Radiomics Analysis of Multi-Sequence MR Images For Predicting Microsatellite Instability Status Preoperatively in Rectal Cancer.

magnetic resonance microsatellite instability multi-sequence MR radiomics rectal cancer

Journal

Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867

Informations de publication

Date de publication:
2021
Historique:
received: 19 04 2021
accepted: 21 06 2021
entrez: 26 7 2021
pubmed: 27 7 2021
medline: 27 7 2021
Statut: epublish

Résumé

Immunotherapy, adjuvant chemotherapy, and prognosis of colorectal cancer are associated with MSI. Biopsy pathology cannot fully reflect the MSI status and heterogeneity of rectal cancer. To develop a radiomic-based model to preoperatively predict MSI status in rectal cancer on MRI. The patients were divided into two cohorts (training and testing) at a 7:3 ratio. Radiomics features, including intensity, texture, and shape, were extracted from the segmented volumes of interest based on T2-weighted and ADC imaging. Independent sample t test, Mann-Whitney test, the chi-squared test, Receiver operating characteristic curves, calibration curves, decision curve analysis and multi-variate logistic regression analysis. The radiomics models were significantly associated with MSI status. The T2-based model showed an area under the curve of 0.870 with 95% CI: 0.794-0.945 (accuracy, 0.845; specificity, 0.714; sensitivity, 0.976) in training set and 0.895 with 95% CI, 0.777-1.000 (accuracy, 0.778; specificity, 0.887; sensitivity, 0.772) in testing set. The ADC-based model had an AUC of 0.790 with 95% CI: 0.794-0.945 (accuracy, 0.774; specificity, 0.714; sensitivity, 0.976) in training set and 0.796 with 95% CI, 0.777-1.000 (accuracy, 0.778; specificity, 0.889; sensitivity, 0.772) in testing set. The combined model integrating T2 and ADC features showed an AUC of 0.908 with 95% CI: 0.845-0.971 (accuracy, 0.857; specificity, 0.762; sensitivity, 0.952) in training set and 0.926 with 95% CI: 0.813-1.000 (accuracy, 0.852; specificity, 1.000; sensitivity, 0.778) in testing set. Calibration curve showed that the combined score had a good calibration degree, and the decision curve demonstrated that the combined score was of benefit for clinical use. Radiomics analysis of T2W and ADC images showed significant relevance in the prediction of microsatellite status, and the accuracy of combined model of ADC and T2W features was better than either alone.

Sections du résumé

Background
Immunotherapy, adjuvant chemotherapy, and prognosis of colorectal cancer are associated with MSI. Biopsy pathology cannot fully reflect the MSI status and heterogeneity of rectal cancer.
Purpose
To develop a radiomic-based model to preoperatively predict MSI status in rectal cancer on MRI.
Assessment
The patients were divided into two cohorts (training and testing) at a 7:3 ratio. Radiomics features, including intensity, texture, and shape, were extracted from the segmented volumes of interest based on T2-weighted and ADC imaging.
Statistical Tests
Independent sample t test, Mann-Whitney test, the chi-squared test, Receiver operating characteristic curves, calibration curves, decision curve analysis and multi-variate logistic regression analysis.
Results
The radiomics models were significantly associated with MSI status. The T2-based model showed an area under the curve of 0.870 with 95% CI: 0.794-0.945 (accuracy, 0.845; specificity, 0.714; sensitivity, 0.976) in training set and 0.895 with 95% CI, 0.777-1.000 (accuracy, 0.778; specificity, 0.887; sensitivity, 0.772) in testing set. The ADC-based model had an AUC of 0.790 with 95% CI: 0.794-0.945 (accuracy, 0.774; specificity, 0.714; sensitivity, 0.976) in training set and 0.796 with 95% CI, 0.777-1.000 (accuracy, 0.778; specificity, 0.889; sensitivity, 0.772) in testing set. The combined model integrating T2 and ADC features showed an AUC of 0.908 with 95% CI: 0.845-0.971 (accuracy, 0.857; specificity, 0.762; sensitivity, 0.952) in training set and 0.926 with 95% CI: 0.813-1.000 (accuracy, 0.852; specificity, 1.000; sensitivity, 0.778) in testing set. Calibration curve showed that the combined score had a good calibration degree, and the decision curve demonstrated that the combined score was of benefit for clinical use.
Data Conclusion
Radiomics analysis of T2W and ADC images showed significant relevance in the prediction of microsatellite status, and the accuracy of combined model of ADC and T2W features was better than either alone.

Identifiants

pubmed: 34307164
doi: 10.3389/fonc.2021.697497
pmc: PMC8293900
doi:

Types de publication

Journal Article

Langues

eng

Pagination

697497

Commentaires et corrections

Type : ErratumIn

Informations de copyright

Copyright © 2021 Li, Dai, Liu, Pan, Yang and Zhang.

Déclaration de conflit d'intérêts

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Références

NMR Biomed. 2018 Jan;31(1):
pubmed: 29073725
Clin Radiol. 2017 Nov;72(11):951-958
pubmed: 28728757
Histopathology. 2013 Apr;62(5):723-30
pubmed: 23425253
Clin Radiol. 2017 Aug;72(8):691.e1-691.e10
pubmed: 28274509
N Engl J Med. 2003 Jul 17;349(3):247-57
pubmed: 12867608
Br J Cancer. 2014 Dec 9;111(12):2205-13
pubmed: 25268373
J Clin Oncol. 2005 Jan 20;23(3):609-18
pubmed: 15659508
J Clin Oncol. 2010 Jul 10;28(20):3219-26
pubmed: 20498393
Br J Cancer. 2015 Jul 28;113(3):500-9
pubmed: 26068398
Gastroenterology Res. 2011 Aug;4(4):157-161
pubmed: 27942333
Eur Radiol. 2018 May;28(5):2058-2067
pubmed: 29335867
NPJ Breast Cancer. 2016;2:
pubmed: 27853751
Eur Radiol. 2019 Jul;29(7):3782-3790
pubmed: 30903331
Gastroenterology. 2010 Jun;138(6):2073-2087.e3
pubmed: 20420947
Curr Probl Cancer. 2018 Nov;42(6):548-559
pubmed: 30119911
N Engl J Med. 2000 Jan 13;342(2):69-77
pubmed: 10631274
Hum Pathol. 2017 May;63:33-39
pubmed: 28232158
J Gastrointest Oncol. 2013 Jun;4(2):182-92
pubmed: 23730514
Expert Rev Gastroenterol Hepatol. 2021 Mar;15(3):291-304
pubmed: 33138649

Auteurs

Zongbao Li (Z)

China-Japan Union Hospital of Jilin University, Changchun, China.

Hui Dai (H)

The First Affiliated Hospital of Soochow University, Suzhou, China.

Yunxia Liu (Y)

China-Japan Union Hospital of Jilin University, Changchun, China.

Feng Pan (F)

China-Japan Union Hospital of Jilin University, Changchun, China.

Yanyan Yang (Y)

China-Japan Union Hospital of Jilin University, Changchun, China.

Mengchao Zhang (M)

China-Japan Union Hospital of Jilin University, Changchun, China.

Classifications MeSH