Medical Augmentation (Med-Aug) for Optimal Data Augmentation in Medical Deep Learning Networks.

Justin Lo,Jillian Cardinell,Alejo Costanzo,Dafna Sussman

doi:10.3390/s21217018

Abstract

Deep learning (DL) algorithms have become an increasingly popular choice for image classification and segmentation tasks; however, their range of applications can be limited. Their limitation stems from them requiring ample data to achieve high performance and adequate generalizability. In the case of clinical imaging data, images are not always available in large quantities. This issue can be alleviated by using data augmentation (DA) techniques. The choice of DA is important because poor selection can possibly hinder the performance of a DL algorithm. We propose a DA policy search algorithm that offers an extended set of transformations that accommodate the variations in biomedical imaging datasets. The algorithm makes use of the efficient and high-dimensional optimizer Bi-Population Covariance Matrix Adaptation Evolution Strategy (BIPOP-CMA-ES) and returns an optimal DA policy based on any input imaging dataset and a DL algorithm. Our proposed algorithm, Medical Augmentation (Med-Aug), can be implemented by other researchers in related medical DL applications to improve their model’s performance. Furthermore, we present our found optimal DA policies for a variety of medical datasets and popular segmentation networks for other researchers to use in related tasks.

Highlights

Accepted: 18 October 2021Deep learning (DL) has become a popular subdivision of artificial intelligence and has shown great success in many medical image analysis tasks [1,2,3]
We present an algorithm, Medical Augmentation (Med-Aug), that can be used to combat the data limitations in medical DL studies by finding the Data augmentation (DA) policies that lead to the ideal performance of a target network
The results demonstrated that even the use of the most basic DA had significant impact on the performance of the model, as shown in Table 1; strategic policies selected by either Bayesian Optimization (BO)-Aug or our Med-Aug show consistent improvements over random DA

Summary

Introduction

Accepted: 18 October 2021DL has become a popular subdivision of artificial intelligence and has shown great success in many medical image analysis tasks [1,2,3]. There are still many limitations to DL networks that restrict their potential range of applications. One of the primary issues, especially in clinical applications, is their reliance on large datasets. In medical studies, datasets are limited due to privacy and legal concerns, disease frequency, cost of data acquisition, and the timeconsuming labelling process [1,2,3]. Despite these constraints, the success of DL networks in medicine has motivated work to adapt these networks to function well under low-data circumstances [1]. Data augmentation (DA) has been a common method used to combat this data limitation restriction

Methods

Discussion

Conclusion