Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone

F. C. R. Staal; M. Taghavi; D. J. van der Reijd; F. M. Gomez; F. Imani; E. G. Klompenhouwer; D. Meek; S. Roberti; M. de Boer; D. M. J. Lambregts; R. G. H. Beets-Tan; M. Maas

doi:10.1016/j.ejrad.2021.109773

Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone

F. C. R. Staal, M. Taghavi, D. J. van der Reijd, F. M. Gomez, F. Imani, E. G. Klompenhouwer, D. Meek, S. Roberti, M. de Boer, D. M. J. Lambregts, R. G. H. Beets-Tan, M. Maas^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Purpose: To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM). Materials and methods: Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV). Results: Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6-115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p =

Original language	English
Article number	109773
Number of pages	7
Journal	European Journal of Radiology
Volume	141
DOIs	https://doi.org/10.1016/j.ejrad.2021.109773
Publication status	Published - Aug 2021

Keywords

Colorectal neoplasms
Radiofrequency ablation
Neoplasm metastasis
Liver
Ablation techniques
Neoplasm recurrence
Local
Tomography
X-ray computed
RADIOFREQUENCY ABLATION
CANCER PATIENTS
STANDARDIZATION
TERMINOLOGY
PERFORMANCE
RECURRENCE
SURVIVAL
CRITERIA
TEXTURE

Access to Document

10.1016/j.ejrad.2021.109773Licence: Unspecified

Cite this

Staal, F. C. R., Taghavi, M., van der Reijd, D. J., Gomez, F. M., Imani, F., Klompenhouwer, E. G., Meek, D., Roberti, S., de Boer, M., Lambregts, D. M. J., Beets-Tan, R. G. H., & Maas, M. (2021). Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone. European Journal of Radiology, 141, Article 109773. https://doi.org/10.1016/j.ejrad.2021.109773

@article{a002ede2722b4f908d6cd91dd60189d7,

title = "Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone",

abstract = "Purpose: To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM). Materials and methods: Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV). Results: Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6-115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p =",

keywords = "Colorectal neoplasms, Radiofrequency ablation, Neoplasm metastasis, Liver, Ablation techniques, Neoplasm recurrence, Local, Tomography, X-ray computed, RADIOFREQUENCY ABLATION, CANCER PATIENTS, STANDARDIZATION, TERMINOLOGY, PERFORMANCE, RECURRENCE, SURVIVAL, CRITERIA, TEXTURE",

author = "Staal, {F. C. R.} and M. Taghavi and {van der Reijd}, {D. J.} and Gomez, {F. M.} and F. Imani and Klompenhouwer, {E. G.} and D. Meek and S. Roberti and {de Boer}, M. and Lambregts, {D. M. J.} and Beets-Tan, {R. G. H.} and M. Maas",

note = "Publisher Copyright: {\textcopyright} 2021",

year = "2021",

month = aug,

doi = "10.1016/j.ejrad.2021.109773",

language = "English",

volume = "141",

journal = "European Journal of Radiology",

issn = "0720-048X",

publisher = "Elsevier Ireland Ltd",

}

Staal, FCR, Taghavi, M, van der Reijd, DJ, Gomez, FM, Imani, F, Klompenhouwer, EG, Meek, D, Roberti, S, de Boer, M, Lambregts, DMJ, Beets-Tan, RGH & Maas, M 2021, 'Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone', European Journal of Radiology, vol. 141, 109773. https://doi.org/10.1016/j.ejrad.2021.109773

TY - JOUR

T1 - Predicting local tumour progression after ablation for colorectal liver metastases

T2 - CT-based radiomics of the ablation zone

AU - Staal, F. C. R.

AU - Taghavi, M.

AU - van der Reijd, D. J.

AU - Gomez, F. M.

AU - Imani, F.

AU - Klompenhouwer, E. G.

AU - Meek, D.

AU - Roberti, S.

AU - de Boer, M.

AU - Lambregts, D. M. J.

AU - Beets-Tan, R. G. H.

AU - Maas, M.

PY - 2021/8

Y1 - 2021/8

N2 - Purpose: To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM). Materials and methods: Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV). Results: Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6-115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p =

AB - Purpose: To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM). Materials and methods: Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV). Results: Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6-115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p =

KW - Colorectal neoplasms

KW - Radiofrequency ablation

KW - Neoplasm metastasis

KW - Liver

KW - Ablation techniques

KW - Neoplasm recurrence

KW - Local

KW - Tomography

KW - X-ray computed

KW - RADIOFREQUENCY ABLATION

KW - CANCER PATIENTS

KW - STANDARDIZATION

KW - TERMINOLOGY

KW - PERFORMANCE

KW - RECURRENCE

KW - SURVIVAL

KW - CRITERIA

KW - TEXTURE

U2 - 10.1016/j.ejrad.2021.109773

DO - 10.1016/j.ejrad.2021.109773

M3 - Article

C2 - 34022475

SN - 0720-048X

VL - 141

JO - European Journal of Radiology

JF - European Journal of Radiology

M1 - 109773

ER -