Department of Medicine, Section of Hematology/Oncology, University of Chicago Medical Center, Chicago, IL, USA.
Department of Pathology, University of Chicago Medical Center, Chicago, IL, USA.
Mod Pathol. 2021 May;34(5):862-874. doi: 10.1038/s41379-020-00724-3. Epub 2020 Dec 10.
Noninvasive follicular thyroid neoplasms with papillary-like nuclear features (NIFTP) are follicular-patterned thyroid neoplasms defined by nuclear atypia and indolent behavior. They harbor RAS mutations, rather than BRAF mutations as is observed in papillary thyroid carcinomas with extensive follicular growth. Reliably identifying NIFTPs aids in safe therapy de-escalation, but has proven to be challenging due to interobserver variability and morphologic heterogeneity. The genomic scoring system BRS (BRAF-RAS score) was developed to quantify the extent to which a tumor's expression profile resembles a BRAF or RAS-mutant neoplasm. We proposed that deep learning prediction of BRS could differentiate NIFTP from other follicular-patterned neoplasms. A deep learning model was trained on slides from a dataset of 115 thyroid neoplasms to predict tumor subtype (NIFTP, PTC-EFG, or classic PTC), and was used to generate predictions for 497 thyroid neoplasms within The Cancer Genome Atlas (TCGA). Within follicular-patterned neoplasms, tumors with positive BRS (RAS-like) were 8.5 times as likely to carry an NIFTP prediction than tumors with negative BRS (89.7% vs 10.5%, P < 0.0001). To test the hypothesis that BRS may serve as a surrogate for biological processes that determine tumor subtype, a separate model was trained on TCGA slides to predict BRS as a linear outcome. This model performed well in cross-validation on the training set (R = 0.67, dichotomized AUC = 0.94). In our internal cohort, NIFTPs were near universally predicted to have RAS-like BRS; as a sole discriminator of NIFTP status, predicted BRS performed with an AUC of 0.99 globally and 0.97 when restricted to follicular-patterned neoplasms. BRAF-mutant PTC-EFG had BRAF-like predicted BRS (mean -0.49), nonmutant PTC-EFG had more intermediate predicted BRS (mean -0.17), and NIFTP had RAS-like BRS (mean 0.35; P < 0.0001). In summary, histologic features associated with the BRAF-RAS gene expression spectrum are detectable by deep learning and can aid in distinguishing indolent NIFTP from PTCs.
非浸润性滤泡甲状腺肿瘤伴乳头状核特征（NIFTP）是一种滤泡模式的甲状腺肿瘤，其特征为核异型性和惰性行为。它们携带 RAS 突变，而不是像广泛滤泡生长的甲状腺乳头状癌那样携带 BRAF 突变。可靠地识别 NIFTP 有助于安全地降低治疗强度，但由于观察者间的变异性和形态异质性，这一过程具有挑战性。BRS（BRAF-RAS 评分）基因组评分系统是为了量化肿瘤的表达谱与 BRAF 或 RAS 突变型肿瘤的相似程度而开发的。我们提出，深度学习对 BRS 的预测可以将 NIFTP 与其他滤泡模式的肿瘤区分开来。一个深度学习模型在一个由 115 例甲状腺肿瘤组成的数据集的幻灯片上进行训练，以预测肿瘤亚型（NIFTP、PTC-EFG 或经典 PTC），并用于生成癌症基因组图谱（TCGA）内 497 例甲状腺肿瘤的预测。在滤泡模式的肿瘤中，BRS 阳性（RAS 样）的肿瘤比 BRS 阴性（89.7%比 10.5%，P<0.0001）更有可能携带 NIFTP 预测。为了检验 BRS 可能作为决定肿瘤亚型的生物学过程的替代物的假设，另一个模型在 TCGA 幻灯片上进行训练，以预测 BRS 作为线性结果。该模型在训练集的交叉验证中表现良好（R=0.67，二分类 AUC=0.94）。在我们的内部队列中，NIFTP 几乎普遍被预测为具有 RAS 样 BRS；作为 NIFTP 状态的唯一鉴别器，预测的 BRS 在全局范围内的 AUC 为 0.99，在限制为滤泡模式的肿瘤时为 0.97。BRAF 突变的 PTC-EFG 具有 BRAF 样预测的 BRS（平均-0.49），非突变的 PTC-EFG 具有更中间的预测 BRS（平均-0.17），而 NIFTP 具有 RAS 样 BRS（平均 0.35；P<0.0001）。总之，与 BRAF-RAS 基因表达谱相关的组织学特征可通过深度学习检测，并有助于将惰性 NIFTP 与 PTC 区分开来。
