LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors

TL;DR

LightMedSeg is a lightweight, anatomy-aware 3D medical image segmentation model that combines priors and adaptive features to achieve high accuracy with minimal parameters and computational cost.

Contribution

It introduces a modular UNet-style architecture with learned spatial anchors and adaptive context modeling for efficient 3D segmentation.

Findings

Achieves near-transformer accuracy with only 0.48M parameters.

Uses 14.64 GFLOPs, significantly less than heavy transformer models.

Demonstrates strong performance on 3D medical image segmentation tasks.

Abstract

Accurate and efficient 3D medical image segmentation is essential for clinical AI, where models must remain reliable under stringent memory, latency, and data availability constraints. Transformer-based methods achieve strong accuracy but suffer from excessive parameters, high FLOPs, and limited generalization. We propose LightMedSeg, a modular UNet-style segmentation architecture that integrates anatomical priors with adaptive context modeling. Anchor-conditioned FiLM modulation enables anatomy-aware feature calibration, while a local structural prior module and texture-aware routing dynamically allocate representational capacity to boundary-rich regions. Computational redundancy is minimized through ghost and depthwise convolutions, and multi-scale features are adaptively fused via a learned skip router with anchor-relative spatial position bias. Despite requiring only 0.48M parameters and 14.64~GFLOPs, LightMedSeg achieves segmentation accuracy within a few Dice points of heavy transformer baselines. Therefore, LightMedSeg is a deployable and data-efficient solution for 3D medical image segmentation. Code will be released publicly upon acceptance.