Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling

TL;DR

This paper introduces a suggestive annotation framework for brain tumour images that efficiently identifies informative samples for expert annotation, significantly reducing manual effort while maintaining high segmentation performance.

Contribution

The proposed method effectively reduces annotation effort by suggesting key samples, enabling high-performance segmentation with only 19% annotated data.

Findings

Training with 19% annotated scans achieves comparable results to full dataset.

Suggestive sampling reduces manual annotation costs.

Framework improves data efficiency in medical image segmentation.

Abstract

Machine learning has been widely adopted for medical image analysis in recent years given its promising performance in image segmentation and classification tasks. As a data-driven science, the success of machine learning, in particular supervised learning, largely depends on the availability of manually annotated datasets. For medical imaging applications, such annotated datasets are not easy to acquire. It takes a substantial amount of time and resource to curate an annotated medical image set. In this paper, we propose an efficient annotation framework for brain tumour images that is able to suggest informative sample images for human experts to annotate. Our experiments show that training a segmentation model with only 19% suggestively annotated patient scans from BraTS 2019 dataset can achieve a comparable performance to training a model on the full dataset for whole tumour segmentation task. It demonstrates a promising way to save manual annotation cost and improve data efficiency in medical imaging applications.