How to Segment in 3D Using 2D Models: Automated 3D Segmentation of Prostate Cancer Metastatic Lesions on PET Volumes Using Multi-angle Maximum Intensity Projections and Diffusion Models

TL;DR

This paper tackles the challenge of segmenting small PSMA-PET metastatic lesions in 3D PET/CT images, which are hindered by low signal-to-noise ratios. It introduces a two-stage approach that first segments on generated multi-angle maximum intensity projections (MA-MIPs) using a 2D denoising diffusion probabilistic model (DDPM) with a four-channel MA-MIP input, and then reconstructs a 3D segmentation via the ordered-subsets expectation maximization (OSEM) algorithm. The method demonstrates superior performance over eight state-of-the-art 3D segmentation methods across Dice, HD95, Jaccard, and volume error metrics, highlighting improved detection of small metastases and potential for quantitative metastatic burden assessment. The work advances practical 3D segmentation from 2D diffusion-based predictions on MA-MIPs, with implications for faster, more accurate analysis of PCa metastases in clinical settings, and it suggests avenues for broader validation and ablation studies.

Abstract

Prostate specific membrane antigen (PSMA) positron emission tomography/computed tomography (PET/CT) imaging provides a tremendously exciting frontier in visualization of prostate cancer (PCa) metastatic lesions. However, accurate segmentation of metastatic lesions is challenging due to low signal-to-noise ratios and variable sizes, shapes, and locations of the lesions. This study proposes a novel approach for automated segmentation of metastatic lesions in PSMA PET/CT 3D volumetric images using 2D denoising diffusion probabilistic models (DDPMs). Instead of 2D trans-axial slices or 3D volumes, the proposed approach segments the lesions on generated multi-angle maximum intensity projections (MA-MIPs) of the PSMA PET images, then obtains the final 3D segmentation masks from 3D ordered subset expectation maximization (OSEM) reconstruction of 2D MA-MIPs segmentations. Our proposed method achieved superior performance compared to state-of-the-art 3D segmentation approaches in terms of accuracy and robustness in detecting and segmenting small metastatic PCa lesions. The proposed method has significant potential as a tool for quantitative analysis of metastatic burden in PCa patients.

Figures (2)

• Figure 1: Visual explanation of how the forward and reverse processes of DDPM model works, along with the input ground truth segmentation mask during the forward process and the prior information of the anatomical/functional context during the reverse process
• Figure 2: Visual comparison of our method against SOTA on a sample case.