# Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation

Source: [Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation](<https://www.sota2.com/research/paper/6912c3492828b7cc6937e08e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-02T05:03:05.635Z

Authors: Fanding Li, Xiangyu Li, Xianghe Su, Xingyu Qiu, Suyu Dong, Wei Wang, Kuanquan Wang, Gongning Luo, Shuo Li (4 and 5) \_\_INSTITUTION\_9\_\_ Faculty of Computing, Harbin Institute of Technology, Harbin, China, (2) College of Computer, Control Engineering, Northeast Forestry University, Harbin, China, (3) Faculty of Computing, Harbin Institute of Technology, Shenzhen, China, (4) Department of Computer, Data Science, Case Western Reserve University, Cleveland, Ohio, United States, (5) Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, United States)

Published: 2025-11-10T08:57:06.000Z

## Abstract

A simultaneous enhancement of accuracy and diversity of predictions remains a challenge in ambiguous medical image segmentation (AMIS) due to the inherent trade-offs. While truncated diffusion probabilistic models (TDPMs) hold strong potential with a paradigm optimization, existing TDPMs suffer from entangled accuracy and diversity of predictions with insufficient fidelity and plausibility. To address the aforementioned challenges, we propose Ambiguity-aware Truncated Flow Matching (ATFM), which introduces a novel inference paradigm and dedicated model components. Firstly, we propose Data-Hierarchical Inference, a redefinition of AMIS-specific inference paradigm, which enhances accuracy and diversity at data-distribution and data-sample level, respectively, for an effective disentanglement. Secondly, Gaussian Truncation Representation (GTR) is introduced to enhance both fidelity of predictions and reliability of truncation distribution, by explicitly modeling it as a Gaussian distribution at $T\_{\\text{trunc}}$ instead of using sampling-based approximations. Thirdly, Segmentation Flow Matching (SFM) is proposed to enhance the plausibility of diverse predictions by extending semantic-aware flow transformation in Flow Matching (FM). Comprehensive evaluations on LIDC and ISIC3 datasets demonstrate that ATFM outperforms SOTA methods and simultaneously achieves a more efficient inference. ATFM improves GED and HM-IoU by up to $12\\%$ and $7.3\\%$ compared to advanced methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.06857>)

[PDF](<https://arxiv.org/pdf/2511.06857.pdf>)
