Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI

Yongheng Sun; Yuexi Gu; Jingwen Sun; Maureen Kohi; Mingxia Liu

cs.CVOct 5, 2026

Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI

Authors: Yongheng Sun, Yuexi Gu, Jingwen Sun, Maureen Kohi, Mingxia Liu

Organizations: Department of Radiology and BRIC, UNC at Chapel Hill, Chapel Hill, NC 27599, USA

Abstract

Multi-structure segmentation of the uterus is important for computer-assisted screening, diagnosis, and treatment planning of uterine diseases, where ultrasound and MRI provide complementary clinical information. However, developing a unified model across these modalities is challenging due to their substantially different image appearances, anatomical contexts, spatial resolutions, and label spaces. Moreover, existing datasets often define different segmentation targets, making joint learning challenging and potentially leading to negative transfer across heterogeneous tasks. To this end, we propose a Topology-informed Prompt-conditioned Universal Segmentation (TPUS) framework for segmenting multiple uterine structures across ultrasound and MRI. TPUS introduces a graph-based multi-dataset backbone comprising modality-specific stems and a modality-shared graph-based encoder-decoder to support modality-sensitive input adaptation, structural feature reasoning, and joint representation learning across heterogeneous uterine segmentation tasks. In addition, TPUS uses task-aware class prompts to condition the segmentation process for different datasets and label spaces, a dynamic convolutional adaptation module to generate task-specific output responses, and a topology-informed loss to encourage anatomically consistent predictions. Experiments on a uterine ultrasound dataset and a T2-weighted uterine myoma MRI dataset demonstrate that TPUS achieves Dice scores of 0.898 and 0.693 on the two held-out test sets, respectively, outperforming several generic and universal segmentation baselines. Source code can be accessed at https://github.com/YonghengSun1997/TPUS.

Figures & tables

Figure 1: Overview of the proposed TPUS framework. (a) Modality-specific stems process input 3D US or MRI volumes. (b) The modality-shared graph-based encoder-decoder with topology blocks (TopoBlocks) extracts multi-scale features, with auxiliary heads at decoders $\mathrm{D}_{1}$ – $\mathrm{D}_{3}$ . (c) Task-aware class prompts from CLIP [ 8 ] and the $\mathrm{E}_{5}$ bottleneck condition a dynamic head at $\mathrm{D}_{4}$ for full-resolution prediction.

Figure 2: Visual comparison of segmentation results on the UterUS (top) and UMD (bottom) datasets. Shown are the input, competing methods, the proposed TPUS, and ground truth. Different colors denote distinct tissues.

Method	UterUS		UMD
Method	Dice $\uparrow$	ASSD (mm) $\downarrow$	Dice $\uparrow$	ASSD (mm) $\downarrow$
UNETR [ 3 ]	0.792 $\pm$ 0.110	0.846 ∗ $\pm$ 0.420	0.330 $\pm$ 0.199	18.899 ∗ $\pm$ 21.245
SwinUNETR [ 2 ]	0.864 $\pm$ 0.071	0.593 ∗ $\pm$ 0.304	0.347 $\pm$ 0.200	15.065 ∗ $\pm$ 20.817
CLIP-UM [ 5 ]	0.861 $\pm$ 0.054	0.637 ∗ $\pm$ 0.251	0.144 $\pm$ 0.137	19.165 ∗ $\pm$ 11.165
UniSeg [ 11 ]	0.498 $\pm$ 0.160	1.715 ∗ $\pm$ 0.513	0.599 $\pm$ 0.242	2.732 ∗ $\pm$ 4.737
DoDNet [ 12 ]	0.891 $\pm$ 0.050	0.760 ∗ $\pm$ 1.169	0.433 $\pm$ 0.197	17.143 ∗ $\pm$ 19.048

Table 1: Segmentation results on UterUS and UMD.

Configuration	Dice $\uparrow$	ASSD (mm) $\downarrow$
Base	0.677 $\pm$ 0.258	1.834 $\pm$ 4.608
Base + Prompt	0.678 $\pm$ 0.253	1.735 $\pm$ 4.128
Base + Prompt + TopoBlock	0.680 $\pm$ 0.259	1.718 $\pm$ 3.383
Base + Prompt + DynConv	0.684 $\pm$ 0.255	1.606 $\pm$ 4.787
Base + TI	0.686 $\pm$ 0.255	1.536 $\boldsymbol{\pm}$ 3.237
TPUS (Ours)	0.693 $\boldsymbol{\pm}$ 0.254	1.684 $\pm$ 4.680

Table 2: Ablation results on all 54 test cases from UMD.

Method	Dice $\uparrow$	ASSD (mm) $\downarrow$	$p$ -value
Prompt-free FiLM [ 7 ]	0.893 $\pm$ 0.048	0.456 $\pm$ 0.154	$1.72\!\times\!10^{-8}$
UniSeg-style Prompt [ 11 ]	0.893 $\pm$ 0.050	0.463 $\pm$ 0.149	$1.53\!\times\!10^{-4}$
Random Embedding	0.896 $\pm$ 0.047	0.448 $\pm$ 0.148	${1.17\!\times\!10^{-3}}$
CLIP Text Encoder (Ours)	0.898 $\boldsymbol{\pm}$ 0.050	0.432 $\boldsymbol{\pm}$ 0.156	–

Table 3: TPUS with different prompt-encoding methods on UterUS.

Explore similar work

BAP-MOS: Bandit-Based Adaptive Prompting for Boundary-Sensitive Multi-Organ Segmentation
Aug 8, 2026Satvik Praveen, Shengji Jin, Ahmed Lamidi +2Semi-Supervised Medical Image Segmentation Prostate Magnetic Resonance Imaging
Computer Science & Engineering, University of South Florida, Tampa, USA · Department of Physics and Astronomy, Stony Brook University, Stony Brook, USA
UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentation
Jul 31, 2026Bo Xu, Quanhao Zhu, Rui Lin +5Ultrasound Ultrafast
School of Software Dalian University of Technology · School of Computing Technologies RMIT University · Dalian University of Technology Affiliated Center Hospital
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
Jun 24, 2026Fangyijie Wang, Guénolé Silvestre, Ziyang Wang +1High Confidence Pseudo-Labels Semi-Supervised Learning
Research Ireland Centre for Research Training in Machine Learning · School of Medicine, University College Dublin, Dublin, Ireland · School of Computer Science, University College Dublin, Dublin, Ireland +1

Aug 8, 2026, cs.CVJ/K move · Enter open · S save

BAP-MOS: Bandit-Based Adaptive Prompting for Boundary-Sensitive Multi-Organ Segmentation

Satvik Praveen, Shengji Jin, Ahmed Lamidi, Xin Qian+1

Computer Science & Engineering, University of South Florida, Tampa, USA · Department of Physics and Astronomy, Stony Brook University, Stony Brook, USA

Semi-Supervised Medical Image Segmentation Prostate Magnetic Resonance Imaging Negative Results Preference Alignment Learning

Open paper AskPDF arXiv

Multi-organ ultrasound segmentation remains challenging when anatomically adjacent structures must be delineated jointly, as localized boundary errors can persist even when Dice scores are high. To address these challenges, we propose Boundary-Adaptive Prompting for Multi-Organ Segmentation (BAP-MOS), a closed-loop adaptive prompting framework. BAP-MOS formulates prompt selection as an organ-specific multi-armed bandit problem over box, point, and combined prompts. An outer Tree-structured Parzen Estimator (TPE) loop selects the prompt-selection parameter vector, while an inner UCB-Tuned loop adapts per-organ prompt preferences during fine-tuning using a bounded Dice--MSD--HD95 validation-probe reward. The framework further introduces an organ-scaled negative prompt ring to adapt sparse prompt geometry across anatomical scales, while keeping the image and prompt encoders frozen and updating only the mask decoder. We evaluate BAP-MOS on pooled prostate-region TRUS cohorts against U-Net, nnU-Net, MedSAM, fixed-prompt SAM/MedSAM, and adaptive policy variants. On this benchmark, BAP-MOS achieves Dice 0.982, HD95 0.482, and MSD 0.204, reducing HD95 by approximately 48% and MSD by 45% relative to the strongest conventional baseline. To verify the generalization ability of the framework, we tested it on the external PFUS1 pelvic-floor ultrasound corpus using MedSAM and its adaptive strategy variants, and the results were good. These results support adaptive prompt allocation as an effective mechanism for improving boundary-sensitive multi-organ ultrasound segmentation without modifying the foundation-model backbone. Source Code is available at: https://github.com/SatvikPraveen/BAP-MOS

Abstract

Explore similar work

BAP-MOS: Bandit-Based Adaptive Prompting for Boundary-Sensitive Multi-Organ Segmentation

UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentation

Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation