Interactive Segmentation for COVID-19 Infection Quantification on Longitudinal CT scans

TL;DR

This paper introduces a novel interactive segmentation model that leverages all available longitudinal CT scan data and user feedback to improve COVID-19 infection quantification across multiple time points, enhancing clinical utility.

Contribution

A new single network model for longitudinal COVID-19 CT segmentation that utilizes past information and user feedback for improved accuracy.

Findings

Outperforms static segmentation models on longitudinal data

Effectively localizes COVID-19 infections in follow-up scans

Utilizes user feedback for iterative refinement

Abstract

Consistent segmentation of COVID-19 patient's CT scans across multiple time points is essential to assess disease progression and response to therapy accurately. Existing automatic and interactive segmentation models for medical images only use data from a single time point (static). However, valuable segmentation information from previous time points is often not used to aid the segmentation of a patient's follow-up scans. Also, fully automatic segmentation techniques frequently produce results that would need further editing for clinical use. In this work, we propose a new single network model for interactive segmentation that fully utilizes all available past information to refine the segmentation of follow-up scans. In the first segmentation round, our model takes 3D volumes of medical images from two-time points (target and reference) as concatenated slices with the additional reference time point segmentation as a guide to segment the target scan. In subsequent segmentation refinement rounds, user feedback in the form of scribbles that correct the segmentation and the target's previous segmentation results are additionally fed into the model. This ensures that the segmentation information from previous refinement rounds is retained. Experimental results on our in-house multiclass longitudinal COVID-19 dataset show that the proposed model outperforms its static version and can assist in localizing COVID-19 infections in patient's follow-up scans.