Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study.
Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study.
复制标题
DOI：
10.1016/s2589-7500(21)00180-1
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Rajpoot NM
中科院分区：
文献类型：
--
作者：
Bilal M;Raza SEA;Azam A;Graham S;Ilyas M;Cree IA;Snead D;Minhas F;Rajpoot NM
确定结直肠癌中分子通路和关键突变的状态对于最佳治疗决策至关重要。因此，我们的目标是开发一种新的深度学习管道，以预测关键分子通路的状态和突变从苏木精和曙红染色的结直肠癌载玻片的全载玻片图像作为替代当前的测试。在这项回顾性研究中，我们使用了来自癌症基因组图谱结肠和直肠癌（TCGA-CRC-DX）队列中499名患者的502张原发性结直肠肿瘤诊断切片，并开发了一个弱监督深度学习框架，其中包括三个独立的卷积神经网络模型。将整个载玻片图像分成大小相等的切片，模型1（ResNet 18）从非肿瘤切片中提取肿瘤切片。将这些肿瘤瓦片输入模型2（改编的ResNet 34），通过迭代抽取和排序采样来训练，以计算每个图块的预测得分，该预测得分表示图块属于高突变密度的分子标记的可能性（相对于低突变密度），微卫星不稳定性（相对于微卫星稳定性），染色体不稳定性（相对于基因组稳定性）、CpG岛甲基化子表型（CIMP）-高（相对于CIMP-低）、BRAFmut（相对于BRAFWT）、TP 53 mut（相对于TP 53 WT）和KRASWT（相对于KRASmut）。这些分数用于识别每张幻灯片中排名最高的标题，模型3（HoVer-Net）对这些图块中不同类型的细胞核进行分割和分类。我们计算了受试者工作特征曲线（AUROC）的凸船体下的面积作为模型性能指标，并将我们的结果与以前发表的方法进行了比较。我们的迭代抽取和秩抽样方法产生了预测超突变的平均AUROC（0·81 [SD 0·03] vs 0·71），微卫星不稳定性（0·86 [0·04] vs 0·74），染色体不稳定性（0·83 [0·02] vs 0·73），BRAFmut（0·79 [0·01] vs 0·66），和TP 53 mut（0·73 [0·02] vs 0·64），高于先前发表的方法，KRASmut的AUROC与先前报道的方法相似（0·60 [SD 0·04] vs 0·60）。预测CMP高状态的平均AUROC为0·79（SD 0·05）。我们发现高比例的肿瘤浸润淋巴细胞和坏死肿瘤细胞与微卫星不稳定性相关，高比例的肿瘤浸润淋巴细胞和低比例的坏死肿瘤细胞与超突变相关。经过大规模验证后，我们提出的用于预测结直肠癌中临床重要突变和分子途径（例如微卫星不稳定性）的算法可用于对患者进行分层，以进行靶向治疗，与基于测序或免疫组化的方法相比，成本可能更低，周转时间更快。英国医学研究理事会。
Determining the status of molecular pathways and key mutations in colorectal cancer is crucial for optimal therapeutic decision making. We therefore aimed to develop a novel deep learning pipeline to predict the status of key molecular pathways and mutations from whole-slide images of haematoxylin and eosin-stained colorectal cancer slides as an alternative to current tests. In this retrospective study, we used 502 diagnostic slides of primary colorectal tumours from 499 patients in The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) cohort and developed a weakly supervised deep learning framework involving three separate convolutional neural network models. Whole-slide images were divided into equally sized tiles and model 1 (ResNet18) extracted tumour tiles from non-tumour tiles. These tumour tiles were inputted into model 2 (adapted ResNet34), trained by iterative draw and rank sampling to calculate a prediction score for each tile that represented the likelihood of a tile belonging to the molecular labels of high mutation density (vs low mutation density), microsatellite instability (vs microsatellite stability), chromosomal instability (vs genomic stability), CpG island methylator phenotype (CIMP)-high (vs CIMP-low), BRAFmut (vs BRAFWT), TP53mut (vs TP53WT), and KRASWT (vs KRASmut). These scores were used to identify the top-ranked titles from each slide, and model 3 (HoVer-Net) segmented and classified the different types of cell nuclei in these tiles. We calculated the area under the convex hull of the receiver operating characteristic curve (AUROC) as a model performance measure and compared our results with those of previously published methods. Our iterative draw and rank sampling method yielded mean AUROCs for the prediction of hypermutation (0·81 [SD 0·03] vs 0·71), microsatellite instability (0·86 [0·04] vs 0·74), chromosomal instability (0·83 [0·02] vs 0·73), BRAFmut (0·79 [0·01] vs 0·66), and TP53mut (0·73 [0·02] vs 0·64) in the TCGA-CRC-DX cohort that were higher than those from previously published methods, and an AUROC for KRASmut that was similar to previously reported methods (0·60 [SD 0·04] vs 0·60). Mean AUROC for predicting CIMP-high status was 0·79 (SD 0·05). We found high proportions of tumour-infiltrating lymphocytes and necrotic tumour cells to be associated with microsatellite instability, and high proportions of tumour-infiltrating lymphocytes and a low proportion of necrotic tumour cells to be associated with hypermutation. After large-scale validation, our proposed algorithm for predicting clinically important mutations and molecular pathways, such as microsatellite instability, in colorectal cancer could be used to stratify patients for targeted therapies with potentially lower costs and quicker turnaround times than sequencing-based or immunohistochemistry-based approaches. The UK Medical Research Council.