Metabolic heterogeneity-based radiomic model predicts treatment outcomes of primary mediastinal B-cell lymphoma patients in the IELSG37 study
Metabolic heterogeneity-based radiomic model predicts treatment outcomes of primary mediastinal B-cell lymphoma patients in the IELSG37 study
Early identification of patients at risk of failing first-line therapy remains a key challenge in primary mediastinal B-cell lymphoma (PMBCL). This study assessed whether positron emission tomography (PET) radiomics could predict treatment outcomes in PMBCL. Baseline PET/computed tomography (CT) scans from 501 patients enrolled in the International Extranodal Lymphoma Study Group 37 (IELSG37) trial and treated with rituximab- and doxorubicin-based immunochemotherapy were analysed. Functional PET parameters reflecting tumour burden (metabolic tumour volume, MTV), glucose consumption (total lesion glycolysis, TLG) and metabolic heterogeneity (MH) were calculated using a 25% maximum standard uptake value (SUVmax) segmentation threshold. Radiomic analysis was performed in 495 patients, extracting 107 features; 74 features uncorrelated with SUVmax and MTV were selected and analysed using a recursive-partitioning classification tree (Ctree) approach. Ctree identified grey-level run-length matrix run variance (GLRLM-RV), a marker of MH, as the most significant prognostic feature. Patients with low MH (GLRLM-RV <0.136) had a 5-year progression-free survival (PFS) of 93%, compared with 65% in those with high MH (p < 0.0001). Five-year overall survival (OS) was 96% vs. 80% respectively (p < 0.0001). A subsequent Ctree model integrating GLRLM-RV and TLG further improved prognostic stratification for PFS and OS (p < 0.0001), outperforming established prognostic indices (International Prognostic Index [IPI], revised-IPI and age-adjusted IPI).
393-856
Ceriani, Luca
5767bf0b-1df0-4479-90df-a3e0beb1c8b8
Milan, Lisa
d659fb5e-8d6c-41be-b1cc-b7114772f052
Cascione, Luciano
bda3280b-5e39-4604-9456-f684082bd3c0
Di Rocco, Alessandro
1fe48111-b6bf-4186-a450-4c07e55d9fcc
Kryachouk, Iryna
7edfb59a-b48e-48a2-86cd-89cd7e82f9f4
Davies, Andy J.
0fe6a40a-10d1-4ade-a7e6-d1dceb2470af
Stathis, Anastasios
1c6ad6b5-a68c-4203-b576-8b846744b228
Rossi, Davide
b4b2506d-794c-4c79-8b2d-6767554fd52a
Johnson, P.W.M.
26932758-e8d4-4676-9e55-ed36d00665ea
Martelli, Maurizio
32f72970-6db0-45ec-9246-6d074b504192
Zucca, Emanuele
40bd5950-d74e-4169-a2ea-0bfc1058058e
August 2026
Ceriani, Luca
5767bf0b-1df0-4479-90df-a3e0beb1c8b8
Milan, Lisa
d659fb5e-8d6c-41be-b1cc-b7114772f052
Cascione, Luciano
bda3280b-5e39-4604-9456-f684082bd3c0
Di Rocco, Alessandro
1fe48111-b6bf-4186-a450-4c07e55d9fcc
Kryachouk, Iryna
7edfb59a-b48e-48a2-86cd-89cd7e82f9f4
Davies, Andy J.
0fe6a40a-10d1-4ade-a7e6-d1dceb2470af
Stathis, Anastasios
1c6ad6b5-a68c-4203-b576-8b846744b228
Rossi, Davide
b4b2506d-794c-4c79-8b2d-6767554fd52a
Johnson, P.W.M.
26932758-e8d4-4676-9e55-ed36d00665ea
Martelli, Maurizio
32f72970-6db0-45ec-9246-6d074b504192
Zucca, Emanuele
40bd5950-d74e-4169-a2ea-0bfc1058058e
Ceriani, Luca, Milan, Lisa, Cascione, Luciano, Di Rocco, Alessandro, Kryachouk, Iryna, Davies, Andy J., Stathis, Anastasios, Rossi, Davide, Johnson, P.W.M., Martelli, Maurizio and Zucca, Emanuele
(2026)
Metabolic heterogeneity-based radiomic model predicts treatment outcomes of primary mediastinal B-cell lymphoma patients in the IELSG37 study.
British Journal of Haematology, 209 (2), .
(doi:10.1111/bjh.70614).
Abstract
Early identification of patients at risk of failing first-line therapy remains a key challenge in primary mediastinal B-cell lymphoma (PMBCL). This study assessed whether positron emission tomography (PET) radiomics could predict treatment outcomes in PMBCL. Baseline PET/computed tomography (CT) scans from 501 patients enrolled in the International Extranodal Lymphoma Study Group 37 (IELSG37) trial and treated with rituximab- and doxorubicin-based immunochemotherapy were analysed. Functional PET parameters reflecting tumour burden (metabolic tumour volume, MTV), glucose consumption (total lesion glycolysis, TLG) and metabolic heterogeneity (MH) were calculated using a 25% maximum standard uptake value (SUVmax) segmentation threshold. Radiomic analysis was performed in 495 patients, extracting 107 features; 74 features uncorrelated with SUVmax and MTV were selected and analysed using a recursive-partitioning classification tree (Ctree) approach. Ctree identified grey-level run-length matrix run variance (GLRLM-RV), a marker of MH, as the most significant prognostic feature. Patients with low MH (GLRLM-RV <0.136) had a 5-year progression-free survival (PFS) of 93%, compared with 65% in those with high MH (p < 0.0001). Five-year overall survival (OS) was 96% vs. 80% respectively (p < 0.0001). A subsequent Ctree model integrating GLRLM-RV and TLG further improved prognostic stratification for PFS and OS (p < 0.0001), outperforming established prognostic indices (International Prognostic Index [IPI], revised-IPI and age-adjusted IPI).
Text
Metabolic heterogeneity_accepted_May 2026
- Accepted Manuscript
Restricted to Repository staff only until 16 June 2027.
Request a copy
More information
Accepted/In Press date: 29 May 2026
e-pub ahead of print date: 16 June 2026
Published date: August 2026
Identifiers
Local EPrints ID: 514878
URI: https://eprints.soton.ac.uk/id/eprint/514878
ISSN: 0007-1048
PURE UUID: 170810ef-bf1e-4a9e-83e1-f1371db05c81
Catalogue record
Date deposited: 01 Oct 2026 17:04
Last modified: 02 Oct 2026 01:47
Export record
Altmetrics
Contributors
Author:
Luca Ceriani
Author:
Lisa Milan
Author:
Luciano Cascione
Author:
Alessandro Di Rocco
Author:
Iryna Kryachouk
Author:
Anastasios Stathis
Author:
Davide Rossi
Author:
P.W.M. Johnson
Author:
Maurizio Martelli
Author:
Emanuele Zucca
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics