A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome
Abstract Gene expression signatures are commonly used as predictive biomarkers, but do not capture structural features within the tissue architecture. Here we apply a 2-step machine learning framework for quantitative imaging of tumor vasculature to derive a spatially informed, prognostic gene signa...
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2017
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/734bffa0c8884685a89d36929e58ac7d |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:734bffa0c8884685a89d36929e58ac7d |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:734bffa0c8884685a89d36929e58ac7d2021-12-02T15:05:38ZA novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome10.1038/s41598-017-13196-42045-2322https://doaj.org/article/734bffa0c8884685a89d36929e58ac7d2017-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-13196-4https://doaj.org/toc/2045-2322Abstract Gene expression signatures are commonly used as predictive biomarkers, but do not capture structural features within the tissue architecture. Here we apply a 2-step machine learning framework for quantitative imaging of tumor vasculature to derive a spatially informed, prognostic gene signature. The trained algorithms classify endothelial cells and generate a vascular area mask (VAM) in H&E micrographs of clear cell renal cell carcinoma (ccRCC) cases from The Cancer Genome Atlas (TCGA). Quantification of VAMs led to the discovery of 9 vascular features (9VF) that predicted disease-free-survival in a discovery cohort (n = 64, HR = 2.3). Correlation analysis and information gain identified a 14 gene expression signature related to the 9VF’s. Two generalized linear models with elastic net regularization (14VF and 14GT), based on the 14 genes, separated independent cohorts of up to 301 cases into good and poor disease-free survival groups (14VF HR = 2.4, 14GT HR = 3.33). For the first time, we successfully applied digital image analysis and targeted machine learning to develop prognostic, morphology-based, gene expression signatures from the vascular architecture. This novel morphogenomic approach has the potential to improve previous methods for biomarker development.Nathan IngFangjin HuangAndrew ConleySungyong YouZhaoxuan MaSergey KlimovChisato OheXiaopu YuanMahul B. AminRobert FiglinArkadiusz GertychBeatrice S. KnudsenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-10 (2017) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Nathan Ing Fangjin Huang Andrew Conley Sungyong You Zhaoxuan Ma Sergey Klimov Chisato Ohe Xiaopu Yuan Mahul B. Amin Robert Figlin Arkadiusz Gertych Beatrice S. Knudsen A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| description |
Abstract Gene expression signatures are commonly used as predictive biomarkers, but do not capture structural features within the tissue architecture. Here we apply a 2-step machine learning framework for quantitative imaging of tumor vasculature to derive a spatially informed, prognostic gene signature. The trained algorithms classify endothelial cells and generate a vascular area mask (VAM) in H&E micrographs of clear cell renal cell carcinoma (ccRCC) cases from The Cancer Genome Atlas (TCGA). Quantification of VAMs led to the discovery of 9 vascular features (9VF) that predicted disease-free-survival in a discovery cohort (n = 64, HR = 2.3). Correlation analysis and information gain identified a 14 gene expression signature related to the 9VF’s. Two generalized linear models with elastic net regularization (14VF and 14GT), based on the 14 genes, separated independent cohorts of up to 301 cases into good and poor disease-free survival groups (14VF HR = 2.4, 14GT HR = 3.33). For the first time, we successfully applied digital image analysis and targeted machine learning to develop prognostic, morphology-based, gene expression signatures from the vascular architecture. This novel morphogenomic approach has the potential to improve previous methods for biomarker development. |
| format |
article |
| author |
Nathan Ing Fangjin Huang Andrew Conley Sungyong You Zhaoxuan Ma Sergey Klimov Chisato Ohe Xiaopu Yuan Mahul B. Amin Robert Figlin Arkadiusz Gertych Beatrice S. Knudsen |
| author_facet |
Nathan Ing Fangjin Huang Andrew Conley Sungyong You Zhaoxuan Ma Sergey Klimov Chisato Ohe Xiaopu Yuan Mahul B. Amin Robert Figlin Arkadiusz Gertych Beatrice S. Knudsen |
| author_sort |
Nathan Ing |
| title |
A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| title_short |
A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| title_full |
A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| title_fullStr |
A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| title_full_unstemmed |
A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| title_sort |
novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome |
| publisher |
Nature Portfolio |
| publishDate |
2017 |
| url |
https://doaj.org/article/734bffa0c8884685a89d36929e58ac7d |
| work_keys_str_mv |
AT nathaning anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT fangjinhuang anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT andrewconley anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT sungyongyou anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT zhaoxuanma anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT sergeyklimov anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT chisatoohe anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT xiaopuyuan anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT mahulbamin anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT robertfiglin anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT arkadiuszgertych anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT beatricesknudsen anovelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT nathaning novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT fangjinhuang novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT andrewconley novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT sungyongyou novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT zhaoxuanma novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT sergeyklimov novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT chisatoohe novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT xiaopuyuan novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT mahulbamin novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT robertfiglin novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT arkadiuszgertych novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome AT beatricesknudsen novelmachinelearningapproachrevealslatentvascularphenotypespredictiveofrenalcanceroutcome |
| _version_ |
1718388772800823296 |