Zero-Shot lung segmentation of Phase-Resolved Functional Lung (PREFUL) MRI from adults and children with pulmonary diseases

Motivation: PREFUL MRI relies on accurate lung segmentation. Automating lung segmentation using supervised machine learning requires the laborious creation of training data. Therefore, an alternative independent of availability and peculiarities of training data may be useful. Goal(s): Investigate feasibility and limits of lung segmentation in PREFUL MRI across different vendors, acquisition parameters, age groups and pulmonary diseases without training data. Approach: Segment Anything Model (SAM) using different point grids and seedpoint-based prompts was evaluated in overall 14 different configurations. Results: Comparison with ground truth showed median Dice Similarity Coefficient (DSC) of 0.82 without training data. Impact: Lung segmentation of PREFUL MRI of child and adult patients with different pulmonary diseases appears feasible without training data. The construction of supervised trained segmentation models may be not mandatory for projects when a median DSC of 0.82 is sufficient.