Papers
arxiv:2102.06515

Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding

Published on Feb 11, 2021
Authors:
,
,
,

Abstract

As lung cancer evolves, the presence of enlarged and potentially malignant lymph nodes must be assessed to properly estimate disease progression and select the best treatment strategy. Following the clinical guidelines, estimation of short-axis diameter and mediastinum station are paramount for correct diagnosis. A method for accurate and automatic segmentation is hence decisive for quantitatively describing lymph nodes. In this study, the use of 3D convolutional neural networks, either through slab-wise schemes or the leveraging of downsampled entire volumes, is investigated. Furthermore, the potential impact from simple ensemble strategies is considered. As lymph nodes have similar attenuation values to nearby anatomical structures, we suggest using the knowledge of other organs as prior information to guide the segmentation task. To assess the segmentation and instance detection performances, a 5-fold cross-validation strategy was followed over a dataset of 120 contrast-enhanced CT volumes. For the 1178 lymph nodes with a short-axis diameter geq10 mm, our best performing approach reached a patient-wise recall of 92%, a false positive per patient ratio of 5, and a segmentation overlap of 80.5%. The method performs similarly well across all stations. Fusing a slab-wise and a full volume approach within an ensemble scheme generated the best performances. The anatomical priors guiding strategy is promising, yet a larger set than four organs appears needed to generate an optimal benefit. A larger dataset is also mandatory, given the wide range of expressions a lymph node can exhibit (i.e., shape, location, and attenuation), and contrast uptake variations.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2102.06515 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2102.06515 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2102.06515 in a Space README.md to link it from this page.

Collections including this paper 1