Harnessing Advanced Machine Learning Techniques for Microscopic Vessel Segmentation in Pulmonary Fibrosis Using Novel Hierarchical Phase-Contrast Tomography (HiP-CT) Images.

Abstract

Background: Fibrotic lung disease is a progressive illness that causes scarring and ultimately respiratory failure, with irreversible damage by the time its diagnosed on computed tomography imaging. Recent research postulates the role of the lung vasculature on the pathogenesis of the disease, and with the recent development of high-resolution hierarchical phase contrast tomography (HiP-CT), we have the potential to understand and detect changes in the lungs long before conventional imaging. However, to gain quantitative insight into vascular changes you first need to be able to segment the vessels before further downstream analysis can be conducted. Aside from this, HiP-CT generates large volume, high resolution data which is time consuming and expensive to label.

Objectives: This project aims to qualitatively assess the latest machine learning methods for vessel segmentation in HiP-CT data to enable label propagation as the first step for imaging biomarker discovery, with the goal to identify early-stage interstitial lung disease amenable to treatment, before fibrosis begins.

Methods: Semi-supervised learning has become a growing method to tackle sparsely labelled datasets due to its leveraging of unlabelled data. In this study we will compare 2 semi-supervised learning methods; Seg PL, based on pseudo labelling and MisMatch, using consistency regularisation against state of the art supervised learning method, in nnU-Net, on vessel segmentation in sparsely labelled lung HiP-CT data.

Results: On initial experimentation, both MisMatch and SegPL showed promising performance on qualitative review. In comparison with supervised learning, both MisMatch and SegPL showed better on out of distribution performance within the same sample (different vessel morphology and texture vessels), though supervised learning provided more consistent segmentations for well represented labels in the limited annotations.

Conclusion: Further quantitative research is required to better assess the generalisability of these findings, though they show promising first steps towards leveraging this novel data to tackle fibrotic lung disease.