When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences or your device and is mainly used to make the site work as you expect it to. The information does not directly identify you but can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies. Click on the different category headings to learn more and change our default settings. However, blocking some types of cookies may impact your experience of the site. You can find more information, including a detailed cookie explanation, on our Cookie Policy.
The challenge
B-cell lymphoma patients who relapse after two lines of treatment are candidates for chimeric antigen receptor T cell (CAR-T) therapy, which has shown notable success with complete remission rates ranging from 40% to 54%.
However, despite these advancements, a significant proportion of patients progress or relapse after CAR-T infusion. Additionally, CAR-T therapy can lead to serious side effects such as immune effector cell-associated neurotoxicity syndrome (ICANS). Traditional clinical predictors alone have been insufficient to accurately predict patient outcomes, highlighting the need for identifying non-invasive biomarkers that may allow better patient risk stratification and management.
The solution
In this multicentric retrospective study, Quibim developed advanced imaging-based prognostic and predictive models using logistic regression and Cox proportional-hazards models to predict CAR-T therapy response at 3 and 6 months, overall survival (OS), progression-free survival (PFS), and the occurrence of ICANS.
Sixty-five relapsed/refractory (R/R) B-cell lymphoma patients treated with CAR-T cells were included. All visible lesions from pre-treatment 18F-FDG PET/CT scans were segmented, and quantitative imaging features were extracted using the QP-Insights® platform. Quantitative imaging features were combined with relevant clinical variables to develop prognostic and predictive models.
The outcome
The combined models significantly improved prediction accuracy compared to clinical or imaging features alone. For instance, the model for predicting ICANS achieved an area under the curve (AUC) of 0.830, and those for CAR-T response at 3 and 6 months showed AUCs of 0.754 and 0.818, respectively. Furthermore, the identified total metabolic tumor volume (MTVtotal) cut-off values effectively stratified patients by OS and PFS, with low MTVtotal associated with longer survival times.
These multi-omic models provide a promising tool for risk stratification and personalized treatment, potentially improving outcomes for CAR-T treated R/R B-cell lymphoma patients and addressing current unmet needs in designing clinical trials for CAR-T therapy in which the prediction of side effects can improve the screening process.
Reference
Blanca Ferrer-Lores, Alfonso Ortiz-Algarra, Alfonso Picó-Peris, Alejandra Estepa-Fernández, Fuensanta Bellvís-Bataller, Glen J. Weiss, Almudena Fuster-Matanzo, Juan Pedro Fernández, Ana Jimenez-Pastor, Rafael Hernani, Ana Saus-Carreres, Ana Benzaquen, Laura Ventura, José Luis Piñana, Ana Belén Teruel, Alicia Serrano-Alcalá, Rosa Dosdá, Pablo Sopena-Novales, Aitana Balaguer-Rosello, Manuel Guerreiro, Jaime Sanz, Luis Martí-Bonmatí, María José Terol, Ángel Alberich-Bayarri. Predicting survival, neurotoxicity and response in B-Cell lymphoma patients treated with CAR-T therapy using an imaging features-based model. Research Square [Preprint link].
Related case studies
-
Prognostic value of genetic alterations and 18F-FDG PET/CT imaging features in diffuse large B cell lymphoma
Read more
-
Development of CT-based radiomic model to predict 5-year progression free survival in locally advanced head and neck squamous cell carcinoma treated with definitive chemoradiation
Read more
-
Empowering DIPG and Neuroblastoma through advanced imaging biomarkers
Read more