

The paper presents a new efficient annotation framework combining variational autoencoders, clustering, and MCMC-based sample selection to minimize annotation effort in medical imaging.

Findings

EPOSA outperforms random and state-of-the-art selection methods under the same annotation budget.

The approach achieves high classification accuracy with fewer annotated samples.

Experimental validation on Med-MNIST demonstrates its effectiveness.

Abstract

Annotating biomedical images for supervised learning is a complex and labor-intensive task due to data diversity and its intricate nature. In this paper, we propose an innovative method, the efficient one-pass selective annotation (EPOSA), that significantly reduces the annotation burden while maintaining robust model performance. Our approach employs a variational autoencoder (VAE) to extract salient features from unannotated images, which are subsequently clustered using the DBSCAN algorithm. This process groups similar images together, forming distinct clusters. We then use a two-stage sample selection algorithm, called representative selection (RepSel), to form a selected dataset. The first stage is a Markov Chain Monte Carlo (MCMC) sampling technique to select representative samples from each cluster for annotations. This selection process is the second stage, which is guided by the principle of maximizing intra-cluster mutual information and minimizing inter-cluster mutual information. This ensures a diverse set of features for model training and minimizes outlier inclusion. The selected samples are used to train a VGG-16 network for image classification. Experimental results on the Med-MNIST dataset demonstrate that our proposed EPOSA outperforms random selection and other state-of-the-art methods under the same annotation budget, presenting a promising direction for efficient and effective annotation in medical image analysis.