Relapse predictability of topological signature on pretreatment planning CT images of stage I non-small cell lung cancer patients before treatment with stereotactic ablative radiotherapy.
non-small cell lung cancer (NSCLC)
radiotherapy
relapse
topology
Journal
Thoracic cancer
ISSN: 1759-7714
Titre abrégé: Thorac Cancer
Pays: Singapore
ID NLM: 101531441
Informations de publication
Date de publication:
08 2022
08 2022
Historique:
received:
06
04
2022
accepted:
04
05
2022
pubmed:
18
6
2022
medline:
5
8
2022
entrez:
17
6
2022
Statut:
ppublish
Résumé
This study aimed to explore the predictability of topological signatures linked to the locoregional relapse (LRR) and distant metastasis (DM) on pretreatment planning computed tomography images of stage I non-small cell lung cancer (NSCLC) patients before treatment with stereotactic ablative radiotherapy (SABR). We divided 125 primary stage I NSCLC patients (LRR: 34, DM: 22) into training (n = 60) and test datasets (n = 65), and the training dataset was augmented to 260 cases using a synthetic minority oversampling technique. The relapse predictabilities of the conventional wavelet-based features (WF), topology-based features [BF, Betti number (BN) map features; iBF, inverted BN map features], and their combined features (BWF, iBWF) were compared. The patients were stratified into high-risk and low-risk groups using the medians of the radiomics scores in the training dataset. For the LRR in the test, the iBF, iBWF, and WF showed statistically significant differences (p < 0.05), and the highest nLPC was obtained for the iBF. For the DM in the test, the iBWF showed a significant difference and the highest nLPC. The iBF indicated the potential of improving the LRR and DM prediction of stage I NSCLC patients prior to undergoing SABR.
Sections du résumé
BACKGROUND
This study aimed to explore the predictability of topological signatures linked to the locoregional relapse (LRR) and distant metastasis (DM) on pretreatment planning computed tomography images of stage I non-small cell lung cancer (NSCLC) patients before treatment with stereotactic ablative radiotherapy (SABR).
METHODS
We divided 125 primary stage I NSCLC patients (LRR: 34, DM: 22) into training (n = 60) and test datasets (n = 65), and the training dataset was augmented to 260 cases using a synthetic minority oversampling technique. The relapse predictabilities of the conventional wavelet-based features (WF), topology-based features [BF, Betti number (BN) map features; iBF, inverted BN map features], and their combined features (BWF, iBWF) were compared. The patients were stratified into high-risk and low-risk groups using the medians of the radiomics scores in the training dataset.
RESULTS
For the LRR in the test, the iBF, iBWF, and WF showed statistically significant differences (p < 0.05), and the highest nLPC was obtained for the iBF. For the DM in the test, the iBWF showed a significant difference and the highest nLPC.
CONCLUSION
The iBF indicated the potential of improving the LRR and DM prediction of stage I NSCLC patients prior to undergoing SABR.
Identifiants
pubmed: 35711108
doi: 10.1111/1759-7714.14483
pmc: PMC9346172
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
2117-2126Informations de copyright
© 2022 The Authors. Thoracic Cancer published by China Lung Oncology Group and John Wiley & Sons Australia, Ltd.
Références
Sci Rep. 2018 Feb 5;8(1):2354
pubmed: 29403060
Med Phys. 2020 Jun;47(5):2197-2205
pubmed: 32096876
Med Phys. 2020 Sep;47(9):4634-4643
pubmed: 32645224
Thorac Cancer. 2019 Jun;10(6):1489-1499
pubmed: 31124275
CA Cancer J Clin. 2021 May;71(3):209-249
pubmed: 33538338
Med Phys. 2018 Nov;45(11):5116-5128
pubmed: 30230556
Neoplasma. 2003;50(1):66-73
pubmed: 12687281
Front Oncol. 2021 Oct 11;11:746785
pubmed: 34707992
Thorac Cancer. 2022 Aug;13(15):2117-2126
pubmed: 35711108
Phys Med Biol. 2015 Jul 21;60(14):5471-96
pubmed: 26119045
Thorac Cancer. 2016 Jul;7(4):442-51
pubmed: 27385987
Sci Rep. 2018 Jul 10;8(1):10393
pubmed: 29991684
Cancer. 2018 Feb 15;124(4):667-678
pubmed: 29266226
Int J Radiat Oncol Biol Phys. 2011 Dec 1;81(5):1352-8
pubmed: 20638194
JAMA. 1982 May 14;247(18):2543-6
pubmed: 7069920
Phys Med. 2020 Jan;69:90-100
pubmed: 31855844
Radiology. 2016 Oct;281(1):270-8
pubmed: 27046074
Am Fam Physician. 2007 Jan 1;75(1):56-63
pubmed: 17225705
Int J Radiat Oncol Biol Phys. 2016 Apr 1;94(5):1121-8
pubmed: 26907916
Eur J Radiol. 2014 Jul;83(7):1275-1281
pubmed: 24840477
JAMA Oncol. 2018 Sep 1;4(9):1263-1266
pubmed: 29852037
Lung Cancer. 2018 Jan;115:34-41
pubmed: 29290259
Int J Radiat Oncol Biol Phys. 2014 Nov 1;90(3):603-11
pubmed: 25052562
J Natl Compr Canc Netw. 2017 Apr;15(4):504-535
pubmed: 28404761
Lung Cancer. 2018 Nov;125:185-191
pubmed: 30429018
PLoS One. 2021 Jan 11;16(1):e0244354
pubmed: 33428651