Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug 14:10:1363.
doi: 10.3389/fonc.2020.01363. eCollection 2020.

Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis

Yuqi Han  1   2   3 , Fan Chai  4 , Jingwei Wei  2   3 , Yali Yue  5   6 , Jin Cheng  4 , Dongsheng Gu  2   3 , Yinli Zhang  7 , Tong Tong  5   6 , Weiqi Sheng  6   8 , Nan Hong  4 , Yingjiang Ye  9 , Yi Wang  4 , Jie Tian  2   3   10   11
Affiliations

Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis

Yuqi Han et al. Front Oncol. .

Abstract

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.

Keywords: colorectal cancer; histopathologic growth patterns; liver metastasis; magnetic resonance; radiomics.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Flowchart for this study. (A) The T2W images were used as an example to illustrate the segmentation process, and slicer-to-slicer delineation obtained two sets of ROI. (B) Multiple radiomic features were extracted from two sets of ROI. Clinical features were obtained from medical records, and qualitative gross imaging features were evaluated by two board-certified radiologists. (C) Intra-/inter-observer coefficients were used to select the stability features, and decision tree were used to construct the radiomics model in each sequence. The best performed sequences and related clinical features were used to form the final classification model. The ROC, calibration curve, and decision curve were used to evaluate the performance of models.
Figure 2
Figure 2
(A) ROC curve for the clinical model. (B) ROC curves for the radiomicsTLI model. (C) ROC curves for the combination model.
Figure 3
Figure 3
(A) Violin graph of distribution of clinical model between replacement and desmoplastic HGPs. (B) Violin graph of distribution of radiomicsTLI model between replacement and desmoplastic HGPs. (C) Violin graph of distribution of combination model between replacement and desmoplastic HGPs.
Figure 4
Figure 4
Confusion matrixes for clinical, radiomicsTLI, and combination model in all cohorts.
Figure 5
Figure 5
Development of nomogram and calibration curves. (A) Nomogram based on radiomics signatures and clinical factors. Calibration curves of the radiomics nomogram in the (B) training cohort, (C) internal validation cohort, and (D) external validation cohorts.
Figure 6
Figure 6
The decision curve of the nomogram.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Goey KKH, Sørbye H, Glimelius B, Adams RA, André T, Arnold D, et al. . Consensus statement on essential patient characteristics in systemic treatment trials for metastatic colorectal cancer: supported by the ARCAD Group. Eur J Cancer. (2018) 100:35–45. 10.1016/j.ejca.2018.05.010 - DOI - PubMed
    1. Moro CF, Béla B, Marco G. Growth patterns of colorectal cancer liver metastases and their impact on prognosis: a systematic review. BMJ Open Gastroenterol. (2018) 5:e000217. 10.1136/bmjgast-2018-000217 - DOI - PMC - PubMed
    1. van Dam PJ, Van der Stok EP, Teuwen LA, Van den Eynden GG, Illemann M, Frentzas S, et al. . International consensus guidelines for scoring the histopathological growth patterns of liver metastasis. Br J Cancer. (2017) 117:1427–41. 10.1038/bjc.2017.334 - DOI - PMC - PubMed
    1. Vermeulen PB, Colpaert C, Salgado R, Royers R, Hellemans H, Van Den Heuvel E, et al. . Liver metastases from colorectal adenocarcinomas grow in three patterns with different angiogenesis and desmoplasia. J Pathol. (2001) 195:336–42. 10.1002/path.966 - DOI - PubMed
    1. Frentzas S, Simoneau E, Bridgeman VL, Vermeulen PB, Foo S, Kostaras E, et al. . Vessel co-option mediates resistance to anti-angiogenic therapy in liver metastases. Nat Med. (2016) 22:1294–302. 10.1038/nm.4197 - DOI - PMC - PubMed

LinkOut - more resources