Pretreatment CT and PET radiomics predicting rectal cancer patients in response to neoadjuvant chemoradiotherapy.

CT PET neoadjuvant chemoradiation therapy pathologic response radiomics rectal cancer

Journal

Reports of practical oncology and radiotherapy : journal of Greatpoland Cancer Center in Poznan and Polish Society of Radiation Oncology
ISSN: 1507-1367
Titre abrégé: Rep Pract Oncol Radiother
Pays: Poland
ID NLM: 100885761

Informations de publication

Date de publication:
2021
Historique:
received: 28 05 2020
accepted: 12 12 2020
entrez: 5 5 2021
pubmed: 6 5 2021
medline: 6 5 2021
Statut: epublish

Résumé

The purpose of this study was to characterize pre-treatment non-contrast computed tomography (CT) and An exploratory analysis was performed using pre-treatment non-contrast CT and PET imaging dataset. The association of tumor regression grade (TRG) and neoadjuvant rectal (NAR) score with pre-treatment CT and PET features was assessed using machine learning algorithms. Three separate predictive models were built for composite features from CT + PET. The patterns of pathological response were TRG 0 (n = 13; 19.7%), 1 (n = 34; 51.5%), 2 (n = 16; 24.2%), and 3 (n = 3; 4.5%). There were 20 (30.3%) patients with low, 22 (33.3%) with intermediate and 24 (36.4%) with high NAR scores. Three separate predictive models were built for composite features from CT + PET and analyzed separately for clinical endpoints. Composite features with α = 0.2 resulted in the best predictive power using logistic regression. For pathological response prediction, the signature resulted in 88.1% accuracy in predicting TRG 0 The pre-treatment composite radiomics signatures were highly predictive of pathological response in rectal cancer treated with NACR T. A larger cohort is warranted for further validation.

Sections du résumé

BACKGROUND BACKGROUND
The purpose of this study was to characterize pre-treatment non-contrast computed tomography (CT) and
MATERIALS AND METHODS METHODS
An exploratory analysis was performed using pre-treatment non-contrast CT and PET imaging dataset. The association of tumor regression grade (TRG) and neoadjuvant rectal (NAR) score with pre-treatment CT and PET features was assessed using machine learning algorithms. Three separate predictive models were built for composite features from CT + PET.
RESULTS RESULTS
The patterns of pathological response were TRG 0 (n = 13; 19.7%), 1 (n = 34; 51.5%), 2 (n = 16; 24.2%), and 3 (n = 3; 4.5%). There were 20 (30.3%) patients with low, 22 (33.3%) with intermediate and 24 (36.4%) with high NAR scores. Three separate predictive models were built for composite features from CT + PET and analyzed separately for clinical endpoints. Composite features with α = 0.2 resulted in the best predictive power using logistic regression. For pathological response prediction, the signature resulted in 88.1% accuracy in predicting TRG 0
CONCLUSION CONCLUSIONS
The pre-treatment composite radiomics signatures were highly predictive of pathological response in rectal cancer treated with NACR T. A larger cohort is warranted for further validation.

Identifiants

pubmed: 33948299
doi: 10.5603/RPOR.a2021.0004
pii: rpor-26-1-29
pmc: PMC8086711
doi:

Types de publication

Journal Article

Langues

eng

Pagination

29-34

Informations de copyright

© 2021 Greater Poland Cancer Centre.

Déclaration de conflit d'intérêts

Conflicts of interest None were declared.

Références

Radiol Med. 2018 Apr;123(4):286-295
pubmed: 29230678
Eur Radiol. 2019 Nov;29(11):6080-6088
pubmed: 31028447
Clin Cancer Res. 2019 Jun 1;25(11):3266-3275
pubmed: 31010833
Neuro Oncol. 2020 Jun 9;22(6):797-805
pubmed: 31956919
Clin Radiol. 2004 Dec;59(12):1061-9
pubmed: 15556588
Br J Radiol. 2017 Feb;90(1070):20160642
pubmed: 27885836
J Natl Compr Canc Netw. 2018 Jul;16(7):909-915
pubmed: 30006431
Curr Colorectal Cancer Rep. 2015;11(5):275-280
pubmed: 26321890
Invest Radiol. 2015 Apr;50(4):239-45
pubmed: 25501017
Eur J Nucl Med Mol Imaging. 2018 Mar;45(3):365-375
pubmed: 29046927
J Nucl Med. 2014 Jun;55(6):891-7
pubmed: 24752672
J Med Imaging Radiat Oncol. 2020 Jun;64(3):444-449
pubmed: 32386109
Eur J Cancer. 2012 Mar;48(4):441-6
pubmed: 22257792
Eur J Nucl Med Mol Imaging. 2019 Apr;46(4):878-888
pubmed: 30637502
Eur J Nucl Med Mol Imaging. 2020 May;47(5):1116-1126
pubmed: 31982990

Auteurs

Zhigang Yuan (Z)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Marissa Frazer (M)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Anupam Rishi (A)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Kujtim Latifi (K)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Michal R Tomaszewski (MR)

Department of Radiology, Moffitt Cancer Center, Tampa, Florida, United States.

Eduardo G Moros (EG)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Vladimir Feygelman (V)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Seth Felder (S)

Department of GI Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Julian Sanchez (J)

Department of GI Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Sophie Dessureault (S)

Department of GI Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Iman Imanirad (I)

Department of GI Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Richard D Kim (RD)

Department of GI Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Louis B Harrison (LB)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Sarah E Hoffe (SE)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Geoffrey G Zhang (GG)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Jessica M Frakes (JM)

Department of Radiation Oncology, Moffitt Cancer Center, Tampa, Florida, United States.

Classifications MeSH