用深度学习自动分析结直肠癌患者CT图像中的体成分，准确率超80%。
Deep learning-based computed tomography (CT) derived body composition classifier for colorectal cancer patients
- 用四种深度学习模型从CT图像预测肌肉/脂肪面积与密度
- 最佳模型GoogLeNet对肌肉面积误差仅4.96%，独立测试准确率达80%
- 开发网页工具实现快速分析，适合临床医生日常使用
背景：基于计算机断层扫描（CT）的体成分分析对评估癌症患者的骨骼肌面积（SMA）和骨骼肌密度（SMD）至关重要，二者是营养状态的关键指标。传统人工方法耗时且需专业技能，限制了其在临床中的常规应用。本研究为可行性与试点调查，探索深度学习驱动的自动化回归在临床流程中进行体成分分析的潜力。方法：训练四种深度学习架构（AlexNet、UNet、GoogLeNet、ResNet34），从结直肠癌患者CT图像中预测SMA、SMD、皮下脂肪面积（SFA）和内脏脂肪面积（VFA）。通过系统性超参数优化确定最优模型，并部署于网页应用以支持临床使用。结果：GoogLeNet在SMA预测中表现最佳，平均百分比误差（PE）为4.96%；AlexNet在SMD预测中达到8.12%。独立测试显示模型分类准确率达80%。网页应用输出快速一致，具备临床整合潜力。结论：经优化的深度学习模型（尤其是GoogLeNet和AlexNet）可实现高精度的CT体成分分析，平均百分比误差分别为4.96%（SMA）和8.12%（SMD），有望显著降低人工分割的时间与专业门槛。未来需在更大、更多样化的数据集中进一步验证。
原文摘要 · Abstract (English)
Background: Accurate body composition analysis using Computed Tomography (CT) scans is essential for assessing skeletal muscle area (SMA) and skeletal muscle density (SMD), key markers of nutritional status in cancer patients. Conventional manual methods are labour-intensive and require specialist expertise, limiting their routine clinical use. Therefore, this study serves as a feasibility and pilot investigation to explore the potential of deep learning-based automated regression for body composition analysis within a clinical workflow. Methods: Four deep learning architectures (AlexNet, UNet, GoogLeNet, and ResNet34) were trained to predict SMA, SMD, subcutaneous fat area (SFA), and visceral fat area (VFA) from CT scans of colorectal cancer patients. Systematic hyperparameter optimization identified the most accurate models, which were subsequently implemented in a web application for clinical use. Results: GoogLeNet achieved the best performance, with a mean percentage error (PE) of 4.96% for SMA prediction, while AlexNet reached 8.12% for SMD. Independent testing demonstrated robust accuracy, correctly classifying body composition metrics in 80% of cases. The web application delivered rapid and consistent outputs, supporting integration into clinical workflows. Conclusion: Optimized deep learning models, particularly GoogLeNet and AlexNet, can automate CT-derived body composition analysis with a Mean Percentage Error (PE) of 4.96% for SMA and 8.12% for SMD. These tools have the potential to streamline clinical practice by reducing the time and expertise required for manual segmentation. Further validation in larger, more diverse datasets is warranted.
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。