腹部CT图像上骨骼肌与脂肪组织自动分割的深度学习模型外部验证
研究用3187例腹部手术患者的L3层面CT训练深度学习神经网络自动分割内脏脂肪、皮下脂肪和骨骼肌,并在2535例腹部癌症患者中外部验证;自动与手动分割一致性高,骨骼肌、内脏脂肪、皮下脂肪中位Dice系数分别为0.97、0.98、0.95,Bland-Altman偏倚小。
要点
- 自动与手动分割一致性高:骨骼肌、内脏脂肪、皮下脂肪中位Dice系数分别为0.97、0.98、0.95。
- 一致性相关系数优秀:骨骼肌0.964、内脏脂肪0.998、皮下脂肪0.992。
- Bland-Altman偏倚小:骨骼肌辐射密度0.23 HU(0.5%),骨骼肌1.26 cm2·m-2(2.8%)。
核心结论
- 开发了性能稳健且经独立外部验证的深度学习神经网络,用于自动身体成分分析。
研究设计与样本
- 用3187例腹部手术患者L3层面CT的专家勾画分割(内脏脂肪、皮下脂肪、骨骼肌)训练深度学习神经网络;外部验证队列为2535例腹部癌症患者;以Dice相似度和Lin一致性相关系数评估性能。
诊断标准与关键数值
- 自动与手动分割中位Dice系数:骨骼肌0.97(IQR 0.95-0.98)、内脏脂肪0.98(IQR 0.95-0.98)、皮下脂肪0.95(IQR 0.92-0.97)。一致性相关系数:骨骼肌0.964(0.959-0.968)、内脏脂肪0.998(0.998-0.998)、皮下脂肪0.992(0.991-0.993)。Bland-Altman偏倚:骨骼肌辐射密度0.23 HU(0.5%)、骨骼肌1.26 cm2·m-2(2.8%)、内脏脂肪-1.02 cm2·m-2(1.7%)、皮下脂肪3.24 cm2·m-2(4.6%)。
临床应用与阅片要点
- 该深度学习神经网络经外部验证可用于大规模人群研究和推动身体成分分析进入临床实践。
局限性
- 原文未报告局限性。
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: Body composition assessment using CT images at the L3-level is increasingly applied in cancer research and has been shown to be strongly associated with long-term survival. Robust high-throughput automated segmentation is key to assess large patient cohorts and to support implementation of body composition analysis into routine clinical practice. We trained and externally validated a deep learning neural network (DLNN) to automatically segment L3-CT images.
METHODS: Expert-drawn segmentations of visceral and subcutaneous adipose tissue (VAT/SAT) and skeletal muscle (SM) of L3-CT-images of 3187 patients undergoing abdominal surgery were used to train a DLNN. The external validation cohort was comprised of 2535 patients with abdominal cancer. DLNN performance was evaluated with (geometric) dice similarity (DS) and Lin's concordance correlation coefficient.
RESULTS: There was a strong concordance between automatic and manual segmentations with median DS for SM, VAT, and SAT of 0.97 (IQR: 0.95-0.98), 0.98 (IQR: 0.95-0.98), and 0.95 (IQR: 0.92-0.97), respectively. Concordance correlations were excellent: SM 0.964 (0.959-0.968), VAT 0.998 (0.998-0.998), and SAT 0.992 (0.991-0.993). Bland-Altman metrics indicated only small and clinically insignificant systematic offsets; SM radiodensity: 0.23 Hounsfield units (0.5%), SM: 1.26 cm2.m-2 (2.8%), VAT: -1.02 cm2.m-2 (1.7%), and SAT: 3.24 cm2.m-2 (4.6%).
CONCLUSION: A robustly-performing and independently externally validated DLNN for automated body composition analysis was developed.
ADVANCES IN KNOWLEDGE: This DLNN was successfully trained and externally validated on several large patient cohorts. The trained algorithm could facilitate large-scale population studies and implementation of body composition analysis into clinical practice.
引用
- van Dijk DPJ, Volmer LF, Brecheisen R, et al. External validation of a deep learning model for automatic segmentation of skeletal muscle and adipose tissue on abdominal CT images. Br J Radiol. 2024. PMID: 39286936. doi:10.1093/bjr/tqae191
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。