Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma
Abstract Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical d...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/29a1d68a17774a75aedf2ebb89547a04 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:29a1d68a17774a75aedf2ebb89547a04 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:29a1d68a17774a75aedf2ebb89547a042021-12-02T12:11:50ZUncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma10.1038/s41598-021-83141-z2045-2322https://doaj.org/article/29a1d68a17774a75aedf2ebb89547a042021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83141-zhttps://doaj.org/toc/2045-2322Abstract Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical decision making, no published studies have directly addressed uncertainty in these model predictions. We developed a radiogenomics ML model to quantify uncertainty using transductive Gaussian Processes (GP) and a unique dataset of 95 image-localized biopsies with spatially matched MRI from 25 untreated Glioblastoma (GBM) patients. The model generated predictions for regional EGFR amplification status (a common and important target in GBM) to resolve the intratumoral genetic heterogeneity across each individual tumor—a key factor for future personalized therapeutic paradigms. The model used probability distributions for each sample prediction to quantify uncertainty, and used transductive learning to reduce the overall uncertainty. We compared predictive accuracy and uncertainty of the transductive learning GP model against a standard GP model using leave-one-patient-out cross validation. Additionally, we used a separate dataset containing 24 image-localized biopsies from 7 high-grade glioma patients to validate the model. Predictive uncertainty informed the likelihood of achieving an accurate sample prediction. When stratifying predictions based on uncertainty, we observed substantially higher performance in the group cohort (75% accuracy, n = 95) and amongst sample predictions with the lowest uncertainty (83% accuracy, n = 72) compared to predictions with higher uncertainty (48% accuracy, n = 23), due largely to data interpolation (rather than extrapolation). On the separate validation set, our model achieved 78% accuracy amongst the sample predictions with lowest uncertainty. We present a novel approach to quantify radiogenomics uncertainty to enhance model performance and clinical interpretability. This should help integrate more reliable radiogenomics models for improved medical decision-making.Leland S. HuLujia WangAndrea Hawkins-DaarudJennifer M. EschbacherKyle W. SingletonPamela R. JacksonKamala Clark-SwansonChristopher P. SeredukSen PengPanwen WangJunwen WangLeslie C. BaxterKris A. SmithGina L. MazzaAshley M. StokesBernard R. BendokRichard S. ZimmermanChandan KrishnaAlyx B. PorterMaciej M. MrugalaJoseph M. HoxworthTeresa WuNhan L. TranKristin R. SwansonJing LiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Leland S. Hu Lujia Wang Andrea Hawkins-Daarud Jennifer M. Eschbacher Kyle W. Singleton Pamela R. Jackson Kamala Clark-Swanson Christopher P. Sereduk Sen Peng Panwen Wang Junwen Wang Leslie C. Baxter Kris A. Smith Gina L. Mazza Ashley M. Stokes Bernard R. Bendok Richard S. Zimmerman Chandan Krishna Alyx B. Porter Maciej M. Mrugala Joseph M. Hoxworth Teresa Wu Nhan L. Tran Kristin R. Swanson Jing Li Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| description |
Abstract Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical decision making, no published studies have directly addressed uncertainty in these model predictions. We developed a radiogenomics ML model to quantify uncertainty using transductive Gaussian Processes (GP) and a unique dataset of 95 image-localized biopsies with spatially matched MRI from 25 untreated Glioblastoma (GBM) patients. The model generated predictions for regional EGFR amplification status (a common and important target in GBM) to resolve the intratumoral genetic heterogeneity across each individual tumor—a key factor for future personalized therapeutic paradigms. The model used probability distributions for each sample prediction to quantify uncertainty, and used transductive learning to reduce the overall uncertainty. We compared predictive accuracy and uncertainty of the transductive learning GP model against a standard GP model using leave-one-patient-out cross validation. Additionally, we used a separate dataset containing 24 image-localized biopsies from 7 high-grade glioma patients to validate the model. Predictive uncertainty informed the likelihood of achieving an accurate sample prediction. When stratifying predictions based on uncertainty, we observed substantially higher performance in the group cohort (75% accuracy, n = 95) and amongst sample predictions with the lowest uncertainty (83% accuracy, n = 72) compared to predictions with higher uncertainty (48% accuracy, n = 23), due largely to data interpolation (rather than extrapolation). On the separate validation set, our model achieved 78% accuracy amongst the sample predictions with lowest uncertainty. We present a novel approach to quantify radiogenomics uncertainty to enhance model performance and clinical interpretability. This should help integrate more reliable radiogenomics models for improved medical decision-making. |
| format |
article |
| author |
Leland S. Hu Lujia Wang Andrea Hawkins-Daarud Jennifer M. Eschbacher Kyle W. Singleton Pamela R. Jackson Kamala Clark-Swanson Christopher P. Sereduk Sen Peng Panwen Wang Junwen Wang Leslie C. Baxter Kris A. Smith Gina L. Mazza Ashley M. Stokes Bernard R. Bendok Richard S. Zimmerman Chandan Krishna Alyx B. Porter Maciej M. Mrugala Joseph M. Hoxworth Teresa Wu Nhan L. Tran Kristin R. Swanson Jing Li |
| author_facet |
Leland S. Hu Lujia Wang Andrea Hawkins-Daarud Jennifer M. Eschbacher Kyle W. Singleton Pamela R. Jackson Kamala Clark-Swanson Christopher P. Sereduk Sen Peng Panwen Wang Junwen Wang Leslie C. Baxter Kris A. Smith Gina L. Mazza Ashley M. Stokes Bernard R. Bendok Richard S. Zimmerman Chandan Krishna Alyx B. Porter Maciej M. Mrugala Joseph M. Hoxworth Teresa Wu Nhan L. Tran Kristin R. Swanson Jing Li |
| author_sort |
Leland S. Hu |
| title |
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| title_short |
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| title_full |
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| title_fullStr |
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| title_full_unstemmed |
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma |
| title_sort |
uncertainty quantification in the radiogenomics modeling of egfr amplification in glioblastoma |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/29a1d68a17774a75aedf2ebb89547a04 |
| work_keys_str_mv |
AT lelandshu uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT lujiawang uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT andreahawkinsdaarud uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT jennifermeschbacher uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT kylewsingleton uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT pamelarjackson uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT kamalaclarkswanson uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT christopherpsereduk uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT senpeng uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT panwenwang uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT junwenwang uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT lesliecbaxter uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT krisasmith uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT ginalmazza uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT ashleymstokes uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT bernardrbendok uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT richardszimmerman uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT chandankrishna uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT alyxbporter uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT maciejmmrugala uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT josephmhoxworth uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT teresawu uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT nhanltran uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT kristinrswanson uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma AT jingli uncertaintyquantificationintheradiogenomicsmodelingofegframplificationinglioblastoma |
| _version_ |
1718394562083291136 |