Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model

Yafei Dong, Kuang Gong

TL;DR

The effectiveness of the proposed 3D diffusion model is demonstrated in generating more accurate H&N tumor segmentation masks compared to the other reference methods.

Abstract

Head and neck (H&N) cancers are among the most prevalent types of cancer worldwide, and [18F]F-FDG PET/CT is widely used for H&N cancer management. Recently, the diffusion model has demonstrated remarkable performance in various image-generation tasks. In this work, we proposed a 3D diffusion model to accurately perform H&N tumor segmentation from 3D PET and CT volumes. The 3D diffusion model was developed considering the 3D nature of PET and CT images acquired. During the reverse process, the model utilized a 3D UNet structure and took the concatenation of PET, CT, and Gaussian noise volumes as the network input to generate the tumor mask. Experiments based on the HECKTOR challenge dataset were conducted to evaluate the effectiveness of the proposed diffusion model. Several state-of-the-art techniques based on U-Net and Transformer structures were adopted as the reference methods. Benefits of employing both PET and CT as the network input as well as further extending the diffusion model from 2D to 3D were investigated based on various quantitative metrics and the uncertainty maps generated. Results showed that the proposed 3D diffusion model could generate more accurate segmentation results compared with other methods. Compared to the diffusion model in 2D format, the proposed 3D model yielded superior results. Our experiments also highlighted the advantage of utilizing dual-modality PET and CT data over only single-modality data for H&N tumor segmentation.

Head and Neck Tumor Segmentation from [18F]F-FDG PET/CT Images Based on 3D Diffusion Model

TL;DR

The effectiveness of the proposed 3D diffusion model is demonstrated in generating more accurate H&N tumor segmentation masks compared to the other reference methods.

Abstract

Head and neck (H&N) cancers are among the most prevalent types of cancer worldwide, and [18F]F-FDG PET/CT is widely used for H&N cancer management. Recently, the diffusion model has demonstrated remarkable performance in various image-generation tasks. In this work, we proposed a 3D diffusion model to accurately perform H&N tumor segmentation from 3D PET and CT volumes. The 3D diffusion model was developed considering the 3D nature of PET and CT images acquired. During the reverse process, the model utilized a 3D UNet structure and took the concatenation of PET, CT, and Gaussian noise volumes as the network input to generate the tumor mask. Experiments based on the HECKTOR challenge dataset were conducted to evaluate the effectiveness of the proposed diffusion model. Several state-of-the-art techniques based on U-Net and Transformer structures were adopted as the reference methods. Benefits of employing both PET and CT as the network input as well as further extending the diffusion model from 2D to 3D were investigated based on various quantitative metrics and the uncertainty maps generated. Results showed that the proposed 3D diffusion model could generate more accurate segmentation results compared with other methods. Compared to the diffusion model in 2D format, the proposed 3D model yielded superior results. Our experiments also highlighted the advantage of utilizing dual-modality PET and CT data over only single-modality data for H&N tumor segmentation.
Paper Structure (16 sections, 10 equations, 5 figures, 5 tables)

This paper contains 16 sections, 10 equations, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Diffusion Models
  4. Network Structure
  5. Dataset and Prepocessing
  6. Reference Methods
  7. Implementation Details
  8. Data Analysis
  9. Results
  10. Comparison with Reference Methods
  11. Comparison with 2D DDPM
  12. Comparison with Single Modality-Based Segmentations
  13. Comparison of Uncertainty from DDPM-based Methods
  14. Discussion
  15. Conclusion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Graphic illustration for our proposed 3D diffusion model. In the forward process, small amounts of Gaussian noise were added to the 3D tumor masks. In the reverse process, the model took 3D [$^{18}$F]F-FDG-PET, CT, and Gaussian distribution volumes as input and restored the 3D tumor masks step by step.
  • Figure 2: Three views of the H&N segmentation results generated by different methods.
  • Figure 3: Three views of H&N segmentation results from the diffusion models in 2D and 3D forms.
  • Figure 4: Three views of H&N segmentation results from the 3D diffusion models with different input modalities.
  • Figure 5: Three views of the uncertainty maps of H&N tumor segmentation results from different DDPM-based methods.