Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Comparative Analysis of nnUNet and MedNeXt for Head and Neck Tumor Segmentation in MRI-guided Radiotherapy

Nikoo Moradi, André Ferreira, Behrus Puladi, Jens Kleesiek, Emad Fatemizadeh, Gijs Luijten, Victor Alves, Jan Egger

TL;DR

This study utilized the HNTS-MRG2024 dataset, which consists of 150 MRI scans from patients diagnosed with HNC, including original and registered pre-RT and mid-RT T2-weighted images with corresponding segmentation masks for GTVp and GTVn, and employed two state-of-the-art models in deep learning, nnUNet and MedNeXt.

Abstract

Radiation therapy (RT) is essential in treating head and neck cancer (HNC), with magnetic resonance imaging(MRI)-guided RT offering superior soft tissue contrast and functional imaging. However, manual tumor segmentation is time-consuming and complex, and therfore remains a challenge. In this study, we present our solution as team TUMOR to the HNTS-MRG24 MICCAI Challenge which is focused on automated segmentation of primary gross tumor volumes (GTVp) and metastatic lymph node gross tumor volume (GTVn) in pre-RT and mid-RT MRI images. We utilized the HNTS-MRG2024 dataset, which consists of 150 MRI scans from patients diagnosed with HNC, including original and registered pre-RT and mid-RT T2-weighted images with corresponding segmentation masks for GTVp and GTVn. We employed two state-of-the-art models in deep learning, nnUNet and MedNeXt. For Task 1, we pretrained models on pre-RT registered and mid-RT images, followed by fine-tuning on original pre-RT images. For Task 2, we combined registered pre-RT images, registered pre-RT segmentation masks, and mid-RT data as a multi-channel input for training. Our solution for Task 1 achieved 1st place in the final test phase with an aggregated Dice Similarity Coefficient of 0.8254, and our solution for Task 2 ranked 8th with a score of 0.7005. The proposed solution is publicly available at Github Repository.

Comparative Analysis of nnUNet and MedNeXt for Head and Neck Tumor Segmentation in MRI-guided Radiotherapy

TL;DR

This study utilized the HNTS-MRG2024 dataset, which consists of 150 MRI scans from patients diagnosed with HNC, including original and registered pre-RT and mid-RT T2-weighted images with corresponding segmentation masks for GTVp and GTVn, and employed two state-of-the-art models in deep learning, nnUNet and MedNeXt.

Abstract

Radiation therapy (RT) is essential in treating head and neck cancer (HNC), with magnetic resonance imaging(MRI)-guided RT offering superior soft tissue contrast and functional imaging. However, manual tumor segmentation is time-consuming and complex, and therfore remains a challenge. In this study, we present our solution as team TUMOR to the HNTS-MRG24 MICCAI Challenge which is focused on automated segmentation of primary gross tumor volumes (GTVp) and metastatic lymph node gross tumor volume (GTVn) in pre-RT and mid-RT MRI images. We utilized the HNTS-MRG2024 dataset, which consists of 150 MRI scans from patients diagnosed with HNC, including original and registered pre-RT and mid-RT T2-weighted images with corresponding segmentation masks for GTVp and GTVn. We employed two state-of-the-art models in deep learning, nnUNet and MedNeXt. For Task 1, we pretrained models on pre-RT registered and mid-RT images, followed by fine-tuning on original pre-RT images. For Task 2, we combined registered pre-RT images, registered pre-RT segmentation masks, and mid-RT data as a multi-channel input for training. Our solution for Task 1 achieved 1st place in the final test phase with an aggregated Dice Similarity Coefficient of 0.8254, and our solution for Task 2 ranked 8th with a score of 0.7005. The proposed solution is publicly available at Github Repository.

Paper Structure

This paper contains 19 sections, 2 equations, 3 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Task 1:
  3. Task 2:
  4. Materials and Methods
  5. Dataset
  6. HNTS-MRG24 Dataset:
  7. BraTS24 Meningioma Radiotherapy Dataset:
  8. Networks
  9. nnUNet:
  10. MedNeXt:
  11. Ensemble strategy
  12. Methodology
  13. Task 1:
  14. Task 2:
  15. Evaluation
  16. ...and 4 more sections

Figures (3)

  • Figure 1: A sample pre-RT image (Case 78) with its corresponding segmentation. The green label represents GTVp (label=1), while the yellow label represents GTVn (label=2). The images show axial, coronal, and sagittal views, along with a 3D rendering of the segmented tumors.
  • Figure 2: Comparison of predicted segmentations of two pre-RT samples (Case 78 and 166) for Task 1. The left image shows the prediction from MedNeXt with the best DSC${\text{agg}}$, the middle image shows the prediction from the average ensemble of nnUNet and MedNeXt, which had the lowest DSC${\text{agg}}$, and the right image shows the ground truth segmentation. The green label represents GTVp (label=1), and the yellow label represents GTVn (label=2).
  • Figure 3: Comparison of segmentation predictions of sample mid-RT (Case 78 and 166) for Task 2. The left image shows the prediction from ensemble of nnUNet Cascade and FullRes with the best DSCagg, the middle image shows the prediction from the average ensemble of nnUNet and MedNeXt, which had the lowest DSCagg, and the right image shows the ground truth segmentation. The green label represents GTVp (label=1), and the yellow label represents GTVn (label=2).