MEDPSeg: Hierarchical polymorphic multitask learning for the segmentation of ground-glass opacities, consolidation, and pulmonary structures on computed tomography

TL;DR

MEDPSeg introduces a hierarchical polymorphic multitask learning framework that significantly improves segmentation of lung lesions and structures in chest CT scans, enabling comprehensive analysis in a single model.

Contribution

The paper presents MEDPSeg, a novel hierarchical polymorphic multitask learning approach that leverages heterogeneous data for improved lung and lesion segmentation in CT images.

Findings

Achieved state-of-the-art performance in GGO and consolidation segmentation.

Simultaneously segments multiple lung structures with performance comparable to specialized methods.

Utilized over 6000 CT scans for training and testing.

Abstract

The COVID-19 pandemic response highlighted the potential of deep learning methods in facilitating the diagnosis, prognosis and understanding of lung diseases through automated segmentation of pulmonary structures and lesions in chest computed tomography (CT). Automated separation of lung lesion into ground-glass opacity (GGO) and consolidation is hindered due to the labor-intensive and subjective nature of this task, resulting in scarce availability of ground truth for supervised learning. To tackle this problem, we propose MEDPSeg. MEDPSeg learns from heterogeneous chest CT targets through hierarchical polymorphic multitask learning (HPML). HPML explores the hierarchical nature of GGO and consolidation, lung lesions, and the lungs, with further benefits achieved through multitasking airway and pulmonary artery segmentation. Over 6000 volumetric CT scans from different partially labeled sources were used for training and testing. Experiments show PML enabling new state-of-the-art performance for GGO and consolidation segmentation tasks. In addition, MEDPSeg simultaneously performs segmentation of the lung parenchyma, airways, pulmonary artery, and lung lesions, all in a single forward prediction, with performance comparable to state-of-the-art methods specialized in each of those targets. Finally, we provide an open-source implementation with a graphical user interface at https://github.com/MICLab-Unicamp/medpseg.