An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients
© 2023. Springer Nature Limited..
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.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:13 |
---|---|
Enthalten in: |
Scientific reports - 13(2023), 1 vom: 12. Aug., Seite 13111 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Ferrández, Maria C [VerfasserIn] |
---|
Links: |
---|
Themen: |
0Z5B2CJX4D |
---|
Anmerkungen: |
Date Completed 14.08.2023 Date Revised 19.11.2023 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1038/s41598-023-40218-1 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM36072938X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM36072938X | ||
003 | DE-627 | ||
005 | 20231226210748.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41598-023-40218-1 |2 doi | |
028 | 5 | 2 | |a pubmed24n1202.xml |
035 | |a (DE-627)NLM36072938X | ||
035 | |a (NLM)37573446 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Ferrández, Maria C |e verfasserin |4 aut | |
245 | 1 | 3 | |a An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 14.08.2023 | ||
500 | |a Date Revised 19.11.2023 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023. Springer Nature Limited. | ||
520 | |a 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 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 7 | |a Fluorodeoxyglucose F18 |2 NLM | |
650 | 7 | |a 0Z5B2CJX4D |2 NLM | |
700 | 1 | |a Golla, Sandeep S V |e verfasserin |4 aut | |
700 | 1 | |a Eertink, Jakoba J |e verfasserin |4 aut | |
700 | 1 | |a de Vries, Bart M |e verfasserin |4 aut | |
700 | 1 | |a Lugtenburg, Pieternella J |e verfasserin |4 aut | |
700 | 1 | |a Wiegers, Sanne E |e verfasserin |4 aut | |
700 | 1 | |a Zwezerijnen, Gerben J C |e verfasserin |4 aut | |
700 | 1 | |a Pieplenbosch, Simone |e verfasserin |4 aut | |
700 | 1 | |a Kurch, Lars |e verfasserin |4 aut | |
700 | 1 | |a Hüttmann, Andreas |e verfasserin |4 aut | |
700 | 1 | |a Hanoun, Christine |e verfasserin |4 aut | |
700 | 1 | |a Dührsen, Ulrich |e verfasserin |4 aut | |
700 | 1 | |a de Vet, Henrica C W |e verfasserin |4 aut | |
700 | 0 | |a PETRA |e verfasserin |4 aut | |
700 | 1 | |a Zijlstra, Josée M |e verfasserin |4 aut | |
700 | 1 | |a Boellaard, Ronald |e verfasserin |4 aut | |
700 | 1 | |a Hoekstra, Otto S |e investigator |4 oth | |
700 | 1 | |a Burggraaff, Coreline N |e investigator |4 oth | |
700 | 1 | |a Bes, Annelies |e investigator |4 oth | |
700 | 1 | |a Heymans, Martijn W |e investigator |4 oth | |
700 | 1 | |a Jauw, Yvonne W S |e investigator |4 oth | |
700 | 1 | |a Chamuleau, Martine E D |e investigator |4 oth | |
700 | 1 | |a Barrington, Sally F |e investigator |4 oth | |
700 | 1 | |a Mikhaeel, George |e investigator |4 oth | |
700 | 1 | |a Zucca, Emanuele |e investigator |4 oth | |
700 | 1 | |a Ceriani, Luca |e investigator |4 oth | |
700 | 1 | |a Carr, Robert |e investigator |4 oth | |
700 | 1 | |a Györke, Tamás |e investigator |4 oth | |
700 | 1 | |a Czibor, Sándor |e investigator |4 oth | |
700 | 1 | |a Fanti, Stefano |e investigator |4 oth | |
700 | 1 | |a Kostakoglu, Lale |e investigator |4 oth | |
700 | 1 | |a Loft, Annika |e investigator |4 oth | |
700 | 1 | |a Hutchings, Martin |e investigator |4 oth | |
700 | 1 | |a Lee, Sze Ting |e investigator |4 oth | |
773 | 0 | 8 | |i Enthalten in |t Scientific reports |d 2011 |g 13(2023), 1 vom: 12. Aug., Seite 13111 |w (DE-627)NLM215703936 |x 2045-2322 |7 nnns |
773 | 1 | 8 | |g volume:13 |g year:2023 |g number:1 |g day:12 |g month:08 |g pages:13111 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41598-023-40218-1 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 13 |j 2023 |e 1 |b 12 |c 08 |h 13111 |