Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)最新文献

Neural Autoregressive Modeling of Brain Aging. 脑老化的神经自回归模型。

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea) Pub Date : 2026-01-01 Epub Date: 2025-09-25 DOI: 10.1007/978-3-032-05472-2_33

Ridvan Yesiloglu, Wei Peng, Md Tauhidul Islam, Ehsan Adeli

{"title":"Neural Autoregressive Modeling of Brain Aging.","authors":"Ridvan Yesiloglu, Wei Peng, Md Tauhidul Islam, Ehsan Adeli","doi":"10.1007/978-3-032-05472-2_33","DOIUrl":"10.1007/978-3-032-05472-2_33","url":null,"abstract":"Brain aging synthesis is a critical task with broad applications in clinical and computational neuroscience. The ability to predict the future structural evolution of a subject's brain from an earlier MRI scan provides valuable insights into aging trajectories. Yet, the high-dimensionality of data, subtle changes of structure across ages, and subject-specific patterns constitute challenges in the synthesis of the aging brain. To overcome these challenges, we propose NeuroAR, a novel brain aging simulation model based on generative autoregressive transformers. NeuroAR synthesizes the aging brain by autoregressively estimating the discrete token maps of a future scan from a convenient space of concatenated token embeddings of a previous and future scan. To guide the generation, it concatenates into each scale the subject's previous scan, and uses its acquisition age and the target age at each block via cross-attention. We evaluate our approach on both the elderly population and adolescent subjects, demonstrating superior performance over state-of-the-art generative models, including latent diffusion models (LDM) and generative adversarial networks, in terms of image fidelity. Furthermore, we employ a pre-trained age predictor to further validate the consistency and realism of the synthesized images with respect to expected aging patterns. NeuroAR significantly outperforms key models, including LDM, demonstrating its ability to model subject-specific brain aging trajectories with high fidelity.","PeriodicalId":521129,"journal":{"name":"Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)","volume":"16128 ","pages":"341-350"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13035358/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147597727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Latent Causal Modeling for 3D Brain MRI Counterfactuals. 三维脑MRI反事实的潜在因果建模。

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea) Pub Date : 2026-01-01 Epub Date: 2025-09-25 DOI: 10.1007/978-3-032-05472-2_19

Wei Peng, Tian Xia, Fabio De Sousa Ribeiro, Tomas Bosschieter, Ehsan Adeli, Qingyu Zhao, Ben Glocker, Kilian M Pohl

{"title":"Latent Causal Modeling for 3D Brain MRI Counterfactuals.","authors":"Wei Peng, Tian Xia, Fabio De Sousa Ribeiro, Tomas Bosschieter, Ehsan Adeli, Qingyu Zhao, Ben Glocker, Kilian M Pohl","doi":"10.1007/978-3-032-05472-2_19","DOIUrl":"10.1007/978-3-032-05472-2_19","url":null,"abstract":"The number of samples in structural brain MRI studies is often too small to properly train deep learning models. Generative models show promise in addressing this issue by effectively learning the data distribution and generating high-fidelity MRI. However, they struggle to produce diverse, high-quality data outside the distribution defined by the training data. One way to address the issue is using causal models developed for 3D volume counterfactuals. However, accurately modeling causality in high-dimensional spaces is a challenge so that these models generally generate 3D brain MRIS of lower quality. To address these challenges, we propose a two-stage method that constructs a Structural Causal Model (SCM) within the latent space. In the first stage, we employ a VQ-VAE to learn a compact embedding of the MRI volume. Subsequently, we integrate our causal model into this latent space and execute a three-step counterfactual procedure using a closed-form Generalized Linear Model (GLM). Our experiments conducted on real-world high-resolution MRI data (1mm) provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) demonstrate that our method can generate high-quality 3D MRI counterfactuals.","PeriodicalId":521129,"journal":{"name":"Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)","volume":"16128 ","pages":"192-201"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12988853/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147470770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of 3D Counterfactual Brain MRI Generation. 三维反事实脑MRI生成的评价。

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea) Pub Date : 2026-01-01 Epub Date: 2025-09-25 DOI: 10.1007/978-3-032-05472-2_5

Pengwei Sun, Wei Peng, Lun Yu Li, Yixin Wang, Kilian M Pohl

{"title":"Evaluation of 3D Counterfactual Brain MRI Generation.","authors":"Pengwei Sun, Wei Peng, Lun Yu Li, Yixin Wang, Kilian M Pohl","doi":"10.1007/978-3-032-05472-2_5","DOIUrl":"10.1007/978-3-032-05472-2_5","url":null,"abstract":"Counterfactual generation offers a principled framework for simulating hypothetical changes in medical imaging, with potential applications in understanding disease mechanisms and generating physiologically plausible data. However, generating realistic structural 3D brain MRIs that respect anatomical and causal constraints remains challenging due to data scarcity, structural complexity, and the lack of standardized evaluation protocols. In this work, we convert six generative models into 3D counterfactual approaches by incorporating an anatomy-guided framework based on a causal graph, in which regional brain volumes serve as direct conditioning inputs. Each model is evaluated with respect to composition, reversibility, realism, effectiveness and minimality on T1-weighted brain MRIs (T1w MRIs) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). In addition, we test the generalizability of each model with respect to T1w MRIs of the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA). Our results indicate that anatomically grounded conditioning successfully modifies the targeted anatomical regions; however, it exhibits limitations in preserving non-targeted structures. Beyond laying the groundwork for more interpretable and clinically relevant generative modeling of brain MRIs, this benchmark highlights the need for novel architectures that more accurately capture anatomical interdependencies. Code: https://github.com/pengwei2000/counterfactual_3DMRI.","PeriodicalId":521129,"journal":{"name":"Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)","volume":"16128 ","pages":"46-56"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13012881/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147523848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models. RealDeal：通过图像到图像扩散模型增强大脑图像生成的真实感和细节。

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea) Pub Date : 2026-01-01 Epub Date: 2025-09-25 DOI: 10.1007/978-3-032-05472-2_15

Shen Zhu, Yinzhu Jin, Tyler Spears, Ifrah Zawar, P Thomas Fletcher

{"title":"RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models.","authors":"Shen Zhu, Yinzhu Jin, Tyler Spears, Ifrah Zawar, P Thomas Fletcher","doi":"10.1007/978-3-032-05472-2_15","DOIUrl":"10.1007/978-3-032-05472-2_15","url":null,"abstract":"Generative models have been widely adopted in the biomedical domain, especially in image generation applications. Latent diffusion models achieve state-of-the-art results in generating brain MRIs. However, due to latent compression, generated images from these models are overly smooth, lacking fine anatomical structures and scan acquisition noise that are typically seen in real images. We propose image-to-image diffusion models that are designed to enhance the realism and details of generated brain images by introducing sharp edges, fine textures, subtle anatomical features, and imaging noise. This work formulates the realism enhancing and detail adding process as an image-to-image diffusion model, which refines the quality of LDM-generated images. We employ commonly used metrics like FID and LPIPS for image realism assessment. Furthermore, we introduce new metrics to quantify the improved realism of images generated by RealDeal in terms of image noise distribution, sharpness, and texture.","PeriodicalId":521129,"journal":{"name":"Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)","volume":"16128 ","pages":"151-160"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12658453/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145650816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0