Transesophageal Echocardiography Generation using Anatomical Models

TL;DR

This paper presents a pipeline for generating synthetic transesophageal echocardiography images using anatomical models and evaluates their effectiveness in improving deep learning segmentation performance.

Contribution

It introduces a novel data augmentation pipeline for TEE images using unpaired I2I translation methods and assesses their impact on deep learning tasks.

Findings

Synthetic images improve segmentation dice scores by up to 10%.

Comparison of I2I translation metrics reveals disagreements in evaluating synthetic data.

FID score correlates better with augmentation effectiveness than other metrics.

Abstract

Through automation, deep learning (DL) can enhance the analysis of transesophageal echocardiography (TEE) images. However, DL methods require large amounts of high-quality data to produce accurate results, which is difficult to satisfy. Data augmentation is commonly used to tackle this issue. In this work, we develop a pipeline to generate synthetic TEE images and corresponding semantic labels. The proposed data generation pipeline expands on an existing pipeline that generates synthetic transthoracic echocardiography images by transforming slices from anatomical models into synthetic images. We also demonstrate that such images can improve DL network performance through a left-ventricle semantic segmentation task. For the pipeline's unpaired image-to-image (I2I) translation section, we explore two generative methods: CycleGAN and contrastive unpaired translation. Next, we evaluate the synthetic images quantitatively using the Fr\'echet Inception Distance (FID) Score and qualitatively through a human perception quiz involving expert cardiologists and the average researcher. In this study, we achieve a dice score improvement of up to 10% when we augment datasets with our synthetic images. Furthermore, we compare established methods of assessing unpaired I2I translation and observe a disagreement when evaluating the synthetic images. Finally, we see which metric better predicts the generated data's efficacy when used for data augmentation.