Disentangling Prompt Dependence to Evaluate Segmentation Reliability in Gynecological MRI

• URL: http://arxiv.org/abs/2603.13369v1
• Date: Mon, 09 Mar 2026 14:42:43 GMT
• Title: Disentangling Prompt Dependence to Evaluate Segmentation Reliability in Gynecological MRI
• Abstract summary: We introduce the first formulation of prompt dependence that explicitly disentangles prompt ambiguity (inter-user variability) from local sensitivity (interaction imprecision)<n>Experiments on two female pelvic MRI datasets for uterus and bladder segmentation reveal a strong negative correlation between both metrics and segmentation performance.
• Score: 0.022046427675233182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Promptable segmentation models (e.g., the Segment Anything Models) enable generalizable, zero-shot segmentation across diverse domains. Although predictions are deterministic for a fixed image-prompt pair, the robustness of these models to variations in user prompts, referred to as prompt dependence, remains underexplored. In safety-critical workflows with substantial inter-user variability, interpretable and informative frameworks are needed to evaluate prompt dependence. In this work, we assess the reliability of promptable segmentation by analyzing and measuring its sensitivity to prompt variability. We introduce the first formulation of prompt dependence that explicitly disentangles prompt ambiguity (inter-user variability) from local sensitivity (interaction imprecision), offering an interpretable view of segmentation robustness. Experiments on two female pelvic MRI datasets for uterus and bladder segmentation reveal a strong negative correlation between both metrics and segmentation performance, highlighting the value of our framework for assessing robustness. The two metrics have low mutual correlation, supporting the disentangled design of our formulation, and provide meaningful indicators of prompt-related failure modes.

Related papers

• Registration-Grounded Spectral Fusion for Unregistered WLI/NBI Endoscopic Lesion Segmentation [87.5409605461001]
  White-light imaging (WLI) and narrow-band imaging (NBI) provide complementary views of endoscopic lesions.<n>Their paired observations are often spatially misaligned due to viewpoint changes, tissue deformation, and sequential handheld acquisition.<n>We propose a reliability-aware complex-domain fusion framework for paired-but-unregistered WLI/NBI lesion segmentation.
  arXiv  Detail & Related papers  (2026-07-29T02:09:28Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• VEELA: A Clinically-Constrained Benchmark for Liver Vessel Segmentation in Computed Tomography Angiography [0.3267907805950309]
  We introduce VEELA (Vessel Extraction and Extrication for Liver Analysis), a rigorously curated vessel dataset from 40 CTA scans.<n>All vessels were manually delineated slice-by-slice under multi-expert consensus, using a strict visibility-driven annotation policy.<n>We establish a standardized benchmarking framework and analyze complementary evaluation metrics, including topology-aware (clDice), overlap-based (IoU), boundary-sensitive (NSD), and geometry-aware (area, length) measures.
  arXiv  Detail & Related papers  (2026-05-21T11:42:47Z)
• Multi-Rater Calibrated Segmentation Models [1.1043348234031376]
  We improve the probabilistic calibration of medical image segmentation models by reformulating multi-rater supervision as an ordinal learning problem.<n>Results consistently show that ordinal-aware training yields substantially improved calibration with respect to inter-rater agreement without degrading segmentation accuracy.
  arXiv  Detail & Related papers  (2026-05-04T10:35:34Z)
• Green Shielding: A User-Centric Approach Towards Trustworthy AI [19.485991712624095]
  Green Shielding is a user-centric agenda for building evidence-backed deployment guidance.<n>We instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis.<n>Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.
  arXiv  Detail & Related papers  (2026-04-27T17:04:17Z)
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability [9.522045116604358]
  Deep neural networks for medical image classification often fail to generalize consistently in clinical practice.<n>This paper examines interpretability in deep neural networks fine-tuned for fracture detection by evaluating model performance against adversarial attack.
  arXiv  Detail & Related papers  (2025-04-07T20:26:02Z)
• SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation [10.871259365539087]
  Uncertainty in medical image segmentation data can stem from imperfect image quality and variability in labeling preferences.<n>We propose textbfSPA, a new textbfSegmentation textbfPreference textbfAlignment framework that efficiently adapts to diverse test-time preferences.<n> SPA shows 1) a significant reduction in user time and effort compared to existing interactive segmentation approaches, 2) strong adaptability based on human feedback, and 3) state-of-the-art image segmentation performance across different imaging modalities and semantic labels.
  arXiv  Detail & Related papers  (2024-11-23T10:27:08Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• How are Prompts Different in Terms of Sensitivity? [50.67313477651395]
  We present a comprehensive prompt analysis based on the sensitivity of a function. We use gradient-based saliency scores to empirically demonstrate how different prompts affect the relevance of input tokens to the output. We introduce sensitivity-aware decoding which incorporates sensitivity estimation as a penalty term in the standard greedy decoding.
  arXiv  Detail & Related papers  (2023-11-13T10:52:01Z)
• SUPER-Net: Trustworthy Image Segmentation via Uncertainty Propagation in Encoder-Decoder Networks [0.17398560678845076]
  SUPER-Net is a framework for trustworthy image segmentation via uncertainty propagation.<n>It generates two outputs simultaneously: the segmented image and a pixel-wise uncertainty map.<n>Results show that SUPER-Net outperforms state-of-the-art models in robustness and accuracy.
  arXiv  Detail & Related papers  (2021-11-10T22:46:05Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition [59.52434325897716]
  We propose a solution, named DMUE, to address the problem of annotation ambiguity from two perspectives. For the former, an auxiliary multi-branch learning framework is introduced to better mine and describe the latent distribution in the label space. For the latter, the pairwise relationship of semantic feature between instances are fully exploited to estimate the ambiguity extent in the instance space.
  arXiv  Detail & Related papers  (2021-04-01T03:21:57Z)
• Analyzing Epistemic and Aleatoric Uncertainty for Drusen Segmentation in Optical Coherence Tomography Images [4.125187280299246]
  Age-related macular degeneration (AMD) is one of the leading causes of permanent vision loss in people aged over 60 years. We develop a U-Net based drusen segmentation model and quantify the segmentation uncertainty.
  arXiv  Detail & Related papers  (2021-01-21T23:34:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.