Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer
PurposeWe aimed to explore potential confounders of prognostic radiomics signature predicting survival outcomes in clear cell renal cell carcinoma (ccRCC) patients and demonstrate how to control for them.Materials and MethodsPreoperative contrast enhanced abdominal CT scan of ccRCC patients along wi...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.638185/full |
id |
doaj-f9f777e18a1b4bd6bf8dbf603cd40968 |
---|---|
record_format |
Article |
spelling |
doaj-f9f777e18a1b4bd6bf8dbf603cd409682021-05-27T04:19:29ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-05-011110.3389/fonc.2021.638185638185Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney CancerLin Lu0Firas S. Ahmed1Oguz Akin2Lyndon Luk3Xiaotao Guo4Hao Yang5Jin Yoon6A. Aari Hakimi7Lawrence H. Schwartz8Binsheng Zhao9Department of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesDepartment of Radiology, Columbia University Irving Medical Center, New York, NY, United StatesPurposeWe aimed to explore potential confounders of prognostic radiomics signature predicting survival outcomes in clear cell renal cell carcinoma (ccRCC) patients and demonstrate how to control for them.Materials and MethodsPreoperative contrast enhanced abdominal CT scan of ccRCC patients along with pathological grade/stage, gene mutation status, and survival outcomes were retrieved from The Cancer Imaging Archive (TCIA)/The Cancer Genome Atlas—Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) database, a publicly available dataset. A semi-automatic segmentation method was applied to segment ccRCC tumors, and 1,160 radiomics features were extracted from each segmented tumor on the CT images. Non-parametric principal component decomposition (PCD) and unsupervised hierarchical clustering were applied to build the radiomics signature models. The factors confounding the radiomics signature were investigated and controlled sequentially. Kaplan–Meier curves and Cox regression analyses were performed to test the association between radiomics signatures and survival outcomes.Results183 patients of TCGA-KIRC cohort with available imaging, pathological, and clinical outcomes were included in this study. All 1,160 radiomics features were included in the first radiomics signature. Three additional radiomics signatures were then modelled in successive steps removing redundant radiomics features first, removing radiomics features biased by CT slice thickness second, and removing radiomics features dependent on tumor size third. The final radiomics signature model was the most parsimonious, unbiased by CT slice thickness, and independent of tumor size. This final radiomics signature stratified the cohort into radiomics phenotypes that are different by cancer-specific and recurrence-free survival; HR (95% CI) = 3.0 (1.5–5.7), p <0.05 and HR (95% CI) = 6.6 (3.1–14.1), p <0.05, respectively.ConclusionRadiomics signature can be confounded by multiple factors, including feature redundancy, image acquisition parameters like slice thickness, and tumor size. Attention to and proper control for these potential confounders are necessary for a reliable and clinically valuable radiomics signature.https://www.frontiersin.org/articles/10.3389/fonc.2021.638185/fullradiomicsquality controlmachine learningTCGAThe Cancer Imaging Archive (TCIA)clear cell renal cell cancer |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lin Lu Firas S. Ahmed Oguz Akin Lyndon Luk Xiaotao Guo Hao Yang Jin Yoon A. Aari Hakimi Lawrence H. Schwartz Binsheng Zhao |
spellingShingle |
Lin Lu Firas S. Ahmed Oguz Akin Lyndon Luk Xiaotao Guo Hao Yang Jin Yoon A. Aari Hakimi Lawrence H. Schwartz Binsheng Zhao Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer Frontiers in Oncology radiomics quality control machine learning TCGA The Cancer Imaging Archive (TCIA) clear cell renal cell cancer |
author_facet |
Lin Lu Firas S. Ahmed Oguz Akin Lyndon Luk Xiaotao Guo Hao Yang Jin Yoon A. Aari Hakimi Lawrence H. Schwartz Binsheng Zhao |
author_sort |
Lin Lu |
title |
Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer |
title_short |
Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer |
title_full |
Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer |
title_fullStr |
Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer |
title_full_unstemmed |
Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer |
title_sort |
uncontrolled confounders may lead to false or overvalued radiomics signature: a proof of concept using survival analysis in a multicenter cohort of kidney cancer |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Oncology |
issn |
2234-943X |
publishDate |
2021-05-01 |
description |
PurposeWe aimed to explore potential confounders of prognostic radiomics signature predicting survival outcomes in clear cell renal cell carcinoma (ccRCC) patients and demonstrate how to control for them.Materials and MethodsPreoperative contrast enhanced abdominal CT scan of ccRCC patients along with pathological grade/stage, gene mutation status, and survival outcomes were retrieved from The Cancer Imaging Archive (TCIA)/The Cancer Genome Atlas—Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) database, a publicly available dataset. A semi-automatic segmentation method was applied to segment ccRCC tumors, and 1,160 radiomics features were extracted from each segmented tumor on the CT images. Non-parametric principal component decomposition (PCD) and unsupervised hierarchical clustering were applied to build the radiomics signature models. The factors confounding the radiomics signature were investigated and controlled sequentially. Kaplan–Meier curves and Cox regression analyses were performed to test the association between radiomics signatures and survival outcomes.Results183 patients of TCGA-KIRC cohort with available imaging, pathological, and clinical outcomes were included in this study. All 1,160 radiomics features were included in the first radiomics signature. Three additional radiomics signatures were then modelled in successive steps removing redundant radiomics features first, removing radiomics features biased by CT slice thickness second, and removing radiomics features dependent on tumor size third. The final radiomics signature model was the most parsimonious, unbiased by CT slice thickness, and independent of tumor size. This final radiomics signature stratified the cohort into radiomics phenotypes that are different by cancer-specific and recurrence-free survival; HR (95% CI) = 3.0 (1.5–5.7), p <0.05 and HR (95% CI) = 6.6 (3.1–14.1), p <0.05, respectively.ConclusionRadiomics signature can be confounded by multiple factors, including feature redundancy, image acquisition parameters like slice thickness, and tumor size. Attention to and proper control for these potential confounders are necessary for a reliable and clinically valuable radiomics signature. |
topic |
radiomics quality control machine learning TCGA The Cancer Imaging Archive (TCIA) clear cell renal cell cancer |
url |
https://www.frontiersin.org/articles/10.3389/fonc.2021.638185/full |
work_keys_str_mv |
AT linlu uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT firassahmed uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT oguzakin uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT lyndonluk uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT xiaotaoguo uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT haoyang uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT jinyoon uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT aaarihakimi uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT lawrencehschwartz uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer AT binshengzhao uncontrolledconfoundersmayleadtofalseorovervaluedradiomicssignatureaproofofconceptusingsurvivalanalysisinamulticentercohortofkidneycancer |
_version_ |
1721426046505451520 |