PO.BCS02.02 · 生物信息与计算
使用基于注意力的深度学习框架从横纹肌肉瘤全切片图像检测PAX3/7::FOXO1融合并预测转录组：一项多机构研究
PAX3/7::FOXO1 fusion detection and transcriptomic prediction from whole-slide images of rhabdomyosarcoma using attention-based deep learning frameworks: A multi-institutional study
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
背景：横纹肌肉瘤（RMS）是一种高度恶性的儿童软组织肉瘤，其分子亚型分类，特别是PAX3/7::FOXO1融合状态，决定预后和治疗。然而，基于组织学的诊断方法仍受限于主观性和全面分子注释的稀缺。为克服这些挑战，我们改进了先前报道的用于从全切片图像（WSI）预测PAX3/7::FOXO1融合状态的卷积神经网络学习模型，并额外训练了从组织学推断基因表达谱的模型，从而将形态学与转录组特征联系起来。方法：来自三个来源的共826张独立WSI[儿童肿瘤协作组（COG）生物样本库方案=322，Kids First（KIDS）=252，儿童癌症数据倡议/分子表征倡议（CCDI/MCI）=252]被用于训练和评估一个使用UNI2-h基础特征进行融合分类的基于注意力的多示例学习（ABMIL）模型。对于基因表达预测，使用135张与bulk RNA-seq数据配对的RMS WSI来微调一个SEQUOIA transformer模型，该模型在TCGA UCEC/COAD数据集上训练。模型性能采用Matthews相关系数（MCC）、AUC和Pearson's r相关性进行评估，并通过通路富集分析进行生物学验证。结果：融合检测模型在各独立测试队列中取得了稳健且可泛化的性能（MCC≥0.80，AUC≥0.94），多机构训练改善了外部泛化能力（MCC最高达0.84）。基因表达模型可靠地从WSI预测bulk转录组谱（平均r>0.6，p<0.05），识别出包括细胞周期和肌肉发育在内的具有生物学意义的通路。这些模型共同证明了整合形态学影像数据以获取仅凭组织学无法获得的分子洞见的可行性。结论：本工作提出了首个经大规模验证的深度学习框架，可在RMS中同时进行分子亚型分类和转录组推断。通过将数字病理学与分子预测相结合，我们的方法为推进RMS精准肿瘤学提供了一种可扩展、节省组织且可泛化的工具。
查看英文原文 English abstract
Background: Rhabdomyosarcoma (RMS) is a highly malignant pediatric soft-tissue sarcoma where molecular subtyping, particularly PAX3/7::FOXO1 fusion status, drives prognosis and treatment. However, histology-based diagnostic approaches remain limited by subjectivity and the scarcity of comprehensive molecular annotations. To overcome these challenges, we improved our previously reported convolutional neural network learning models that predict PAX3/7::FOXO1 fusion status from whole-slide images (WSIs) while additionally trained models to infer gene expression profiles from histology, thereby linking morphology to transcriptomic signatures. Methods: A total of 826 independent WSIs from three sources [Children's Oncology Group (COG) biobanking protocols = 322, Kids First (KIDS) = 252, Childhood Cancer Data Initiative/Molecular Characterization Initiative (CCDI/MCI) = 252] were used to train and evaluate an Attention-Based Multiple Instance Learning (ABMIL) model using UNI2-h foundation features for fusion classification. For gene expression prediction, 135 RMS WSIs paired with bulk RNA-seq data were used to fine-tune a SEQUOIA transformer model, which was trained on TCGA UCEC/COAD datasets. Model performance was evaluated using the Matthews Correlation Coefficient (MCC), AUC, and Pearson's r correlation, with biological validation through pathway enrichment analysis. Results: The fusion detection model achieved robust and generalizable performance across independent test cohorts (MCC ≥ 0.80, AUC ≥ 0.94), with multi-institutional training improving external generalization (MCC up to 0.84). The gene expression model reliably predicted bulk transcriptomic profiles from WSIs (mean r > 0.6, p < 0.05), identifying biologically meaningful pathways including cell cycle and muscle development. Together, these models demonstrate the feasibility of integrating morphological imaging data to gain molecular insights that would not be possible with histology alone. Conclusions: This work presents the first large-scale validated deep learning framework for simultaneous molecular subtyping and transcriptomic inference in RMS. By combining digital pathology with molecular prediction, our approach offers a scalable, tissue-sparing, and generalizable tool for advancing precision oncology in RMS.
利益披露 Disclosure
D. Ziaei, None..
H. Jung, None..
P. J. Lupo, None..
P. Sok, None..
J. F. Shern, None..
C. M. Linardic, None..
S. A. Bukhari, None..
H. Chou, None..
J. S. Wei, None..
C. Lisle, None..
U. Mudunuri, None..
J. Khan, None.