Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

Background Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these ap...

Full description

Saved in:

Bibliographic Details
Published in:	European radiology experimental Vol. 4; no. 1; p. 50
Main Authors:	Hofmanninger, Johannes, Prayer, Forian, Pan, Jeanny, Röhrich, Sebastian, Prosch, Helmut, Langs, Georg
Format:	Journal Article
Language:	English
Published:	Cham Springer International Publishing 20-08-2020 Springer Nature B.V SpringerOpen
Subjects:	Algorithms Datasets Datasets as Topic Deep Learning Diagnostic Radiology Humans Imaging Internal Medicine Interventional Radiology Lung Lung Diseases - diagnostic imaging Medicine Medicine & Public Health Neuroradiology Original Original Article Radiographic Image Interpretation, Computer-Assisted - methods Radiology Reproducibility Reproducibility of Results Tomography, X-Ray Computed Ultrasound Deep learning Reproducibility of results Algorithms Tomography (x-ray computed) Lung
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Background Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exists, involving sophisticated pipelines trained and validated on different datasets. However, the clinical applicability of these approaches across diseases remains limited. Methods We compared four generic deep learning approaches trained on various datasets and two readily available lung segmentation algorithms. We performed evaluation on routine imaging data with more than six different disease patterns and three published data sets. Results Using different deep learning approaches, mean Dice similarity coefficients (DSCs) on test datasets varied not over 0.02. When trained on a diverse routine dataset ( n = 36), a standard approach (U-net) yields a higher DSC (0.97 ± 0.05) compared to training on public datasets such as the Lung Tissue Research Consortium (0.94 ± 0.13, p = 0.024) or Anatomy 3 (0.92 ± 0.15, p = 0.001). Trained on routine data ( n = 231) covering multiple diseases, U-net compared to reference methods yields a DSC of 0.98 ± 0.03 versus 0.94 ± 0.12 ( p = 0.024). Conclusions The accuracy and reliability of lung segmentation algorithms on demanding cases primarily relies on the diversity of the training data, highlighting the importance of data diversity compared to model choice. Efforts in developing new datasets and providing trained models to the public are critical. By releasing the trained model under General Public License 3.0, we aim to foster research on lung diseases by providing a readily available tool for segmentation of pathological lungs.
Bibliography:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23
ISSN:	2509-9280 2509-9280
DOI:	10.1186/s41747-020-00173-2