Rapid Training Data Creation by Synthesizing Medical Images for Classification and Localization

TL;DR

This paper introduces a method to rapidly generate synthetic medical images to train deep learning models, reducing the need for extensive expert annotation and improving localization accuracy.

Contribution

The authors propose a data transformation approach that enables effective training of localization models with synthetic images, minimizing the need for exhaustive real data annotation.

Findings

Synthetic data improves localization accuracy significantly.

Training with generated images matches performance of models trained on exhaustively annotated data.

Approach applicable to both weakly and strongly supervised models.

Abstract

While the use of artificial intelligence (AI) for medical image analysis is gaining wide acceptance, the expertise, time and cost required to generate annotated data in the medical field are significantly high, due to limited availability of both data and expert annotation. Strongly supervised object localization models require data that is exhaustively annotated, meaning all objects of interest in an image are identified. This is difficult to achieve and verify for medical images. We present a method for the transformation of real data to train any Deep Neural Network to solve the above problems. We show the efficacy of this approach on both a weakly supervised localization model and a strongly supervised localization model. For the weakly supervised model, we show that the localization accuracy increases significantly using the generated data. For the strongly supervised model, this approach overcomes the need for exhaustive annotation on real images. In the latter model, we show that the accuracy, when trained with generated images, closely parallels the accuracy when trained with exhaustively annotated real images. The results are demonstrated on images of human urine samples obtained using microscopy.