UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation

2026-10-03

AI Summary

This study addresses the disconnect between task paradigms and data dimensionality in medical image segmentation by proposing a unified slice-based framework. The model integrates class priors, reference exemplars, user clicks, and neighborhood predictions as conditional inputs, employing a reference-conditioned prediction mechanism to coherently propagate 2D edits across 3D volumetric data. Furthermore, it reveals that volumetric segmentation propagation and contextual segmentation share a common underlying mechanism, leveraging bidirectional and 3D supervision to enhance inter-slice propagation reliability. The proposed method demonstrates superior performance across multi-modal anatomical structures, enabling efficient 3D annotation from sparse 2D initializations and significantly reducing the cost of slice-by-slice correction.

Abstract

Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed separately for semantic, in-context, and interactive segmentation, and are further specialized to either native 2D images or 3D volumetric data. In clinical practice, however, segmentation workflows take many forms: a case may be initialized by semantic prediction, reference-guided segmentation, or user interaction. Regardless of how it begins, fine-grained refinement is naturally performed on 2D views; for volumetric scans, such 2D edits must propagate coherently to the rest of the volume. We present UniPro, a unified model that bridges segmentation paradigms and data dimensionality, using propagation to extend 2D segmentation to 3D volumes. Our key insight is that volumetric propagation and in-context segmentation share the same reference-conditioned prediction mechanism, differing only in whether the reference image-mask pairs come from other cases or from previously segmented neighboring slices. Building on this view, UniPro supports semantic, in-context, interactive, and propagation-based segmentation within a single slice-based framework, using class priors, reference exemplars, user clicks, and neighboring-slice predictions as mode-specific conditioning inputs. To improve propagation reliability, UniPro further incorporates bidirectional and 3D supervision to regularize slice-wise propagation beyond per-slice losses. Extensive experiments across diverse modalities and anatomies show that UniPro achieves strong performance across all segmentation settings, enabling annotation-efficient 3D segmentation from sparse 2D initialization and reducing slice-by-slice correction effort.

Problem

• Medical Image Segmentation
• Unified Framework
• 2D-to-3D Propagation
• Multi-Mode Segmentation

Innovation

• Unified Segmentation
• Volumetric Propagation
• In-Context Segmentation
• Multi-Mode Conditioning
• 3D Supervision