LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a Probabilistic Lymph Node Atlas

TL;DR

This paper presents a novel approach for mediastinal lymph node segmentation using a probabilistic lymph node atlas, significantly improving accuracy in challenging CT images through anatomical priors and data augmentation.

Contribution

It introduces the use of a probabilistic lymph node atlas combined with ensemble methods and data augmentation to enhance segmentation performance under partial annotation conditions.

Findings

Dice score of 0.6033 achieved with the proposed method

Segmentation of 57% of ground truth lymph nodes

Significant accuracy improvement over CT-only training

Abstract

The evaluation of lymph node metastases plays a crucial role in achieving precise cancer staging, influencing subsequent decisions regarding treatment options. Lymph node detection poses challenges due to the presence of unclear boundaries and the diverse range of sizes and morphological characteristics, making it a resource-intensive process. As part of the LNQ 2023 MICCAI challenge, we propose the use of anatomical priors as a tool to address the challenges that persist in mediastinal lymph node segmentation in combination with the partial annotation of the challenge training data. The model ensemble using all suggested modifications yields a Dice score of 0.6033 and segments 57% of the ground truth lymph nodes, compared to 27% when training on CT only. Segmentation accuracy is improved significantly by incorporating a probabilistic lymph node atlas in loss weighting and post-processing. The largest performance gains are achieved by oversampling fully annotated data to account for the partial annotation of the challenge training data, as well as adding additional data augmentation to address the high heterogeneity of the CT images and lymph node appearance. Our code is available at https://github.com/MICAI-IMI-UzL/LNQ2023.