Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.
An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients / Ferrandez M.C.; Golla S.S.V.; Eertink J.J.; de Vries B.M.; Lugtenburg P.J.; Wiegers S.E.; Zwezerijnen G.J.C.; Pieplenbosch S.; Kurch L.; Huttmann A.; Hanoun C.; Duhrsen U.; de Vet H.C.W.; Hoekstra O.S.; Burggraaff C.N.; Bes A.; Heymans M.W.; Jauw Y.W.S.; Chamuleau M.E.D.; Barrington S.F.; Mikhaeel G.; Zucca E.; Ceriani L.; Carr R.; Gyorke T.; Czibor S.; Fanti S.; Kostakoglu L.; Loft A.; Hutchings M.; Lee S.T.; Zijlstra J.M.; Boellaard R.. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - ELETTRONICO. - 13:1(2023), pp. 13111.1-13111.11. [10.1038/s41598-023-40218-1]
An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients
Fanti S.;
2023
Abstract
Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.| File | Dimensione | Formato | |
|---|---|---|---|
|
s41598-023-40218-1.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
2.62 MB
Formato
Adobe PDF
|
2.62 MB | Adobe PDF | Visualizza/Apri |
|
file supplementari.zip
accesso aperto
Tipo:
File Supplementare
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
47.63 MB
Formato
Zip File
|
47.63 MB | Zip File | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
