Cargando…
Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features
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(V600E) mutations as is observed in papillary thyroid carcinomas with extensive...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group US
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8064913/ https://www.ncbi.nlm.nih.gov/pubmed/33299111 http://dx.doi.org/10.1038/s41379-020-00724-3 |
_version_ | 1783682237963698176 |
---|---|
author | Dolezal, James M. Trzcinska, Anna Liao, Chih-Yi Kochanny, Sara Blair, Elizabeth Agrawal, Nishant Keutgen, Xavier M. Angelos, Peter Cipriani, Nicole A. Pearson, Alexander T. |
author_facet | Dolezal, James M. Trzcinska, Anna Liao, Chih-Yi Kochanny, Sara Blair, Elizabeth Agrawal, Nishant Keutgen, Xavier M. Angelos, Peter Cipriani, Nicole A. Pearson, Alexander T. |
author_sort | Dolezal, James M. |
collection | PubMed |
description | 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(V600E) 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(V600E) 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(2) = 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(V600E)-mutant PTC-EFG had BRAF(V600E)-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. |
format | Online Article Text |
id | pubmed-8064913 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Nature Publishing Group US |
record_format | MEDLINE/PubMed |
spelling | pubmed-80649132021-05-05 Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features Dolezal, James M. Trzcinska, Anna Liao, Chih-Yi Kochanny, Sara Blair, Elizabeth Agrawal, Nishant Keutgen, Xavier M. Angelos, Peter Cipriani, Nicole A. Pearson, Alexander T. Mod Pathol Article 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(V600E) 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(V600E) 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(2) = 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(V600E)-mutant PTC-EFG had BRAF(V600E)-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. Nature Publishing Group US 2020-12-10 2021 /pmc/articles/PMC8064913/ /pubmed/33299111 http://dx.doi.org/10.1038/s41379-020-00724-3 Text en © The Author(s) 2020 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Dolezal, James M. Trzcinska, Anna Liao, Chih-Yi Kochanny, Sara Blair, Elizabeth Agrawal, Nishant Keutgen, Xavier M. Angelos, Peter Cipriani, Nicole A. Pearson, Alexander T. Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title | Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title_full | Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title_fullStr | Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title_full_unstemmed | Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title_short | Deep learning prediction of BRAF-RAS gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
title_sort | deep learning prediction of braf-ras gene expression signature identifies noninvasive follicular thyroid neoplasms with papillary-like nuclear features |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8064913/ https://www.ncbi.nlm.nih.gov/pubmed/33299111 http://dx.doi.org/10.1038/s41379-020-00724-3 |
work_keys_str_mv | AT dolezaljamesm deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT trzcinskaanna deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT liaochihyi deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT kochannysara deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT blairelizabeth deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT agrawalnishant deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT keutgenxavierm deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT angelospeter deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT ciprianinicolea deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures AT pearsonalexandert deeplearningpredictionofbrafrasgeneexpressionsignatureidentifiesnoninvasivefollicularthyroidneoplasmswithpapillarylikenuclearfeatures |