An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients

Maria C. Ferrández; Sandeep S.V. Golla; PETRA consortium; Jakoba J. Eertink; Bart M. de Vries; Pieternella J. Lugtenburg; Sanne E. Wiegers; Gerben J.C. Zwezerijnen; Simone Pieplenbosch; Lars Kurch; Andreas Hüttmann; Christine Hanoun; Ulrich Dührsen; Henrica C.W. de Vet; Josée M. Zijlstra; Ronald Boellaard

doi:10.1038/s41598-023-40218-1

An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients

Maria C. Ferrández, Sandeep S.V. Golla, PETRA consortium, Jakoba J. Eertink, Bart M. de Vries, Pieternella J. Lugtenburg, Sanne E. Wiegers, Gerben J.C. Zwezerijnen, Simone Pieplenbosch, Lars Kurch, Andreas Hüttmann, Christine Hanoun, Ulrich Dührsen, Henrica C.W. de Vet, Josée M. Zijlstra, Ronald Boellaard

Hematology

Research output: Contribution to journal › Article › Academic › peer-review

7 Citations (Scopus)

17 Downloads (Pure)

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.

Original language	English
Article number	13111
Number of pages	1
Journal	Scientific Reports
Volume	13
Issue number	1
DOIs	https://doi.org/10.1038/s41598-023-40218-1
Publication status	Published - Dec 2023

Bibliographical note

Funding Information:
This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures and were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9).

Funding Information:
This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures 2 and 3 were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9).

Publisher Copyright:
© 2023, Springer Nature Limited.

Access to Document

10.1038/s41598-023-40218-1Licence: CC BY

An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patientsFinal published version, 2.56 MBLicence: CC BY

Cite this

Ferrández, M. C., Golla, S. S. V., PETRA consortium, Eertink, J. J., de Vries, B. M., Lugtenburg, P. J., Wiegers, S. E., Zwezerijnen, G. J. C., Pieplenbosch, S., Kurch, L., Hüttmann, A., Hanoun, C., Dührsen, U., de Vet, H. C. W., Zijlstra, J. M., & Boellaard, R. (2023). An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients. Scientific Reports, 13(1), Article 13111. https://doi.org/10.1038/s41598-023-40218-1

@article{bca8da42c42341b0ac90c62c7eb2cb55,

title = "An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients",

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.",

author = "Ferr{\'a}ndez, {Maria C.} and Golla, {Sandeep S.V.} and {PETRA consortium} and Eertink, {Jakoba J.} and {de Vries}, {Bart M.} and Lugtenburg, {Pieternella J.} and Wiegers, {Sanne E.} and Zwezerijnen, {Gerben J.C.} and Simone Pieplenbosch and Lars Kurch and Andreas H{\"u}ttmann and Christine Hanoun and Ulrich D{\"u}hrsen and {de Vet}, {Henrica C.W.} and Zijlstra, {Jos{\'e}e M.} and Ronald Boellaard",

note = "Funding Information: This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures and were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9). Funding Information: This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures 2 and 3 were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9). Publisher Copyright: {\textcopyright} 2023, Springer Nature Limited.",

year = "2023",

month = dec,

doi = "10.1038/s41598-023-40218-1",

language = "English",

volume = "13",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

Ferrández, MC, Golla, SSV, PETRA consortium, Eertink, JJ, de Vries, BM, Lugtenburg, PJ, Wiegers, SE, Zwezerijnen, GJC, Pieplenbosch, S, Kurch, L, Hüttmann, A, Hanoun, C, Dührsen, U, de Vet, HCW, Zijlstra, JM & Boellaard, R 2023, 'An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients', Scientific Reports, vol. 13, no. 1, 13111. https://doi.org/10.1038/s41598-023-40218-1

TY - JOUR

T1 - An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients

AU - Ferrández, Maria C.

AU - Golla, Sandeep S.V.

AU - PETRA consortium

AU - Eertink, Jakoba J.

AU - de Vries, Bart M.

AU - Lugtenburg, Pieternella J.

AU - Wiegers, Sanne E.

AU - Zwezerijnen, Gerben J.C.

AU - Pieplenbosch, Simone

AU - Kurch, Lars

AU - Hüttmann, Andreas

AU - Hanoun, Christine

AU - Dührsen, Ulrich

AU - de Vet, Henrica C.W.

AU - Zijlstra, Josée M.

AU - Boellaard, Ronald

N1 - Funding Information: This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures and were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9). Funding Information: This work was financially supported by the Hanarth Fonds Fund and the Dutch Cancer Society (#VU-2018-11648). The sponsor had no role in gathering, analyzing or interpreting the data. The authors thank all the patients who participated in the trials and all of the member of the PETRA consortium which names and affiliations are given in the Supplementary Material. Figures 2 and 3 were designed and drawn by M.C.F. The rest of the figures were generated with Python (version 3.9). Publisher Copyright: © 2023, Springer Nature Limited.

PY - 2023/12

Y1 - 2023/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85167764089&partnerID=8YFLogxK

U2 - 10.1038/s41598-023-40218-1

DO - 10.1038/s41598-023-40218-1

M3 - Article

C2 - 37573446

AN - SCOPUS:85167764089

SN - 2045-2322

VL - 13

JO - Scientific Reports

JF - Scientific Reports

IS - 1

M1 - 13111

ER -

An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this