Segmentation of Mediastinal Lymph Nodes in CT with Anatomical Priors

TL;DR

This work introduces an end-to-end LN segmentation approach in mediastinal CT that leverages 28 anatomical priors generated by TotalSegmentator to guide a 3D nnUNet. Training on 89 NIH CT LN volumes and testing on an out-of-distribution St Olavs set, the method uses a cascade architecture to achieve a Dice score of $72.2 \pm 22.3$ for clinically significant LNs ($SAD \ge 8~\mathrm{mm}$) and $54.8 \pm 23.8$ overall, representing a ~10-point improvement over prior methods. The approach addresses class imbalance and disambiguation of LNs from neighboring structures, with no post-processing required. This technique has potential to improve initial staging CT assessments and could extend to segmentation of other nodal regions, ultimately aiding in diagnosis and treatment planning.

Abstract

Purpose: Lymph nodes (LNs) in the chest have a tendency to enlarge due to various pathologies, such as lung cancer or pneumonia. Clinicians routinely measure nodal size to monitor disease progression, confirm metastatic cancer, and assess treatment response. However, variations in their shapes and appearances make it cumbersome to identify LNs, which reside outside of most organs. Methods: We propose to segment LNs in the mediastinum by leveraging the anatomical priors of 28 different structures (e.g., lung, trachea etc.) generated by the public TotalSegmentator tool. The CT volumes from 89 patients available in the public NIH CT Lymph Node dataset were used to train three 3D nnUNet models to segment LNs. The public St. Olavs dataset containing 15 patients (out-of-training-distribution) was used to evaluate the segmentation performance. Results: For the 15 test patients, the 3D cascade nnUNet model obtained the highest Dice score of 72.2 +- 22.3 for mediastinal LNs with short axis diameter $\geq$ 8mm and 54.8 +- 23.8 for all LNs respectively. These results represent an improvement of 10 points over a current approach that was evaluated on the same test dataset. Conclusion: To our knowledge, we are the first to harness 28 distinct anatomical priors to segment mediastinal LNs, and our work can be extended to other nodal zones in the body. The proposed method has immense potential for improved patient outcomes through the identification of enlarged nodes in initial staging CT scans.

Figures (3)

• Figure 1: Flowchart of the proposed approach to segment mediastinal lymph nodes in CT using anatomical priors. First, the public TotalSegmentator tool was used to segment 28 structures in 89 mediastinal CT volumes from the public NIH CT Lymph Node dataset. Next, these labels were combined with the manual annotations for mediastinal LNs, and used to train a 3D nnUNet segmentation model. At test time, the 3D nnUNet was executed on CT volumes of 15 patients in the public St Olavs dataset. Green labels in the prediction correspond to the predicted LNs. The figure is best viewed in color in the PDF.
• Figure 2: Results from our approach to detect mediastinal LNs in CT volumes. Left column: A slice of the original CT volume, Middle column: GT annotation, Right column: Prediction from the nnUNet Cascade model. The different colors in the GT correspond to the different stations of the LNs, but for evaluation purposes, they were all considered to belong to one class based on their short axis diameter. Notice that in (b) for patient #7, the model was able to partially capture the large metastatic node (blue), while it also identified an unmarked node in the GT (middle). In (c), the model missed the node in blue.
• Figure 3: Box plots of the different 3D nnUNet model configurations for the segmentation of mediastinal lymph nodes in the St Olavs dataset. Results are shown for lymph nodes with short axis diameters $\geq$ 8mm.