Automated Prediction of the Response to Neoadjuvant Chemoradiotherapy in Patients Affected by Rectal Cancer.
artificial intelligence
machine and deep learning
medical imaging
radiomics
Journal
Cancers
ISSN: 2072-6694
Titre abrégé: Cancers (Basel)
Pays: Switzerland
ID NLM: 101526829
Informations de publication
Date de publication:
29 04 2022
29 04 2022
Historique:
received:
01
03
2022
revised:
22
04
2022
accepted:
27
04
2022
entrez:
14
5
2022
pubmed:
15
5
2022
medline:
15
5
2022
Statut:
epublish
Résumé
Rectal cancer is a malignant neoplasm of the large intestine resulting from the uncontrolled proliferation of the rectal tract. Predicting the pathologic response of neoadjuvant chemoradiotherapy at an MRI primary staging scan in patients affected by locally advanced rectal cancer (LARC) could lead to significant improvement in the survival and quality of life of the patients. In this study, the possibility of automatizing this estimation from a primary staging MRI scan, using a fully automated artificial intelligence-based model for the segmentation and consequent characterization of the tumor areas using radiomic features was evaluated. The TRG score was used to evaluate the clinical outcome. Forty-three patients under treatment in the IRCCS Sant'Orsola-Malpighi Polyclinic were retrospectively selected for the study; a U-Net model was trained for the automated segmentation of the tumor areas; the radiomic features were collected and used to predict the tumor regression grade (TRG) score. The segmentation of tumor areas outperformed the state-of-the-art results in terms of the Dice score coefficient or was comparable to them but with the advantage of considering mucinous cases. Analysis of the radiomic features extracted from the lesion areas allowed us to predict the TRG score, with the results agreeing with the state-of-the-art results. The results obtained regarding TRG prediction using the proposed fully automated pipeline prove its possible usage as a viable decision support system for radiologists in clinical practice.
Sections du résumé
BACKGROUND
Rectal cancer is a malignant neoplasm of the large intestine resulting from the uncontrolled proliferation of the rectal tract. Predicting the pathologic response of neoadjuvant chemoradiotherapy at an MRI primary staging scan in patients affected by locally advanced rectal cancer (LARC) could lead to significant improvement in the survival and quality of life of the patients. In this study, the possibility of automatizing this estimation from a primary staging MRI scan, using a fully automated artificial intelligence-based model for the segmentation and consequent characterization of the tumor areas using radiomic features was evaluated. The TRG score was used to evaluate the clinical outcome.
METHODS
Forty-three patients under treatment in the IRCCS Sant'Orsola-Malpighi Polyclinic were retrospectively selected for the study; a U-Net model was trained for the automated segmentation of the tumor areas; the radiomic features were collected and used to predict the tumor regression grade (TRG) score.
RESULTS
The segmentation of tumor areas outperformed the state-of-the-art results in terms of the Dice score coefficient or was comparable to them but with the advantage of considering mucinous cases. Analysis of the radiomic features extracted from the lesion areas allowed us to predict the TRG score, with the results agreeing with the state-of-the-art results.
CONCLUSIONS
The results obtained regarding TRG prediction using the proposed fully automated pipeline prove its possible usage as a viable decision support system for radiologists in clinical practice.
Identifiants
pubmed: 35565360
pii: cancers14092231
doi: 10.3390/cancers14092231
pmc: PMC9100060
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
Radiother Oncol. 2020 Jan;142:246-252
pubmed: 31431368
IEEE Trans Cybern. 2021 Nov;51(11):5397-5408
pubmed: 32248143
J Natl Compr Canc Netw. 2011 Nov;9(11):1238-90
pubmed: 22056656
Med Ultrason. 2015 Jun;17(2):227-34
pubmed: 26052575
BMC Med Imaging. 2021 Feb 16;21(1):30
pubmed: 33593304
Ann Oncol. 2013 Oct;24 Suppl 6:vi64-72
pubmed: 24078664
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Eur J Nucl Med Mol Imaging. 2019 Apr;46(4):878-888
pubmed: 30637502
Diagnostics (Basel). 2021 Apr 28;11(5):
pubmed: 33924854
Front Oncol. 2021 Aug 04;11:711747
pubmed: 34422664
Diagnostics (Basel). 2021 Apr 23;11(5):
pubmed: 33922483
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1675-1678
pubmed: 33018318
Invest Radiol. 2015 Apr;50(4):239-45
pubmed: 25501017
Cancers (Basel). 2021 Apr 28;13(9):
pubmed: 33925250
Ann Surg Oncol. 2010 Jun;17(6):1471-4
pubmed: 20180029
Sci Rep. 2017 Jul 13;7(1):5301
pubmed: 28706185
Oncol Rep. 2022 Feb;47(2):
pubmed: 34935061
Eur Radiol. 2018 Apr;28(4):1465-1475
pubmed: 29043428
J R Soc Med. 2002 Dec;95(12):587-90
pubmed: 12461143