文献速递甲状腺疾病

深度学习从甲状腺乳头状癌组织病理学中预测基因改变并发现新形态特征

Deep Learning Discovers New Morphological Features while Predicting Genetic Alterations from Histopathology of Papillary Thyroid Carcinoma.
PubMed 文献 · Thyroid · 2025-07-03

该回顾性研究利用两个独立队列共662例甲状腺乳头状癌(PTC)患者,建立人工智能(AI)流程,以Vision Transformer在数字化H&E染色切片上预测BRAF、panRAS及基因融合状态。外部测试集曲线下面积分别为0.882、0.876和0.858,准确率分别为79.3%、89.3%和84.7%,并发现与融合相关PTC的新形态学标准。

要点

  • AI模型在独立外部测试集上对BRAF、panRAS和基因融合的预测AUC分别为0.882、0.876和0.858。
  • 模型准确率在BRAF为79.3%、panRAS为89.3%、基因融合为84.7%,验证集与测试集表现几乎一致。
  • 分析最高预测概率图块发现了与融合相关PTC的先前未描述的形态学模式。

核心结论

  • AI可从数字化H&E切片预测PTC的BRAF、panRAS和基因融合状态,具有较高准确性,可能适合预筛查。
  • 可解释性方法揭示了与特定基因型相关的先前未描述的形态学模式。

研究设计与样本

  • 回顾性研究,使用两个独立PTC队列共662例建立AI流程。
  • 癌症基因组图谱队列496例为开发队列,美因茨队列166例为独立外部测试队列。
  • 目标变量为BRAF、panRAS和融合状态,采用Vision Transformer在数字化标注H&E切片上训练。

主要发现

  • BRAF的AUC为0.882(置信区间0.829-0.931),准确率79.3%(72.7-85.8%)。
  • panRAS的AUC为0.876(0.822-0.927),准确率89.3%(84.2-94.0%)。
  • 基因融合的AUC为0.858(0.801-0.912),准确率84.7%(78.8-90.2%)。
  • 验证集与测试集性能几乎相同。
  • 分析最高预测图块发现融合相关PTC的新形态学标准。

关键数值与推荐

  • BRAF突变在PTC中发生率为40-60%,panRAS突变为10-15%,RET融合等基因融合事件为7-35%。

临床怎么用

  • 模型高准确率使其可能适用于PTC基因改变的预筛查。
  • 向病理学家提供AI识别的形态学特征可能提高其准确性。

局限性

  • 结论基于回顾性研究,需进一步前瞻性验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Background: Papillary thyroid carcinoma (PTC) is the most common malignant tumor of the endocrine system. BRAF mutations occur in 40-60%, panRAS mutations in 10-15%, and different gene fusion events such as RET fusions in 7-35% of these neoplasms. Artificial intelligence (AI) methods could be used to predict genetic changes from conventional histopathological slides. Methods: In this retrospective study, we used two independent cohorts of patients with PTC, totaling 662 cases for the establishment of our AI pipeline. The Cancer Genome Atlas cohort (496 cases) served as the developmental cohort, while the Mainz cohort (166 cases) served as an independent external test cohort. BRAF, panRAS, and fusion status was determined for all of these patients as target variables. Vision Transformer was trained on digitized annotated hematoxylin and eosin-stained slides for the presence of these alterations. Highest probability image tiles were used to identify new morphological criteria associated with the genetic changes. Results: The trained model resulted in an area under the receiver operating characteristic curve of 0.882 (confidence interval 0.829-0.931) for BRAF, 0.876 (0.822-0.927) for panRAS, and 0.858 (0.801-0.912) for gene fusions. Accuracy was 79.3% (72.7-85.8%) for BRAF, 89.3% (84.2-94.0%) for panRAS, and 84.7% (78.8-90.2%) for gene fusions. The performance on the validation set was almost identical to that on the test set. Analyzing the highest predictive tiles, novel morphological criteria for fusion-associated PTC could be discovered. Conclusions: Our study demonstrates that predicting genetic alterations in digitized histopathological slides using AI is feasible in patients with PTC. Our model showed high accuracy in predicting these changes, making it potentially suitable for pre-screening. Explainability approaches uncovered previously undescribed morphological patterns associated with certain genotypes. Providing pathologists with these AI-based features could improve their accuracy. Assuming further positive prospective validation, this discovery could contribute to a deeper understanding of PTC.

来源:Thyroid,查看原文。版权归原作者所有。

引用

  1. Marion I, Schulz S, Glasner C, et al. Deep Learning Discovers New Morphological Features while Predicting Genetic Alterations from Histopathology of Papillary Thyroid Carcinoma. Thyroid. 2025. PMID: 40607934. doi:10.1089/thy.2024.0691

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。