Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States.
Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States.
EBioMedicine. 2020 Dec;62:103094. doi: 10.1016/j.ebiom.2020.103094. Epub 2020 Nov 7.
Identifying which individuals will develop tuberculosis (TB) remains an unresolved problem due to few animal models and computational approaches that effectively address its heterogeneity. To meet these shortcomings, we show that Diversity Outbred (DO) mice reflect human-like genetic diversity and develop human-like lung granulomas when infected with Mycobacterium tuberculosis (M.tb) .
Following M.tb infection, a "supersusceptible" phenotype develops in approximately one-third of DO mice characterized by rapid morbidity and mortality within 8 weeks. These supersusceptible DO mice develop lung granulomas patterns akin to humans. This led us to utilize deep learning to identify supersusceptibility from hematoxylin & eosin (H&E) lung tissue sections utilizing only clinical outcomes (supersusceptible or not-supersusceptible) as labels.
The proposed machine learning model diagnosed supersusceptibility with high accuracy (91.50 ± 4.68%) compared to two expert pathologists using H&E stained lung sections (94.95% and 94.58%). Two non-experts used the imaging biomarker to diagnose supersusceptibility with high accuracy (88.25% and 87.95%) and agreement (96.00%). A board-certified veterinary pathologist (GB) examined the imaging biomarker and determined the model was making diagnostic decisions using a form of granuloma necrosis (karyorrhectic and pyknotic nuclear debris). This was corroborated by one other board-certified veterinary pathologist. Finally, the imaging biomarker was quantified, providing a novel means to convert visual patterns within granulomas to data suitable for statistical analyses.
Overall, our results have translatable implication to improve our understanding of TB and also to the broader field of computational pathology in which clinical outcomes alone can drive automatic identification of interpretable imaging biomarkers, knowledge discovery, and validation of existing clinical biomarkers.
National Institutes of Health and American Lung Association.
由于缺乏能够有效解决其异质性的动物模型和计算方法，识别哪些个体将患结核病（TB）仍然是一个未解决的问题。为了克服这些不足，我们证明了多样性杂交（DO）小鼠反映了人类样的遗传多样性，并在感染结核分枝杆菌（M.tb）时发展出类似于人类的肺部肉芽肿。
在 M.tb 感染后，大约三分之一的 DO 小鼠会发展出一种“超敏”表型，其特征是在 8 周内迅速发病和死亡。这些超敏 DO 小鼠发展出类似于人类的肺部肉芽肿模式。这使我们能够利用深度学习，仅使用临床结果（超敏或非超敏）作为标签，从苏木精和伊红（H&E）肺部组织切片中识别超敏性。
与使用 H&E 染色肺切片的两位专家病理学家相比（94.95%和 94.58%），所提出的机器学习模型对超敏性的诊断具有很高的准确性（91.50±4.68%）。两位非专家也使用成像生物标志物以很高的准确性（88.25%和 87.95%）和一致性（96.00%）诊断超敏性。一位经过董事会认证的兽医病理学家（GB）检查了成像生物标志物，并确定该模型正在使用一种肉芽肿坏死形式（核碎裂和固缩核碎片）做出诊断决策。另一位经过董事会认证的兽医病理学家证实了这一点。最后，对成像生物标志物进行了量化，为将肉芽肿内的视觉模式转换为适合统计分析的数据提供了一种新方法。
总的来说，我们的结果具有可转化的意义，可以提高我们对结核病的理解，也可以推动计算病理学领域的发展，在这个领域中，仅临床结果就可以驱动自动识别可解释的成像生物标志物、知识发现和验证现有的临床生物标志物。
美国国立卫生研究院和美国肺脏协会。
