Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma

Q. Yin, S. C. Hung, W. K. Rathmell, L. Shen, L. Wang, W. Lin, J. R. Fielding, A. H. Khandani, M. E. Woods, M. I. Milowsky, S. A. Brooks, E. M. Wallen, Dinggang Shen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Aim: To identify combined positron-emission tomography (PET)/magnetic resonance imaging (MRI)-based radiomics as a surrogate biomarker of intratumour disease risk for molecular subtype ccA and ccB in patients with primary clear cell renal cell carcinoma (ccRCC). Materials and methods: PET/MRI data were analysed retrospectively from eight patients. One hundred and sixty-eight radiomics features for each tumour sampling based on the regionally sampled tumours with 23 specimens were extracted. Sparse partial least squares discriminant analysis (SPLS-DA) was applied to feature screening on high-throughput radiomics features and project the selected features to low-dimensional intrinsic latent components as radiomics signatures. In addition, multilevel omics datasets were leveraged to explore the complementing information and elevate the discriminative ability. Results: The correct classification rate (CCR) for molecular subtype classification by SPLS-DA using only radiomics features was 86.96% with permutation test p=7×10−4. When multi-omics datasets including mRNA, microvascular density, and clinical parameters from each specimen were combined with radiomics features to refine the model of SPLS-DA, the best CCR was 95.65% with permutation test, p<10−4; however, even in the case of generating the classification based on transcription features, which is the reference standard, there is roughly 10% classification ambiguity. Thus, this classification level (86.96–95.65%) of the proposed method represents the discriminating level that is consistent with reality. Conclusion: Featured with high accuracy, an integrated multi-omics model of PET/MRI-based radiomics could be the first non-invasive investigation for disease risk stratification and guidance of treatment in patients with primary ccRCC.

Original languageEnglish
JournalClinical Radiology
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Renal Cell Carcinoma
Discriminant Analysis
Least-Squares Analysis
Positron-Emission Tomography
Magnetic Resonance Imaging
Neoplasms
Biomarkers
Messenger RNA

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma. / Yin, Q.; Hung, S. C.; Rathmell, W. K.; Shen, L.; Wang, L.; Lin, W.; Fielding, J. R.; Khandani, A. H.; Woods, M. E.; Milowsky, M. I.; Brooks, S. A.; Wallen, E. M.; Shen, Dinggang.

In: Clinical Radiology, 01.01.2018.

Research output: Contribution to journalArticle

Yin, Q, Hung, SC, Rathmell, WK, Shen, L, Wang, L, Lin, W, Fielding, JR, Khandani, AH, Woods, ME, Milowsky, MI, Brooks, SA, Wallen, EM & Shen, D 2018, 'Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma', Clinical Radiology. https://doi.org/10.1016/j.crad.2018.04.009
Yin, Q. ; Hung, S. C. ; Rathmell, W. K. ; Shen, L. ; Wang, L. ; Lin, W. ; Fielding, J. R. ; Khandani, A. H. ; Woods, M. E. ; Milowsky, M. I. ; Brooks, S. A. ; Wallen, E. M. ; Shen, Dinggang. / Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma. In: Clinical Radiology. 2018.
@article{eb62eb679d6a43518694890dcf2b621c,
title = "Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma",
abstract = "Aim: To identify combined positron-emission tomography (PET)/magnetic resonance imaging (MRI)-based radiomics as a surrogate biomarker of intratumour disease risk for molecular subtype ccA and ccB in patients with primary clear cell renal cell carcinoma (ccRCC). Materials and methods: PET/MRI data were analysed retrospectively from eight patients. One hundred and sixty-eight radiomics features for each tumour sampling based on the regionally sampled tumours with 23 specimens were extracted. Sparse partial least squares discriminant analysis (SPLS-DA) was applied to feature screening on high-throughput radiomics features and project the selected features to low-dimensional intrinsic latent components as radiomics signatures. In addition, multilevel omics datasets were leveraged to explore the complementing information and elevate the discriminative ability. Results: The correct classification rate (CCR) for molecular subtype classification by SPLS-DA using only radiomics features was 86.96{\%} with permutation test p=7×10−4. When multi-omics datasets including mRNA, microvascular density, and clinical parameters from each specimen were combined with radiomics features to refine the model of SPLS-DA, the best CCR was 95.65{\%} with permutation test, p<10−4; however, even in the case of generating the classification based on transcription features, which is the reference standard, there is roughly 10{\%} classification ambiguity. Thus, this classification level (86.96–95.65{\%}) of the proposed method represents the discriminating level that is consistent with reality. Conclusion: Featured with high accuracy, an integrated multi-omics model of PET/MRI-based radiomics could be the first non-invasive investigation for disease risk stratification and guidance of treatment in patients with primary ccRCC.",
author = "Q. Yin and Hung, {S. C.} and Rathmell, {W. K.} and L. Shen and L. Wang and W. Lin and Fielding, {J. R.} and Khandani, {A. H.} and Woods, {M. E.} and Milowsky, {M. I.} and Brooks, {S. A.} and Wallen, {E. M.} and Dinggang Shen",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.crad.2018.04.009",
language = "English",
journal = "Clinical Radiology",
issn = "0009-9260",
publisher = "W.B. Saunders Ltd",

}

TY - JOUR

T1 - Integrative radiomics expression predicts molecular subtypes of primary clear cell renal cell carcinoma

AU - Yin, Q.

AU - Hung, S. C.

AU - Rathmell, W. K.

AU - Shen, L.

AU - Wang, L.

AU - Lin, W.

AU - Fielding, J. R.

AU - Khandani, A. H.

AU - Woods, M. E.

AU - Milowsky, M. I.

AU - Brooks, S. A.

AU - Wallen, E. M.

AU - Shen, Dinggang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Aim: To identify combined positron-emission tomography (PET)/magnetic resonance imaging (MRI)-based radiomics as a surrogate biomarker of intratumour disease risk for molecular subtype ccA and ccB in patients with primary clear cell renal cell carcinoma (ccRCC). Materials and methods: PET/MRI data were analysed retrospectively from eight patients. One hundred and sixty-eight radiomics features for each tumour sampling based on the regionally sampled tumours with 23 specimens were extracted. Sparse partial least squares discriminant analysis (SPLS-DA) was applied to feature screening on high-throughput radiomics features and project the selected features to low-dimensional intrinsic latent components as radiomics signatures. In addition, multilevel omics datasets were leveraged to explore the complementing information and elevate the discriminative ability. Results: The correct classification rate (CCR) for molecular subtype classification by SPLS-DA using only radiomics features was 86.96% with permutation test p=7×10−4. When multi-omics datasets including mRNA, microvascular density, and clinical parameters from each specimen were combined with radiomics features to refine the model of SPLS-DA, the best CCR was 95.65% with permutation test, p<10−4; however, even in the case of generating the classification based on transcription features, which is the reference standard, there is roughly 10% classification ambiguity. Thus, this classification level (86.96–95.65%) of the proposed method represents the discriminating level that is consistent with reality. Conclusion: Featured with high accuracy, an integrated multi-omics model of PET/MRI-based radiomics could be the first non-invasive investigation for disease risk stratification and guidance of treatment in patients with primary ccRCC.

AB - Aim: To identify combined positron-emission tomography (PET)/magnetic resonance imaging (MRI)-based radiomics as a surrogate biomarker of intratumour disease risk for molecular subtype ccA and ccB in patients with primary clear cell renal cell carcinoma (ccRCC). Materials and methods: PET/MRI data were analysed retrospectively from eight patients. One hundred and sixty-eight radiomics features for each tumour sampling based on the regionally sampled tumours with 23 specimens were extracted. Sparse partial least squares discriminant analysis (SPLS-DA) was applied to feature screening on high-throughput radiomics features and project the selected features to low-dimensional intrinsic latent components as radiomics signatures. In addition, multilevel omics datasets were leveraged to explore the complementing information and elevate the discriminative ability. Results: The correct classification rate (CCR) for molecular subtype classification by SPLS-DA using only radiomics features was 86.96% with permutation test p=7×10−4. When multi-omics datasets including mRNA, microvascular density, and clinical parameters from each specimen were combined with radiomics features to refine the model of SPLS-DA, the best CCR was 95.65% with permutation test, p<10−4; however, even in the case of generating the classification based on transcription features, which is the reference standard, there is roughly 10% classification ambiguity. Thus, this classification level (86.96–95.65%) of the proposed method represents the discriminating level that is consistent with reality. Conclusion: Featured with high accuracy, an integrated multi-omics model of PET/MRI-based radiomics could be the first non-invasive investigation for disease risk stratification and guidance of treatment in patients with primary ccRCC.

UR - http://www.scopus.com/inward/record.url?scp=85047301201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047301201&partnerID=8YFLogxK

U2 - 10.1016/j.crad.2018.04.009

DO - 10.1016/j.crad.2018.04.009

M3 - Article

JO - Clinical Radiology

JF - Clinical Radiology

SN - 0009-9260

ER -