AI自动评估癌症患者肌肉量，助力早期发现恶病质。
Reliable Radiologic Skeletal Muscle Area Assessment -- A Biomarker for Cancer Cachexia Diagnosis
- 用深度学习自动分割CT图像中的肌肉区域，全程无需人工干预。
- 预测准确率高达97.8%误差仅2.48%，且能标记高风险错误结果。
- 结合临床数据可精准判断恶病质，适合肿瘤诊疗场景使用。
癌症恶病质是一种以严重肌肉萎缩为特征的常见代谢障碍，与预后差和生活质量下降密切相关。通过常规获取的CT扫描纵向监测骨骼肌面积（SMA）是识别和追踪该状况的有效方式。然而，现有工具往往缺乏完全自动化且准确性不一致，限制了其在临床流程中的应用。为此，我们开发了SMAART-AI（基于AI的骨骼肌评估自动化可靠工具），一个基于深度学习模型nnU-Net 2D的端到端自动化流程，训练数据为腰椎中段水平的CT图像，采用5折交叉验证以确保泛化性和鲁棒性。SMAART-AI引入基于不确定性的机制，用于标记高误差的SMA预测结果供专家复核，提升可靠性。我们将SMA、骨骼肌指数、BMI及临床数据整合，训练了一个多层感知机（MLP）模型，用于预测癌症诊断时的恶病质状态。在食管胃癌数据集上测试，SMAART-AI达到97.80% ± 0.93%的Dice分数，所有四组数据中与手动标注（SliceOmatic）相比，中位绝对误差为2.48%。不确定性指标（方差、熵、变异系数）与预测误差强相关（分别为0.83、0.76、0.73）。MLP模型对恶病质的预测精确率达79%，为临床提供可靠的早期诊断与干预工具。通过自动化、高精度与不确定性感知的结合，SMAART-AI弥合了研究与临床应用之间的鸿沟，为管理癌症恶病质提供了变革性方案。
原文摘要 · Abstract (English)
Cancer cachexia is a common metabolic disorder characterized by severe muscle atrophy which is associated with poor prognosis and quality of life. Monitoring skeletal muscle area (SMA) longitudinally through computed tomography (CT) scans, an imaging modality routinely acquired in cancer care, is an effective way to identify and track this condition. However, existing tools often lack full automation and exhibit inconsistent accuracy, limiting their potential for integration into clinical workflows. To address these challenges, we developed SMAART-AI (Skeletal Muscle Assessment-Automated and Reliable Tool-based on AI), an end-to-end automated pipeline powered by deep learning models (nnU-Net 2D) trained on mid-third lumbar level CT images with 5-fold cross-validation, ensuring generalizability and robustness. SMAART-AI incorporates an uncertainty-based mechanism to flag high-error SMA predictions for expert review, enhancing reliability. We combined the SMA, skeletal muscle index, BMI, and clinical data to train a multi-layer perceptron (MLP) model designed to predict cachexia at the time of cancer diagnosis. Tested on the gastroesophageal cancer dataset, SMAART-AI achieved a Dice score of 97.80% +/- 0.93%, with SMA estimated across all four datasets in this study at a median absolute error of 2.48% compared to manual annotations with SliceOmatic. Uncertainty metrics-variance, entropy, and coefficient of variation-strongly correlated with SMA prediction errors (0.83, 0.76, and 0.73 respectively). The MLP model predicts cachexia with 79% precision, providing clinicians with a reliable tool for early diagnosis and intervention. By combining automation, accuracy, and uncertainty awareness, SMAART-AI bridges the gap between research and clinical application, offering a transformative approach to managing cancer cachexia.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。