多模态大语言模型在MRI上零样本分割软组织肉瘤并测量肿瘤直径
本研究回顾性使用TCIA公开数据集中51例经病理证实的软组织肉瘤患者MRI图像,评估Gemini 3.0的零样本分割及直接估测肿瘤直径能力。以放射科医师手动分割为参考,分割DSC均值为0.935±0.082,分割衍生测量的组内相关系数0.976,显著高于直接估测的0.922。结论为基于自动分割的定量测量比模型直接估测更可靠。
要点
- 基于分割掩膜测量肿瘤直径优于直接让模型估测,建议优先采用分割后测量流程
- 模型分割与医师间一致性接近,但自动分割结果仍需医师逐层审核确认
- 测量前需确认输入为脂肪抑制T2WI或STIR序列,其他序列泛化能力未知
核心结论
- Gemini 3.0对软组织肉瘤MRI零样本分割达到较高精度,基于自动分割的直径测量显著优于模型直接估测。
研究设计与样本
- 回顾性研究,使用公开数据集TCIA共51例组织学确诊软组织肉瘤患者,平均年龄54.8±17.0岁,男性24例、女性27例。
- 由Gemini 3.0在脂肪抑制T2加权或STIR图像上执行零样本病灶分割与直接直径估计,参考标准为认证放射科医师手动分割与测量。
关键影像表现/征象
- Gemini分割掩膜与手动分割的DSC均值为0.935±0.082,与医师间一致性0.949±0.037相近,重复性DSC为0.981±0.038。
- 分割衍生测量组内相关系数ICC为0.976,高于直接估测ICC 0.922,差异有统计学意义p=0.027。
- Bland-Altman分析显示分割法平均偏倚为-0.5 mm,小于直接估测的-5.0 mm。
诊断标准与关键数值
- 零样本分割评估指标为Dice相似系数,以认证放射科医师手动分割为参考标准。
- 基于分割的肿瘤直径测量ICC为0.976,直接估计ICC为0.922,两种自动测量方法经Bootstrap比较p=0.027。
- 分割法测量平均偏倚-0.5 mm,直接估计法平均偏倚-5.0 mm。
临床应用与阅片要点
- 对脂肪抑制T2WI或STIR上的软组织肉瘤可尝试使用多模态大语言模型自动勾画,但建议医师复核分割边界
- 肿瘤径线测量优先从模型生成的分割掩膜提取,避免依赖大语言模型直接输出测量数值
局限性
- 回顾性单中心公开数据集,样本量51例,未报告外部独立验证集结果。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: To evaluate the zero-shot capabilities of a multimodal deep learning model (Gemini 3.0) in segmenting Soft Tissue Sarcomas (STS) on MRI and to compare the accuracy of tumor diameter measurements derived from automated segmentation versus direct model estimation.
METHODS: This retrospective study utilized a public dataset (The Cancer Imaging Archive) consisting of 51 patients (mean age, 54.8 ± 17.0 years; 24 men, 27 women) with histologically confirmed STS. Gemini 3.0 performed zero-shot lesion segmentation and direct diameter estimation on a fat-suppressed T2-weighted or STIR image. Segmentation accuracy was evaluated using the Dice similarity coefficient (DSC) against manual segmentation by a board-certified radiologist. Tumor diameters derived from Gemini segmentation masks and direct estimates were compared with manual measurements using intraclass correlation coefficients (ICC) and Bland-Altman analysis. Bootstrap analysis was performed to compare the performance of the two automated measurement methods.
RESULTS: Gemini generated segmentation masks with a mean DSC of 0.935 ± 0.082, comparable to inter-radiologist agreement (0.949 ± 0.037) and showing high reproducibility (DSC, 0.981 ± 0.038). For tumor size assessment, the segmentation-derived measurement yielded an ICC of 0.976, significantly higher than the direct estimation ICC of 0.922 (p = 0.027). Bland-Altman analysis revealed a smaller mean bias for the segmentation-based approach (-0.5 mm) compared with direct estimation (-5.0 mm).
CONCLUSIONS: Gemini 3.0 achieved high accuracy in zero-shot segmentation of STS on MRI. Deriving quantitative measurements from automated segmentation proved significantly more reliable than direct size estimation by the large language model.
引用
- Sugawara, Kato, Takada, et al. Zero-shot segmentation and tumor diameter measurement of soft tissue sarcomas on MRI using a multimodal large language model. Skeletal Radiol. 2026. PMID: 42573778. doi:10.1007/s00256-026-05335-8
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。