Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA, 94305, USA.
Internet Technology and Data Science Lab (IDLab), Ghent University, Ghent, 9052, Belgium.
Nat Commun. 2024 Nov 14;15(1):9886. doi: 10.1038/s41467-024-54182-5.
Cancer is a heterogeneous disease requiring costly genetic profiling for better understanding and management. Recent advances in deep learning have enabled cost-effective predictions of genetic alterations from whole slide images (WSIs). While transformers have driven significant progress in non-medical domains, their application to WSIs lags behind due to high model complexity and limited dataset sizes. Here, we introduce SEQUOIA, a linearized transformer model that predicts cancer transcriptomic profiles from WSIs. SEQUOIA is developed using 7584 tumor samples across 16 cancer types, with its generalization capacity validated on two independent cohorts comprising 1368 tumors. Accurately predicted genes are associated with key cancer processes, including inflammatory response, cell cycles and metabolism. Further, we demonstrate the value of SEQUOIA in stratifying the risk of breast cancer recurrence and in resolving spatial gene expression at loco-regional levels. SEQUOIA hence deciphers clinically relevant information from WSIs, opening avenues for personalized cancer management.
癌症是一种异质性疾病，需要进行昂贵的基因谱分析以更好地理解和管理。深度学习的最新进展使得从全切片图像（WSI）中进行经济高效的基因改变预测成为可能。虽然转换器在非医疗领域推动了重大进展，但由于模型复杂性高和数据集规模有限，它们在 WSI 中的应用落后了。在这里，我们介绍了 SEQUOIA，这是一种线性化的转换器模型，可以从 WSI 预测癌症转录组谱。SEQUOIA 是使用 16 种癌症类型的 7584 个肿瘤样本开发的，其泛化能力在包含 1368 个肿瘤的两个独立队列上得到了验证。准确预测的基因与关键的癌症过程相关，包括炎症反应、细胞周期和代谢。此外，我们证明了 SEQUOIA 在乳腺癌复发风险分层和解决局部区域水平的空间基因表达方面的价值。因此，SEQUOIA 从 WSI 中解析出与临床相关的信息，为个性化癌症管理开辟了道路。
