Interpolation-Split: a data-centric deep learning approach with big interpolated data to boost airway segmentation performance

TL;DR

This paper introduces a data-centric deep learning method called Interpolation-Split that enhances airway segmentation accuracy by using interpolated data and ensemble strategies, outperforming baseline models with low resource requirements.

Contribution

The study presents a novel interpolation-split technique combined with ensemble learning to improve airway segmentation performance and flexibility in deep learning models.

Findings

Outperforms baseline by 2.5% in dice similarity coefficient

Low GPU usage and high deployment flexibility

Effective with any 2D deep learning model

Abstract

The morphology and distribution of airway tree abnormalities enables diagnosis and disease characterisation across a variety of chronic respiratory conditions. In this regard, airway segmentation plays a critical role in the production of the outline of the entire airway tree to enable estimation of disease extent and severity. In this study, we propose a data-centric deep learning technique to segment the airway tree. The proposed technique utilises interpolation and image split to improve data usefulness and quality. Then, an ensemble learning strategy is implemented to aggregate the segmented airway trees at different scales. In terms of segmentation performance (dice similarity coefficient), our method outperforms the baseline model by 2.5% on average when a combined loss is used. Further, our proposed technique has a low GPU usage and high flexibility enabling it to be deployed on any 2D deep learning model.