Fully Automated Machine Learning Pipeline for Echocardiogram Segmentation

TL;DR

This paper presents an automated machine learning pipeline for echocardiogram segmentation that reduces labeling effort and automates model design, achieving high accuracy with less training data and comparable performance to manually designed models.

Contribution

It introduces a fully automated pipeline combining Active Learning and Neural Architecture Search for efficient echocardiogram segmentation.

Findings

Achieved same IOU accuracy with only 40% of original training data.

Automatically designed model matches the performance of hand-crafted models.

Reduces labeling effort and development time for echocardiogram segmentation.

Abstract

Nowadays, cardiac diagnosis largely depends on left ventricular function assessment. With the help of the segmentation deep learning model, the assessment of the left ventricle becomes more accessible and accurate. However, deep learning technique still faces two main obstacles: the difficulty in acquiring sufficient training data and time-consuming in developing quality models. In the ordinary data acquisition process, the dataset was selected randomly from a large pool of unlabeled images for labeling, leading to massive labor time to annotate those images. Besides that, hand-designed model development is strenuous and also costly. This paper introduces a pipeline that relies on Active Learning to ease the labeling work and utilizes Neural Architecture Search's idea to design the adequate deep learning model automatically. We called this Fully automated machine learning pipeline for echocardiogram segmentation. The experiment results show that our method obtained the same IOU accuracy with only two-fifths of the original training dataset, and the searched model got the same accuracy as the hand-designed model given the same training dataset.