Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning
This addresses the problem of safer cancer quantification for medical imaging by reducing radiation exposure and eliminating reliance on CT, though it is incremental as it builds on masked autoencoder ideas.
The paper tackles organ segmentation in ultra-low-dose PET without CT annotations by proposing LDOS, a pipeline that collaborates denoising and segmentation learning, achieving state-of-the-art mean Dice scores of 73.11% and 73.97% across 18 organs at 5% dose.
Organ segmentation in Positron Emission Tomography (PET) plays a vital role in cancer quantification. Low-dose PET (LDPET) provides a safer alternative by reducing radiation exposure. However, the inherent noise and blurred boundaries make organ segmentation more challenging. Additionally, existing PET organ segmentation methods rely on coregistered Computed Tomography (CT) annotations, overlooking the problem of modality mismatch. In this study, we propose LDOS, a novel CT-free ultra-LDPET organ segmentation pipeline. Inspired by Masked Autoencoders (MAE), we reinterpret LDPET as a naturally masked version of Full-Dose PET (FDPET). LDOS adopts a simple yet effective architecture: a shared encoder extracts generalized features, while task-specific decoders independently refine outputs for denoising and segmentation. By integrating CT-derived organ annotations into the denoising process, LDOS improves anatomical boundary recognition and alleviates the PET/CT misalignments. Experiments demonstrate that LDOS achieves state-of-the-art performance with mean Dice scores of 73.11% (18F-FDG) and 73.97% (68Ga-FAPI) across 18 organs in 5% dose PET. Our code will be available at https://github.com/yezanting/LDOS.