MesoGraph: Automatic profiling of mesothelioma subtypes from histological images.
MesoGraph: Automatic profiling of mesothelioma subtypes from histological images.
复制标题
仪表术：从组织学图像中自动分析间皮瘤亚型。
DOI：
10.1016/j.xcrm.2023.101226
复制
发表时间：
2023-10-17
影响因子：
14.3
通讯作者：
Robertus, Jan Lukas
中科院分区：
文献类型：
--
作者：
Eastwood, Mark;Sailem, Heba;Marc, Silviu Tudor;Gao, Xiaohong;Offman, Judith;Karteris, Emmanouil;Fernandez, Angeles Montero;Jonigk, Danny;Cookson, William;Moffatt, Miriam;Popat, Sanjay;Minhas, Fayyaz;Robertus, Jan Lukas
根据上皮样和肉瘤样肿瘤细胞的相对比例，间皮瘤可分为上皮样、肉瘤样和双相三种组织学亚型。目前的指南建议对每个间皮瘤的肉瘤样成分进行量化，因为双期间皮瘤中肉瘤样类型的比例越高，预后越差。在这项工作中，我们开发了一种具有排序损失的双任务图神经网络（GNN）架构，以学习能够对组织区域进行细胞分辨率评分的模型。这允许根据总类肉瘤关联评分对肿瘤样本进行定量分析。组织由具有细胞水平形态和区域特征的细胞图表示。我们使用来自Mesobank的外部多中心测试集，在此基础上展示了我们模型的预测性能。我们还通过分析细胞的典型形态特征来验证我们的模型预测。形态学分析与已知的亚型特征相符。在亚型预测任务中AUROC为0.90，模型得分与生存相关，风险比为2.30。Eastwood等人引入了MesoGraph，这是一种从组织图像中分析间皮瘤亚型的图神经网络模型。间皮瘤样本中肉瘤样区域患病率的定量测量可以对组织样本进行更准确和更少主观的评估。
Mesothelioma is classified into three histological subtypes, epithelioid, sarcomatoid, and biphasic, according to the relative proportions of epithelioid and sarcomatoid tumor cells present. Current guidelines recommend that the sarcomatoid component of each mesothelioma is quantified, as a higher percentage of sarcomatoid pattern in biphasic mesothelioma shows poorer prognosis. In this work, we develop a dual-task graph neural network (GNN) architecture with ranking loss to learn a model capable of scoring regions of tissue down to cellular resolution. This allows quantitative profiling of a tumor sample according to the aggregate sarcomatoid association score. Tissue is represented by a cell graph with both cell-level morphological and regional features. We use an external multicentric test set from Mesobank, on which we demonstrate the predictive performance of our model. We additionally validate our model predictions through an analysis of the typical morphological features of cells according to their predicted score. GNN capable of scoring regions of tissue according to its sarcomatoid association Morphological analysis agrees with known characteristics of subtypes AUROC of 0.90 in subtype prediction task Model score shown to be associated with survival with hazard ratio 2.30 Eastwood et al. introduce MesoGraph, a graph neural network model for the profiling of mesothelioma subtype from tissue images. A quantitative measure of the prevalence of sarcomatoid regions in a mesothelioma sample could allow a more accurate and less subjective assessment of tissue samples.
登录
查看更多内容
影响因子：
4.6
作者：
Bankhead P;Loughrey MB;Fernández JA;Dombrowski Y;McArt DG;Dunne PD;McQuaid S;Gray RT;Murray LJ;Coleman HG;James JA;Salto-Tellez M;Hamilton PW
通讯作者：
Hamilton PW
DOI：
10.1016/j.jtho.2018.04.023
发表时间：
2018-08
期刊：
Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer
影响因子：
--
作者：
Galateau Salle F;Le Stang N;Nicholson AG;Pissaloux D;Churg A;Klebe S;Roggli VL;Tazelaar HD;Vignaud JM;Attanoos R;Beasley MB;Begueret H;Capron F;Chirieac L;Copin MC;Dacic S;Danel C;Foulet-Roge A;Gibbs A;Giusiano-Courcambeck S;Hiroshima K;Hofman V;Husain AN;Kerr K;Marchevsky A;Nabeshima K;Picquenot JM;Rouquette I;Sagan C;Sauter JL;Thivolet F;Travis WD;Tsao MS;Weynand B;Damiola F;Scherpereel A;Pairon JC;Lantuejoul S;Rusch V;Girard N
通讯作者：
Girard N
DOI：
10.1109/tsmc.1973.4309314
发表时间：
1973-01-01
期刊：
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS
影响因子：
--
作者：
HARALICK, RM;SHANMUGAM, K;DINSTEIN, I
通讯作者：
DINSTEIN, I
影响因子：
5.8
作者：
Ai, Jing;Stevenson, James P.
通讯作者：
Stevenson, James P.
影响因子：
20.4
作者：
Santoro, Armando;O'Brien, Mary E.;Manegold, Christian
通讯作者：
Manegold, Christian