Online citations, reference lists, and bibliographies.
← Back to Search

Identification Of Predominant Histopathological Growth Patterns Of Colorectal Liver Metastasis By Multi-Habitat And Multi-Sequence Based Radiomics Analysis

Yuqi Han, Fan Chai, Jing-wei Wei, Y. Yue, J. Cheng, Dongsheng Gu, Yinli Zhang, Tong Tong, W. Sheng, Nan Hong, Yingjiang Ye, Yi Wang, J. Tian
Published 2020 · Medicine

Cite This
Download PDF
Analyze on Scholarcy
Share
Purpose: Developing an MRI-based radiomics model to effectively and accurately predict the predominant histopathologic growth patterns (HGPs) of colorectal liver metastases (CRLMs). Materials and Methods: In this study, 182 resected and histopathological proven CRLMs of chemotherapy-naive patients from two institutions, including 123 replacement CRLMs and 59 desmoplastic CRLMs, were retrospectively analyzed. Radiomics analysis was performed on two regions of interest (ROI), the tumor zone and the tumor-liver interface (TLI) zone. Decision tree (DT) algorithm was used for radiomics modeling on each MR sequence, and fused radiomics model was constructed by combining the radiomics signature of each sequence. The clinical and combination models were developed through multivariate logistic regression method. The performance of the developed models was assessed by receiver operating characteristic (ROC) curves with indicators of area under curve (AUC), accuracy, sensitivity, and specificity. A nomogram was constructed to evaluate the discrimination, calibration, and usefulness. Results: The fused radiomicstumor and radiomicsTLI models showed better performance than any single sequence and clinical model. In addition, the radiomicsTLI model exhibited better performance than radiomicstumor model (AUC of 0.912 vs. 0.879) in internal validation cohort. The combination model showed good discrimination, and the AUC of nomogram was 0.971, 0.909, and 0.905 in the training, internal validation, and external validation cohorts, respectively. Conclusion: MRI-based radiomics method has high potential in predicting the predominant HGPs of CRLM. Preoperative non-invasive identification of predominant HGPs could further explore the ability of HGPs as a potential biomarker for clinical treatment strategy, reflecting different biological pathways.
This paper references
supported by the ARCAD Group
KKH Goey (2018)
10.1007/s10585-012-9469-1
The histological growth pattern of colorectal cancer liver metastases has prognostic value
G. G. Van den Eynden (2012)
10.1158/1078-0432.CCR-12-1501
Do Imaging Biomarkers Relate to Outcome in Patients Treated with VEGF Inhibitors?
J. O’Connor (2012)
Lafferty JD, Williams CKI, Taylor JS, Zemel RS, Culotta A, editors
F Nie (2010)
a potential biomarker for the prediction of disease-free survival in earlystage (I or II) non-small cell lung cancer
Y Huang (2016)
10.1148/radiol.2015151169
Radiomics: Images Are More than Pictures, They Are Data
R. Gillies (2016)
10.1016/j.ejca.2018.05.010
Consensus statement on essential patient characteristics in systemic treatment trials for metastatic colorectal cancer: Supported by the ARCAD Group.
K. K. Goey (2018)
10.1148/RADIOLOGY.215.1.R00MR2989
Perilesional enhancement of hepatic metastases: correlation between MR imaging and histopathologic findings-initial observations.
R. Semelka (2000)
10.1371/journal.pone.0217411
Primary tumour location affects survival after resection of colorectal liver metastases: A two-institutional cohort study with international validation, systematic meta-analysis and a clinical risk score
E. Gasser (2019)
10.1136/bmjgast-2018-000217
Growth patterns of colorectal cancer liver metastases and their impact on prognosis: a systematic review
C. Fernández Moro (2018)
10.1038/nrclinonc.2012.2
Dynamic contrast-enhanced MRI in clinical trials of antivascular therapies
J. O’Connor (2012)
10.1038/srep43356
Associations between Tumor Vascularity, Vascular Endothelial Growth Factor Expression and PET/MRI Radiomic Signatures in Primary Clear-Cell–Renal-Cell-Carcinoma: Proof-of-Concept Study
Qingbo Yin (2017)
10.1002/path.966
Liver metastases from colorectal adenocarcinomas grow in three patterns with different angiogenesis and desmoplasia
P. Vermeulen (2001)
A multicenter study
Lola Falcón-Neyra (2016)
10.14309/ctg.0000000000000070
Selection Between Liver Resection Versus Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Study
Sirui Fu (2019)
10.1007/s10456-019-09661-5
Angiogenic desmoplastic histopathological growth pattern as a prognostic marker of good outcome in patients with colorectal liver metastases
B. Galjart (2019)
10.1177/0193945910394380
Systematic Review
F. Nabavi (2012)
10.1158/1078-0432.CCR-17-3783
Radiomics Signature on Magnetic Resonance Imaging: Association with Disease-Free Survival in Patients with Invasive Breast Cancer
Hyunjin Park (2018)
10.1148/rg.347130090
Update on the role of imaging in management of metastatic colorectal cancer.
Sree Harsha Tirumani (2014)
Dynamic contrast-enhancedMRI in clinical trials of antivascular therapies.Nat Rev Clin Oncol
JP O’Connor (2012)
10.3109/0284186X.2013.812798
Stability of FDG-PET Radiomics features: An integrated analysis of test-retest and inter-observer variability
R. Leijenaar (2013)
10.1007/BF02234637
Computed tomographic features of colorectal carcinoma liver metastases predict posthepatectomy patient survival
S. Nagakura (2001)
10.1016/J.COMPBIOMED.2019.04.014
Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme
Marie-Ange Lèbre (2019)
A proof of concept study
M. Cheetham (2017)
10.1158/1078-0432.CCR-16-0702
Large-scale Radiomic Profiling of Recurrent Glioblastoma Identifies an Imaging Predictor for Stratifying Anti-Angiogenic Treatment Response
P. Kickingereder (2016)
10.1245/s10434-019-07910-x
Prediction of Histopathologic Growth Patterns of Colorectal Liver Metastases with a Noninvasive Imaging Method
Jin Cheng (2019)
10.1007/s11547-019-01046-4
Texture features of colorectal liver metastases on pretreatment contrast-enhanced CT may predict response and prognosis in patients treated with bevacizumab-containing chemotherapy: a pilot study including comparison with standard chemotherapy
M. Ravanelli (2019)
10.1093/annonc/mdx034
Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology
E. Limkin (2017)
10.1038/bjc.2017.334
International consensus guidelines for scoring the histopathological growth patterns of liver metastasis
P. V. van Dam (2017)
10.1158/0008-5472.CAN-17-0122
Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer.
E. Rios Velazquez (2017)
Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization
F. Nie (2010)
10.1002/cjp2.100
Vascularization of colorectal carcinoma liver metastasis: insight into stratification of patients for anti‐angiogenic therapies
A. Lazaris (2018)
a TCGA/TCIA project
SH Patel (2017)
10.1158/1078-0432.CCR-17-0560
T2–FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project
S. Patel (2017)
10.1155/2012/907971
Histopathological Growth Pattern, Proteolysis and Angiogenesis in Chemonaive Patients Resected for Multiple Colorectal Liver Metastases
R. L. Eefsen (2012)
association with disease-free survival in patients with invasive breast cancer
H Park (2018)
10.1038/bjc.2011.191
DCE-MRI biomarkers of tumour heterogeneity predict CRC liver metastasis shrinkage following bevacizumab and FOLFOX-6
J. O'Connor (2011)
10.1093/neuonc/nox092
Quantitative imaging biomarkers for risk stratification of patients with recurrent glioblastoma treated with bevacizumab
P. Grossmann (2017)
10.1148/RADIOL.2016152234
Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer.
Yanqi Huang (2016)
10.1038/nm.4197
Vessel co-option mediates resistance to anti-angiogenic therapy in liver metastases
Sophia Frentzas (2016)



Semantic Scholar Logo Some data provided by SemanticScholar