# Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusion Source: [Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusion]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:57:07.651Z Authors: Meng Zheng, Benjamin Planche, Zhongpai Gao, Terrence Chen, Richard J. Radke, Ziyan Wu Published: 2024-08-26T17:15:37.000Z ## Abstract Conventional 3D medical image segmentation methods typically require learning heavy 3D networks (e.g., 3D-UNet), as well as large amounts of in-domain data with accurate pixel/voxel-level labels to avoid overfitting. These solutions are thus extremely time- and labor-expensive, but also may easily fail to generalize to unseen objects during training. To alleviate this issue, we present MSFSeg, a novel few-shot 3D segmentation framework with a lightweight multi-surrogate fusion (MSF). MSFSeg is able to automatically segment unseen 3D objects/organs (during training) provided with one or a few annotated 2D slices or 3D sequence segments, via learning dense query-support organ/lesion anatomy correlations across patient populations. Our proposed MSF module mines comprehensive and diversified morphology correlations between unlabeled and the few labeled slices/sequences through multiple designated surrogates, making it able to generate accurate cross-domain 3D segmentation masks given annotated slices or sequences. We demonstrate the effectiveness of our proposed framework by showing superior performance on conventional few-shot segmentation benchmarks compared to prior art, and remarkable cross-domain cross-volume segmentation performance on proprietary 3D segmentation datasets for challenging entities, i.e., tubular structures, with only limited 2D or 3D labels. ## 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. - [Few-Shot 3D Volumetric Segmentation on Abdomen-CT Setting 2](): Few-Shot 3D Volumetric Segmentation; Abdomen-CT Setting 2; Dice (LK): 85.73. - [Few-Shot 3D Volumetric Segmentation on CHAOS-MRI Setting 2](): Few-Shot 3D Volumetric Segmentation; CHAOS-MRI Setting 2; Dice (Kidney L): 87.7. - [Few-Shot 3D Volumetric Segmentation on Abdomen-CT Setting 1](): Few-Shot 3D Volumetric Segmentation; Abdomen-CT Setting 1; Dice (LK): 87.22. - [Few-Shot 3D Volumetric Segmentation on CHAOS-MRI Setting 1](): Few-Shot 3D Volumetric Segmentation; CHAOS-MRI Setting 1; Dice Score (LK): 88.63. ## Original sources and implementation [Original paper]() [PDF]()