Exploring pathological signatures for predicting the recurrence of early-stage hepatocellular carcinoma based on deep learning.
Exploring pathological signatures for predicting the recurrence of early-stage hepatocellular carcinoma based on deep learning.
复制标题
基于深度学习探索预测早期肝细胞癌复发的病理特征。
DOI：
10.3389/fonc.2022.968202
复制
发表时间：
2022
影响因子：
4.7
通讯作者：
中科院分区：
文献类型：
--
作者：
术后复发阻碍了早期肝细胞癌（E-HCC）的治愈。我们的目的是建立一种新型的人工智能复发相关病理预测器，并研究病理特征与局部免疫微环境之间的关系。中山队列中 547 例 E-HCC 患者总共收集了 576 张全切片图像（WSI），将其随机分为训练队列和验证队列。外部验证队列由来自癌症基因组图谱 (TCGA) 数据库的 147 名肿瘤淋巴结转移 (TNM) I 期患者组成。通过弱监督卷积神经网络识别出六种类型的 HCC 组织。构建并验证了复发相关的组织学评分（HS）。通过大量免疫组织化学数据评估免疫微环境与 HS 之间的相关性。 HCC组织总体分类准确率为94.17%。训练组、验证组和 TCGA 组中 HS 的 C 指数分别为 0.804、0.739 和 0.708。多变量分析显示HS（HR=4.05，95%CI：3.40-4.84）是无复发生存的独立预测因子。 HS高危组患者术前甲胎蛋白水平升高，肿瘤分化程度较差，微血管侵犯比例较高。免疫组织化学数据将 HS 与局部免疫细胞浸润联系起来。 HS与瘤周CD14+细胞的表达水平呈正相关(p=0.013)，与瘤内CD8+细胞的表达水平呈负相关(p<0.001)。该研究建立了一种新的组织学评分，利用深度学习预测 E-HCC 的短期和长期复发，这可以促进复发预测和管理的临床决策。
Postoperative recurrence impedes the curability of early-stage hepatocellular carcinoma (E-HCC). We aimed to establish a novel recurrence-related pathological prognosticator with artificial intelligence, and investigate the relationship between pathological features and the local immunological microenvironment. A total of 576 whole-slide images (WSIs) were collected from 547 patients with E-HCC in the Zhongshan cohort, which was randomly divided into a training cohort and a validation cohort. The external validation cohort comprised 147 Tumor Node Metastasis (TNM) stage I patients from The Cancer Genome Atlas (TCGA) database. Six types of HCC tissues were identified by a weakly supervised convolutional neural network. A recurrence-related histological score (HS) was constructed and validated. The correlation between immune microenvironment and HS was evaluated through extensive immunohistochemical data. The overall classification accuracy of HCC tissues was 94.17%. The C-indexes of HS in the training, validation and TCGA cohorts were 0.804, 0.739 and 0.708, respectively. Multivariate analysis showed that the HS (HR= 4.05, 95% CI: 3.40-4.84) was an independent predictor for recurrence-free survival. Patients in HS high-risk group had elevated preoperative alpha-fetoprotein levels, poorer tumor differentiation and a higher proportion of microvascular invasion. The immunohistochemistry data linked the HS to local immune cell infiltration. HS was positively correlated with the expression level of peritumoral CD14+ cells (p= 0.013), and negatively with the intratumoral CD8+ cells (p< 0.001). The study established a novel histological score that predicted short-term and long-term recurrence for E-HCCs using deep learning, which could facilitate clinical decision making in recurrence prediction and management.
登录
查看更多内容
影响因子：
19.7
作者：
Mule, Sebastien;Pirgliasco, Athena Galletto;Luciani, Alain
通讯作者：
Luciani, Alain
影响因子：
4.6
作者：
De Lorenzo S;Tovoli F;Barbera MA;Garuti F;Palloni A;Frega G;Garajovà I;Rizzo A;Trevisani F;Brandi G
通讯作者：
Brandi G
影响因子：
25.7
作者：
Calderaro, Julien;Petitprez, Florent;Sautes-Fridman, Catherine
通讯作者：
Sautes-Fridman, Catherine
影响因子：
78.8
作者：
Bera, Kaustav;Schalper, Kurt A.;Madabhushi, Anant
通讯作者：
Madabhushi, Anant
影响因子：
10.1
作者：
Gabrielson A;Wu Y;Wang H;Jiang J;Kallakury B;Gatalica Z;Reddy S;Kleiner D;Fishbein T;Johnson L;Island E;Satoskar R;Banovac F;Jha R;Kachhela J;Feng P;Zhang T;Tesfaye A;Prins P;Loffredo C;Marshall J;Weiner L;Atkins M;He AR
通讯作者：
He AR