用深度学习从常规染色切片中自动量化肿瘤相关巨噬细胞，替代昂贵的免疫组化。
Deep Learning for Automated Quantification of Tumor-Associated Macrophages from H&E-Stained Slides in Diffuse Large B-Cell Lymphoma
- 基于自注意力机制的深层网络直接分析HE染色切片中的巨噬细胞。
- 高巨噬细胞密度患者生存率显著降低（死亡风险提升2.73倍）。
- 模型可替代传统检测，适合临床病理快速评估与大规模研究。
虽然已证实M2极化的肿瘤相关巨噬细胞（TAMs）是弥漫性大B细胞淋巴瘤（DLBCL）疾病侵袭性的标志，但传统的CD163免疫组化仍存在资源消耗大的问题。本研究旨在探索使用深度学习技术直接从标准苏木精-伊红染色（HE）组织切片中量化TAMs的可行性。利用包含52名DLBCL患者的标注数据集（共1,713个经IHC验证的TAM实例），评估了五种模型架构：U-Net、Swin-U-Net、Cerberus-U-Net3+、YOLOv11和HoVer-Net。结果显示，高CD163 TAM密度（>20.04%）与总体生存率显著下降（风险比2.73；95%置信区间：1.21–6.16；p=0.012）及无进展生存率下降（风险比2.88；95%置信区间：1.23–6.76；p=0.011）相关。多变量Cox比例风险模型调整IPI评分、分子亚型（按Hans算法分GCB/non-GCB）、EBV状态及年龄后，CD163 TAM密度在总体生存（风险比3.24；95%置信区间：0.94–11.15；p=0.062）和无进展生存（风险比2.41；95%置信区间：0.80–7.32；p=0.120）方面呈现预后趋势。其中，专为领域设计的Cerberus-U-Net3+具有最高召回率（0.656），而基于Transformer的Swin-U-Net在分割精度（精确率0.694，F1分数0.633）上表现最优。此外，基于Swin-U-Net预测的CD163水平显示20.8%为高低分界点，且预测值越高，总体生存率呈下降趋势（风险比2.63；95%置信区间：0.85–8.33；p=0.083）。结果表明，采用移位窗口自注意力机制的深度学习模型在可扩展性和成本效益方面具备作为IHC替代方案的潜力，可用于DLBCL中TAMs的预后评估。
原文摘要 · Abstract (English)
While M2-polarized tumor-associated macrophages (TAMs) have been established as indicators of disease aggressiveness in diffuse large B-cell lymphoma (DLBCL), traditional CD163 immunohistochemistry (IHC) remains resource-intensive. This study aims to investigate the feasibility of using deep learning to quantify TAMs directly from standard hematoxylin and eosin-stained (HE) tissue sections. Using a curated dataset of 52 patients with DLBCL, with high-resolution HE images and IHC-validated annotations (1,713 TAM instances), five architectures were evaluated: U-Net, Swin-U-Net, Cerberus-U-Net3+, YOLOv11, and HoVer-Net. High CD163 TAM density (>20.04%) was associated with significantly reduced overall survival (HR 2.73; 95% CI:1.21-6.16; p=0.012) and progression-free survival (HR 2.88; 95% CI: 1.23-6.76; p=0.011). In multivariate Cox proportional hazards analysis adjusting for IPI, molecular subtype (GCB/non-GCB per Hans algorithm), EBV status, and age, CD163 TAM density showed a prognostic trend for overall survival (HR 3.24; 95% CI: 0.94-11.15; p=0.062) and progression-free survival (HR 2.41; 95% CI: 0.80-7.32; p=0.120). Among the evaluated models, the domain-specific Cerberus-U-Net3+ achieved the highest sensitivity (Recall 0.656), while the Transformer-based Swin-U-Net demonstrated superior segmentation fidelity (Precision 0.694, F1-score 0.633). Additionally, the survival analysis based on the predicted Swin-U-Net CD163 level revealed a 20.8% cutoff point for patients with high and low CD163 levels near IHC, as well as a downward trend in overall survival among patients with higher predicted CD163 values of 2.63 (95% CI: 0.85-8.33; p=0.083). These findings suggest that deep learning architectures using shifted-window self-attention show potential as a candidate surrogate for IHC that is scalable and cost-effective for prognostic assessment of TAMs in DLBCL.
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。