arXiv AI October 5, 2026 By Yuxuan Ou, Konstantinos Kamnitsas, OxAAA Study, AICT Consortium, Regent Lee, Vicente Grau

Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis

The paper investigates whether uncertainty can act as a proxy for semantic correctness in diffusion-based medical image synthesis, specifically for generating contrast‑enhanced CT (CECT) from non‑contrast CT (NCCT). Using the AortaDiff framework, which produces both CECT images and lumen segmentations, the authors compare six uncertainty estimation methods across pixel, region, and image levels, including their ability to detect out‑of‑distribution cases. They find that uncertainty is informative at all spatial scales, remains useful under distribution shift, and that MCDropout, in particular, offers reliable quality filtering with no extra training cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 16

MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis

arXiv:2609.17169v1 Announce Type: cross Abstract: Forecasting anatomical changes such as tumor growth and neurodegeneration is a challenging generative vision task. Morphological evolution is subtle...

By Anna Oliveras, Roger Mar\'i, Rafael Redondo, Oriol Guardi\`a, Cynthia Ifeyinwa Ugwu, Ana Tost, Bhalaji Nagarajan, Carolina Migliorelli, Vicent Ribas, Petia Radeva

diffusion benchmarks

arXiv AI

Jul 8

Volumetric Directional Diffusion: Anchoring Uncertainty Quantification in Anatomical Consensus for Ambiguous Medical Image Segmentation

arXiv:2603. 04024v2 Announce Type: replace-cross Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible.

By Chao Wu, Mahesh Bhosale, Kangxian Xie, Pouya Karimian, David Doermann, Mingchen Gao

diffusion computer-vision safety

arXiv AI

Jul 14

SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation

arXiv:2604. 15271v3 Announce Type: replace-cross Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support.

By Tianhao Fu, Austin Wang, Charles Chen, Roby Aldave-Garza, Yucheng Chen

computer-vision

arXiv Machine Learning

Jul 28

Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation

arXiv:2607. 22727v1 Announce Type: cross Abstract: Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can be quiet: sensor noise, patient motion, low- resolution acquisition, and contrast variability may all alter model behavior without producing an obvious warning.

By Pranav Kaliaperumal, Manisha Kaliaperumal

computer-vision multimodal benchmarks safety

arXiv Machine Learning

Aug 18

Beyond Boundary Noise: Aggregated Aleatoric Uncertainty Fails to Capture Presence Ambiguity in 3D Lung Nodule Segmentation

arXiv:2608. 14766v1 Announce Type: cross Abstract: Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretically designed to capture irreducible data ambiguity.

By Simon Baur, Arne Schernich, Ekin B\"oke, Wojciech Samek, Jackie Ma

computer-vision safety

arXiv Computer Vision

2d ago

Scalable next-scale autoregression for medical image generation across anatomical regions

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

llms diffusion computer-vision nlp

One email a morning, machine-written

Related stories

MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis

Volumetric Directional Diffusion: Anchoring Uncertainty Quantification in Anatomical Consensus for Ambiguous Medical Image Segmentation

SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation

Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation

Beyond Boundary Noise: Aggregated Aleatoric Uncertainty Fails to Capture Presence Ambiguity in 3D Lung Nodule Segmentation

Scalable next-scale autoregression for medical image generation across anatomical regions