Deep Learning-Based Auto-Segmentation of Planning Target Volume for Total Marrow and Lymph Node Irradiation

TL;DR

This study tackles automatic segmentation of the Planning Target Volume (PTV) for Total Marrow and Lymph Node Irradiation (TMLI) using deep learning. It extends prior work by employing the nnU-Net framework to train both 2D and 3D U-Nets and by evaluating performance after bone subtraction to stress the lymph-node-rich regions. Results show that nnU-Net models significantly outperform a vanilla U-Net in overall PTV segmentation, with DSC improvements around 3 percentage points and HD95 reductions of approximately 4–5 mm; bone-exclusion tests demonstrate robust performance in challenging areas, with no dramatic degradation. The findings support the potential of DL-based auto-segmentation to reduce contouring time and inter-observer variability in complex TMLI planning, while highlighting avenues for future lymph-node–focused improvements and clinician-facing validation.

Abstract

In order to optimize the radiotherapy delivery for cancer treatment, especially when dealing with complex treatments such as Total Marrow and Lymph Node Irradiation (TMLI), the accurate contouring of the Planning Target Volume (PTV) is crucial. Unfortunately, relying on manual contouring for such treatments is time-consuming and prone to errors. In this paper, we investigate the application of Deep Learning (DL) to automate the segmentation of the PTV in TMLI treatment, building upon previous work that introduced a solution to this problem based on a 2D U-Net model. We extend the previous research (i) by employing the nnU-Net framework to develop both 2D and 3D U-Net models and (ii) by evaluating the trained models on the PTV with the exclusion of bones, which consist mainly of lymp-nodes and represent the most challenging region of the target volume to segment. Our result show that the introduction of nnU-NET framework led to statistically significant improvement in the segmentation performance. In addition, the analysis on the PTV after the exclusion of bones showed that the models are quite robust also on the most challenging areas of the target volume. Overall, our study is a significant step forward in the application of DL in a complex radiotherapy treatment such as TMLI, offering a viable and scalable solution to increase the number of patients who can benefit from this treatment.

Figures (9)

• Figure 1: Workflow of the radiotherapy department.
• Figure 2: Single CT image of the thoracic area with CTV and PTV labeling done by the RO (left). 3D Representation of the CTV and PTV labeling (right).
• Figure 3: Architecture of the 2D U-Net generated by the nnU-Net framework.
• Figure 4: Architecture of the 3D U-Net generated by the nnU-Net framework.
• Figure 5: Bone Subtraction Pipeline Description.