深度学习用于弥漫大B细胞淋巴瘤HE染色切片中肿瘤相关巨噬细胞的自动定量
Deep Learning for Automated Quantification of Tumor-Associated Macrophages from H&E-Stained Slides in Diffuse Large B-Cell Lymphoma
AI总结：
本研究针对DLBCL，利用含52例患者的数据集评估5种深度学习模型，发现Swin-U-Net等模型可替代IHC，实现HE切片中TAMs的自动定量与预后评估。
AI中文摘要：
尽管M2型极化的肿瘤相关巨噬细胞（TAMs）已被证实是弥漫大B细胞淋巴瘤（DLBCL）疾病侵袭性的指标，但传统CD163免疫组化（IHC）检测仍资源密集。本研究旨在探究使用深度学习直接从标准苏木精-伊红（HE）染色组织切片定量TAMs的可行性。研究使用了包含52例DLBCL患者的精选数据集，该数据集配有高分辨率HE图像和经IHC验证的标注（共1713个TAM实例），评估了五种架构：U-Net、Swin-U-Net、Cerberus-U-Net3+、YOLOv11和HoVer-Net。高CD163 TAM密度（>20.04%）与显著降低的总生存期（风险比HR=2.73；95%置信区间CI：1.21-6.16；p=0.012）和无进展生存期（HR=2.88；95%CI：1.23-6.76；p=0.011）相关。在调整国际预后指数（IPI）、分子亚型（Hans算法定义的GCB/非GCB）、EB病毒（EBV）状态和年龄的多变量Cox比例风险分析中，CD163 TAM密度显示出总生存期（HR=3.24；95%CI：0.94-11.15；p=0.062）和无进展生存期（HR=2.41；95%CI：0.80-7.32；p=0.120）的预后趋势。在评估的模型中，针对该领域的Cerberus-U-Net3+达到最高灵敏度（召回率=0.656），而基于Transformer的Swin-U-Net表现出更优的分割保真度（精确率=0.694，F1分数=0.633）。此外，基于预测的Swin-U-Net得出的CD163水平的生存分析，确定了接近IHC的高低CD163水平患者的20.8% cutoff值，且预测CD163值较高的患者总生存期呈下降趋势（HR=2.63；95%CI：0.85-8.33；p=0.083）。这些发现表明，使用移位窗口自注意力的深度学习架构有望作为IHC的替代方案，可扩展且具成本效益，用于DLBCL中TAMs的预后评估。
英文摘要：
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.
