The paper introduces MedSegLatDiff, a diffusion-based framework that combines a variational autoencoder (VAE) with a latent diffusion model for medical image segmentation. By compressing images into a low-dimensional latent space, the method reduces noise and speeds up training, while a weighted cross‑entropy loss preserves tiny structures such as small nodules. Evaluated on ISIC‑2018, CVC‑Clinic, and LIDC‑IDRI datasets, MedSegLatDiff achieves state‑of‑the‑art Dice and IoU scores, generates diverse segmentation hypotheses, and produces confidence maps that enhance interpretability and reliability for clinical deployment.
By Ngoc Huynh Trinh, Hai Toan Nguyen, Son Ba Luong, Quoc Long Tran
arXiv:2602.14512v3 Announce Type: replace
Abstract: Autoregressive pretraining has been key to the scalability of large language models, yet medical generative foundation models remain predominantly...
By Zhicheng He, Yunpeng Zhao, Junde Wu, Ziwei Niu, Ziyue Wang, Bohan Li, Zijun Li, Lanfen Lin, Nan Liu, Yueming Jin
We introduce TCAM-Diff, a novel 3D medical image generation model that reduces the memory requirements to encode and generate high-resolution 3D data. This model utilizes a decoder-only autoencoder method to learn triplane representation from dense volume and leverages generalization operations to prevent overfitting.
The paper introduces DiffPT, a diffusion‑based pretraining method for classifier backbones aimed at improving performance when training data is scarce. Experiments on time‑series, natural image, and medical imaging datasets show that DiffPT outperforms many self‑supervised baselines, especially in low‑data regimes for medical and time‑series tasks. While contrastive pretraining remains superior on CIFAR‑10 and Tiny ImageNet, DiffPT offers a simple and effective alternative across diverse modalities.
By Qinyu Li, Yee Whye Teh, Chris Holmes, Joel Jaskari
arXiv:2504. 19621v2 Announce Type: replace Abstract: Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since biases may negatively impact generalization performance.
By Haroui Ma, Francesco Quinzan, Theresa Willem, Stefan Bauer
arXiv:2606. 14759v1 Announce Type: cross Abstract: Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models.
By Yiheng Cao (SyCoIA - IMT Mines Al\`es), Gustavo Andrade-Miranda (SyCoIA - IMT Mines Al\`es), Jiatian Zhang, Guillaume Sall\'e, Xin Gao
arXiv:2607. 02998v2 Announce Type: replace-cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning.
By Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
arXiv:2609.24691v1 Announce Type: new
Abstract: Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the late...
By Niklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa, Julian McGinnis, Jiancheng Yang, Daniel Rueckert, Jiazhen Pan
arXiv:2607. 05319v1 Announce Type: cross Abstract: We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures.
By Rajat Rasal, Avinash Kori, Tian Xia, Ben Glocker
The paper introduces a counterfactual data augmentation method that generates healthy mammograms by inpainting lesions with realistic normal tissue using a Denoising Diffusion Probabilistic Model and a RePaint-based sampling strategy. The generated healthy counterfactuals preserve patient-specific anatomy and match the quality of the original dataset, as confirmed by similarity metrics and radiologist assessment. When applied to four different classifier architectures on the VinDr-Mammo dataset, the augmentation improves sensitivity, especially at 80% fixed specificity, thereby enhancing the reliability of computer-aided breast cancer screening systems.
By In\^es Cruchinho Garcia, Mariana Mour\~ao, Francisco Maria Calisto, Carlos Santiago, Jacinto Nascimento
The paper introduces a 3D-CLIP encoder trained with structured hard negatives to improve vision‑language alignment for text‑to‑CT generation. This encoder drives a latent diffusion model that operates directly in 3D latent space, eliminating spatial artifacts from super‑resolution pipelines. Experiments on the CT‑RATE dataset show state‑of‑the‑art image fidelity and factual correctness across 18 pathological conditions, with lower inference time and GPU memory usage than competing methods.
By Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Paolo Soda, Valerio Guarrasi
arXiv:2605. 31162v1 Announce Type: cross Abstract: Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored.
By Shreyansh Modi, Akshat Tomar, Aarush Aggarwal