Evaluation of a convolution neural network for baseline total tumor metabolic volume on [
Artificial intelligence
Lymphoma
Positron emission tomography
Tumor volume
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
May 2023
May 2023
Historique:
received:
15
07
2022
accepted:
09
12
2022
revised:
20
10
2022
medline:
25
4
2023
pubmed:
5
1
2023
entrez:
4
1
2023
Statut:
ppublish
Résumé
New PET data-processing tools allow for automatic lesion selection and segmentation by a convolution neural network using artificial intelligence (AI) to obtain total metabolic tumor volume (TMTV) and total lesion glycolysis (TLG) routinely at the clinical workstation. Our objective was to evaluate an AI implemented in a new version of commercial software to verify reproducibility of results and time savings in a daily workflow. Using the software to obtain TMTV and TLG, two nuclear physicians applied five methods to retrospectively analyze data for 51 patients. Methods 1 and 2 were fully automated with exclusion of lesions ≤ 0.5 mL and ≤ 0.1 mL, respectively. Methods 3 and 4 were fully automated with physician review. Method 5 was semi-automated and used as reference. Time and number of clicks to complete the measurement were recorded for each method. Inter-instrument and inter-observer variation was assessed by the intra-class coefficient (ICC) and Bland-Altman plots. Between methods 3 and 5, for the main user, the ICC was 0.99 for TMTV and 1.0 for TLG. Between the two users applying method 3, ICC was 0.97 for TMTV and 0.99 for TLG. Mean processing time (± standard deviation) was 20 s ± 9.0 for method 1, 178 s ± 125.7 for method 3, and 326 s ± 188.6 for method 5 (p < 0.05). AI-enabled lesion detection software offers an automated, fast, reliable, and consistently performing tool for obtaining TMTV and TLG in a daily workflow. • Our study shows that artificial intelligence lesion detection software is an automated, fast, reliable, and consistently performing tool for obtaining total metabolic tumor volume and total lesion glycolysis in a daily workflow.
Identifiants
pubmed: 36600126
doi: 10.1007/s00330-022-09375-1
pii: 10.1007/s00330-022-09375-1
doi:
Substances chimiques
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3386-3395Informations de copyright
© 2023. The Author(s), under exclusive licence to European Society of Radiology.
Références
Flodr P, Latalova P, Tichy M, et al (2014) Diffuse large B-cell lymphoma: the history, current view and new perspectives. Neoplasma 62:491–504. https://doi.org/10.4149/neo_2014_062
Cottereau A-S, Lanic H, Mareschal S et al (2016) Molecular profile and FDG-PET/CT total metabolic tumor volume improve risk classification at diagnosis for patients with diffuse large B-cell lymphoma. Clin Cancer Res 22:3801–3809. https://doi.org/10.1158/1078-0432.CCR-15-2825
doi: 10.1158/1078-0432.CCR-15-2825
pubmed: 26936916
Shagera QA, Cheon GJ, Koh Y et al (2019) Prognostic value of metabolic tumour volume on baseline 18F-FDG PET/CT in addition to NCCN-IPI in patients with diffuse large B-cell lymphoma: further stratification of the group with a high-risk NCCN-IPI. Eur J Nucl Med Mol Imaging 46:1417–1427. https://doi.org/10.1007/s00259-019-04309-4
doi: 10.1007/s00259-019-04309-4
pubmed: 30941463
Wight JC, Chong G, Grigg AP, Hawkes EA (2018) Prognostication of diffuse large B-cell lymphoma in the molecular era: moving beyond the IPI. Blood Rev 32:400–415. https://doi.org/10.1016/j.blre.2018.03.005
doi: 10.1016/j.blre.2018.03.005
pubmed: 29605154
Nowakowski GS, Feldman T, Rimsza LM et al (2019) Integrating precision medicine through evaluation of cell of origin in treatment planning for diffuse large B-cell lymphoma. Blood Cancer J 9:48. https://doi.org/10.1038/s41408-019-0208-6
doi: 10.1038/s41408-019-0208-6
pubmed: 31097684
pmcid: 6522601
Barrington SF, Mikhaeel NG, Kostakoglu L et al (2014) Role of imaging in the staging and response assessment of lymphoma: Consensus of the International Conference on Malignant Lymphomas Imaging Working Group. J Clin Oncol 32:3048–3058. https://doi.org/10.1200/JCO.2013.53.5229
doi: 10.1200/JCO.2013.53.5229
pubmed: 25113771
pmcid: 5015423
Vercellino L, Cottereau A-S, Casasnovas O et al (2020) High total metabolic tumor volume at baseline predicts survival independent of response to therapy. Blood 135:1396–1405. https://doi.org/10.1182/blood.2019003526
doi: 10.1182/blood.2019003526
pubmed: 31978225
pmcid: 7162688
Schindelin J, Arganda-Carreras I, Frise E et al (2012) Fiji - an Open Source platform for biological image analysis. Nat Methods 9. https://doi.org/10.1038/nmeth.2019
Barrington SF, Zwezerijnen BGJC, de Vet HCW et al (2021) Automated segmentation of baseline metabolic total tumor burden in diffuse large B-cell lymphoma: which method is most successful? A Study on Behalf of the PETRA Consortium. J Nucl Med 62:332–337. https://doi.org/10.2967/jnumed.119.238923
doi: 10.2967/jnumed.119.238923
pubmed: 32680929
pmcid: 8049348
Ilyas H, Mikhaeel NG, Dunn JT et al (2018) Defining the optimal method for measuring baseline metabolic tumour volume in diffuse large B cell lymphoma. Eur J Nucl Med Mol Imaging 45:1142–1154. https://doi.org/10.1007/s00259-018-3953-z
doi: 10.1007/s00259-018-3953-z
pubmed: 29460024
pmcid: 5953976
Barrington SF, Meignan M (2019) Time to prepare for risk adaptation in lymphoma by standardizing measurement of metabolic tumor burden. J Nucl Med 60:1096–1102. https://doi.org/10.2967/jnumed.119.227249
doi: 10.2967/jnumed.119.227249
pubmed: 30954945
pmcid: 6681699
Sibille L, Seifert R, Avramovic N et al (2020) 18F-FDG PET/CT uptake classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology 294:445–452. https://doi.org/10.1148/radiol.2019191114
doi: 10.1148/radiol.2019191114
pubmed: 31821122
Hans CP, Weisenburger DD, Greiner TC et al (2004) Confirmation of the molecular classification of diffuse large B-cell lymphoma by immunohistochemistry using a tissue microarray. Blood 103:275–282. https://doi.org/10.1182/blood-2003-05-1545
doi: 10.1182/blood-2003-05-1545
pubmed: 14504078
Wahl RL, Jacene H, Kasamon Y, Lodge MA (2009) From RECIST to PERCIST: evolving considerations for PET response criteria in solid tumors. J Nucl Med 50:122S–150S. https://doi.org/10.2967/jnumed.108.057307
doi: 10.2967/jnumed.108.057307
pubmed: 19403881
Meignan M, Sasanelli M, Casasnovas RO et al (2014) Metabolic tumour volumes measured at staging in lymphoma: methodological evaluation on phantom experiments and patients. Eur J Nucl Med Mol Imaging 41:1113–1122. https://doi.org/10.1007/s00259-014-2705-y
doi: 10.1007/s00259-014-2705-y
pubmed: 24570094
Boellaard R, Delgado-Bolton R, Oyen WJG et al (2015) FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging 42:328–354. https://doi.org/10.1007/s00259-014-2961-x
Guo B, Tan X, Ke Q, Cen H (2019) Prognostic value of baseline metabolic tumor volume and total lesion glycolysis in patients with lymphoma: a meta-analysis. PLoS One 14:e0210224. https://doi.org/10.1371/journal.pone.0210224
Blanc-Durand P, Jégou S, Kanoun S et al (2021) Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network. Eur J Nucl Med Mol Imaging 48:1362–1370. https://doi.org/10.1007/s00259-020-05080-7
doi: 10.1007/s00259-020-05080-7
pubmed: 33097974
Tout M, Casasnovas O, Meignan M et al (2017) Rituximab exposure is influenced by baseline metabolic tumor volume and predicts outcome of DLBCL patients: a Lymphoma Study Association report. Blood 129:2616–2623. https://doi.org/10.1182/blood-2016-10-744292
doi: 10.1182/blood-2016-10-744292
pubmed: 28251914
Capobianco N, Meignan M, Cottereau A-S et al (2021) Deep-learning 18F-FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma. J Nucl Med 62:30–36. https://doi.org/10.2967/jnumed.120.242412
doi: 10.2967/jnumed.120.242412
pubmed: 32532925
pmcid: 8679589
Pinochet P, Eude F, Becker S et al (2021) Evaluation of an automatic classification algorithm using convolutional neural networks in oncological positron emission tomography. Front Med (Lausanne) 8:628179. https://doi.org/10.3389/fmed.2021.628179
doi: 10.3389/fmed.2021.628179
pubmed: 33718406
Burggraaff CN, Rahman F, Kaßner I et al (2020) Optimizing workflows for fast and reliable metabolic tumor volume measurements in diffuse large B cell lymphoma. Mol Imaging Biol 22:1102–1110. https://doi.org/10.1007/s11307-020-01474-z
doi: 10.1007/s11307-020-01474-z
pubmed: 31993925
pmcid: 7343740
Nguyen NC, Vercher-Conejero J, Faulhaber P (2019) Tumor volume delineation: a pilot study comparing a digital positron-emission tomography prototype with an analog positron-emission tomography system. World J Nucl Med 18:45–51. https://doi.org/10.4103/wjnm.WJNM_22_18
doi: 10.4103/wjnm.WJNM_22_18
pubmed: 30774546
pmcid: 6357708
de Jong TL, Koopman D, van Dalen JA et al (2022) Performance of digital PET/CT compared with conventional PET/CT in oncologic patients: a prospective comparison study. Ann Nucl Med 36:756–764. https://doi.org/10.1007/s12149-022-01758-0
doi: 10.1007/s12149-022-01758-0
pubmed: 35727433
Koopman D, van Dalen JA, Stevens H et al (2020) Performance of digital PET compared with high-resolution conventional PET in patients with cancer. J Nucl Med 61:1448–1454. https://doi.org/10.2967/jnumed.119.238105
doi: 10.2967/jnumed.119.238105
pubmed: 32060217
Cottereau A-S, Buvat I, Kanoun S et al (2018) Is there an optimal method for measuring baseline metabolic tumor volume in diffuse large B cell lymphoma? Eur J Nucl Med Mol Imaging 45:1463–1464. https://doi.org/10.1007/s00259-018-4005-4
doi: 10.1007/s00259-018-4005-4
pubmed: 29651546
Sun R, Deutsch E, Fournier L (2022) Intelligence artificielle et imagerie médicale. Bull Cancer 109:83–88. https://doi.org/10.1016/j.bulcan.2021.09.009
Iacoboni G, Simó M, Villacampa G et al (2021) Prognostic impact of total metabolic tumor volume in large B-cell lymphoma patients receiving CAR T-cell therapy. Ann Hematol 100:2303–2310. https://doi.org/10.1007/s00277-021-04560-6
doi: 10.1007/s00277-021-04560-6
pubmed: 34236497
Schmidkonz C, Cordes M, Schmidt D et al (2018) 68Ga-PSMA-11 PET/CT-derived metabolic parameters for determination of whole-body tumor burden and treatment response in prostate cancer. Eur J Nucl Med Mol Imaging 45:1862–1872. https://doi.org/10.1007/s00259-018-4042-z
doi: 10.1007/s00259-018-4042-z
pubmed: 29725716
Capobianco N, Sibille L, Chantadisai M et al (2022) Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning. Eur J Nucl Med Mol Imaging 49:517–526. https://doi.org/10.1007/s00259-021-05473-2
doi: 10.1007/s00259-021-05473-2
pubmed: 34232350