RLBCD: Residual-guided Latent Brownian-bridge Co-Diffusion for Anatomical-to-Metabolic Image Synthesis

Authors: Tianxu Lv, Hongnian Tian, Jiansong Fan, Yuan Liu, Lihua Li, Xiang Pan

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on five public and in-house datasets demonstrate that RLBCD not only outperforms state-of-the-art methods for A2MIS, but also is valuable for downstream clinic applications.
Researcher Affiliation Academia 1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China 2Institute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University, Hangzhou 310018, China 3The PRC Ministry of Education Engineering Research Center of Intelligent Technology for Healthcare, Wuxi, Jiangsu 214122, China EMAIL
Pseudocode No The paper describes the methodology using text, equations, and architectural diagrams (Figures 1 and 2), but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statements about making the source code available, nor does it provide any links to code repositories.
Open Datasets Yes Initially, we conduct experiments on three datasets, including two public datasets, i.e. Head-Neck-PET-CT [Valli eres et al., 2017] and Duke-Breast-Cancer-MRI [Saha et al., 2021], as well as an in-house dataset, i.e. Chest-CTA. Subsequently, we utilize two independent datasets to assess the models generalization ability and downstream value, including a public dataset, i.e. Breast-MRI-NACT-Pilo T [Newitt and Hylton, 2016], and an in-house dataset, i.e. HUASHANCT-PET.
Dataset Splits Yes The above three datasets are split in a 7:1:2 ratio based on case-level for training, validation and testing. For the downstream diagnosis and segmentation tasks, we use a five-fold cross-validation strategy and the mean scores of results are presented.
Hardware Specification Yes The developed model is implemented using Pytorch and the experiments in this study are executed on a platform comprising four NVIDIA RTX A6000 GPUs to accelerate the training process.
Software Dependencies No The paper mentions "Pytorch" and "VQGAN" but does not provide specific version numbers for these software components.
Experiment Setup Yes We first pre-train VQGAN [Esser et al., 2021] with downsampling factor of 8 using the collected datasets. The number of time steps of Brownian bridge diffusion is set to be 1000 during the training stage, and then we employ 200 sampling steps during the sample stage with the considerations of both sample quality and efficiency following [Li et al., 2023a].