空间感知图神经网络和结肠癌组织病理学中跨层次分子特征预测：一项回顾性多队列研究。
Spatially aware graph neural networks and cross-level molecular profile prediction in colon cancer histopathology: a retrospective multi-cohort study.
机构信息
Department of Computer Science, The University of North Carolina at Charlotte, Charlotte, NC, USA.
Sensebrain Research, San Jose, CA, USA.
出版信息
Lancet Digit Health. 2022 Nov;4(11):e787-e795. doi: 10.1016/S2589-7500(22)00168-6.
BACKGROUND
Digital whole-slide images are a unique way to assess the spatial context of the cancer microenvironment. Exploring these spatial characteristics will enable us to better identify cross-level molecular markers that could deepen our understanding of cancer biology and related patient outcomes.
METHODS
We proposed a graph neural network approach that emphasises spatialisation of tumour tiles towards a comprehensive evaluation of predicting cross-level molecular profiles of genetic mutations, copy number alterations, and functional protein expressions from whole-slide images. We introduced a transformation strategy that converts whole-slide image scans into graph-structured data to address the spatial heterogeneity of colon cancer. We developed and assessed the performance of the model on The Cancer Genome Atlas colon adenocarcinoma (TCGA-COAD) and validated it on two external datasets (ie, The Cancer Genome Atlas rectum adenocarcinoma [TCGA-READ] and Clinical Proteomic Tumor Analysis Consortium colon adenocarcinoma [CPTAC-COAD]). We also predicted microsatellite instability and result interpretability.
FINDINGS
The model was developed on 459 colon tumour whole-slide images from TCGA-COAD, and externally validated on 165 rectum tumour whole-slide images from TCGA-READ and 161 colon tumour whole-slide images from CPTAC-COAD. For TCGA cohorts, our method accurately predicted the molecular classes of the gene mutations (area under the curve [AUCs] from 82·54 [95% CI 77·41-87·14] to 87·08 [83·28-90·82] on TCGA-COAD, and AUCs from 70·46 [61·37-79·61] to 81·80 [72·20-89·70] on TCGA-READ), along with genes with copy number alterations (AUCs from 81·98 [73·34-89·68] to 90·55 [86·02-94·89] on TCGA-COAD, and AUCs from 62·05 [48·94-73·46] to 76·48 [64·78-86·71] on TCGA-READ), microsatellite instability (MSI) status classification (AUC 83·92 [77·41-87·59] on TCGA-COAD, and AUC 61·28 [53·28-67·93] on TCGA-READ), and protein expressions (AUCs from 85·57 [81·16-89·44] to 89·64 [86·29-93·19] on TCGA-COAD, and AUCs from 51·77 [42·53-61·83] to 59·79 [50·79-68·57] on TCGA-READ). For the CPTAC-COAD cohort, our model predicted a panel of gene mutations with AUC values from 63·74 (95% CI 52·92-75·37) to 82·90 (73·69-90·71), genes with copy number alterations with AUC values from 62·39 (51·37-73·76) to 86·08 (79·67-91·74), and MSI status prediction with AUC value of 73·15 (63·21-83·13).
INTERPRETATION
We showed that spatially connected graph models enable molecular profile predictions in colon cancer and are generalised to rectum cancer. After further validation, our method could be used to infer the prognostic value of multiscale molecular biomarkers and identify targeted therapies for patients with colon cancer.
FUNDING
This research has been partially funded by ARO MURI 805491, NSF IIS-1793883, NSF CNS-1747778, NSF IIS 1763523, DOD-ARO ACC-W911NF, and NSF OIA-2040638 to Dimitri N Metaxas.
背景
数字全切片图像是评估癌症微环境空间上下文的独特方法。探索这些空间特征将使我们能够更好地识别跨层次的分子标志物，从而加深我们对癌症生物学和相关患者结局的理解。
方法
我们提出了一种图神经网络方法，强调肿瘤瓦片的空间化，以全面评估从全切片图像预测遗传突变、拷贝数改变和功能蛋白表达的跨层次分子谱。我们引入了一种转换策略，将全切片图像扫描转换为图结构数据，以解决结肠癌的空间异质性问题。我们开发并评估了该模型在癌症基因组图谱结肠腺癌（TCGA-COAD）上的性能，并在两个外部数据集（即癌症基因组图谱直肠腺癌[TCGA-READ]和临床蛋白质肿瘤分析联盟结肠腺癌[CPTAC-COAD]）上进行了验证。我们还预测了微卫星不稳定性和结果的可解释性。
结果
该模型是在 TCGA-COAD 的 459 个结肠肿瘤全切片图像上开发的，并在 TCGA-READ 的 165 个直肠肿瘤全切片图像和 CPTAC-COAD 的 161 个结肠肿瘤全切片图像上进行了外部验证。对于 TCGA 队列，我们的方法准确预测了基因突变的分子类别（TCGA-COAD 的 AUC 从 82.54（95%CI 77.41-87.14）到 87.08（83.28-90.82），TCGA-READ 的 AUC 从 70.46（61.37-79.61）到 81.80（72.20-89.70）），以及具有拷贝数改变的基因（TCGA-COAD 的 AUC 从 81.98（73.34-89.68）到 90.55（86.02-94.89），TCGA-READ 的 AUC 从 62.05（48.94-73.46）到 76.48（64.78-86.71）），微卫星不稳定性（MSI）状态分类（TCGA-COAD 的 AUC 为 83.92（77.41-87.59），TCGA-READ 的 AUC 为 61.28（53.28-67.93））和蛋白质表达（TCGA-COAD 的 AUC 从 85.57（81.16-89.44）到 89.64（86.29-93.19），TCGA-READ 的 AUC 从 51.77（42.53-61.83）到 59.79（50.79-68.57））。对于 CPTAC-COAD 队列，我们的模型预测了一组基因突变的 AUC 值从 63.74（95%CI 52.92-75.37）到 82.90（73.69-90.71），拷贝数改变基因的 AUC 值从 62.39（51.37-73.76）到 86.08（79.67-91.74），MSI 状态预测的 AUC 值为 73.15（63.21-83.13）。
解释
我们表明，空间连接的图模型能够在结肠癌中预测分子谱，并推广到直肠癌。经过进一步验证，我们的方法可用于推断多尺度分子生物标志物的预后价值，并为结肠癌患者确定靶向治疗方法。
资助
这项研究部分得到了 ARO MURI 805491、NSF IIS-1793883、NSF CNS-1747778、NSF IIS 1763523、DOD-ARO ACC-W911NF 和 NSF OIA-2040638 的资助，资助对象为 Dimitri N Metaxas。
Zotero 插件