1
|
Prognostic value of 18F-FDG PET/CT in T-Lymphoblastic lymphoma before and after hematopoietic stem cell transplantation. Clin Transl Oncol 2021; 23:1571-1576. [PMID: 33449269 DOI: 10.1007/s12094-021-02551-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2020] [Accepted: 01/01/2021] [Indexed: 12/11/2022]
Abstract
PURPOSE We aimed to evaluate the prognostic value of 18F-FDG PET/CT in patients with relapsed or refractory T-Lymphoblastic lymphoma (T-LBL) undergoing hematopoietic stem cell transplantation (HSCT). METHODS PET/CT was performed in 21 consecutive relapsed or refractory T-LBL patients scheduled for HSCT. All PET/CT images were assessed using the Deauville criteria, and patients were divided into negative (Deauville ≤ 3) and positive (Deauville > 3) groups for comparison. The predictive value of sex, age, Ann Arbor stage, presence of B symptoms, lactate dehydrogenase level, presence of extranodal disease, and PET/CT results before and after HSCT were evaluated. RESULTS Kaplan-Meier analysis showed that only PET/CT after HSCT (post-PET) was correlated with progression-free survival (PFS) (P = 0.030). The Cox regression model also showed that the post-PET-positive group had a higher hazard ratio (HR) than the negative group (HR = 3.884 and P = 0.049). However, none of the evaluated factors were predictive of overall survival (OS). CONCLUSIONS Pre-PET cannot predict the PFS and OS of patients with T-LBL undergoing HSCT, which means that 18F-FDG PET/CT cannot be used for identifying patients who can benefit from HSCT. Post-PET is not predictive for OS in patients with T-LBL undergoing HSCT. However, post-PET showed strong correlations with PFS, which means that it may be useful for guiding subsequent clinical treatment decisions.
Collapse
|
2
|
Sollini M, Kirienko M, Cavinato L, Ricci F, Biroli M, Ieva F, Calderoni L, Tabacchi E, Nanni C, Zinzani PL, Fanti S, Guidetti A, Alessi A, Corradini P, Seregni E, Carlo-Stella C, Chiti A. Methodological framework for radiomics applications in Hodgkin's lymphoma. Eur J Hybrid Imaging 2020; 4:9. [PMID: 34191173 PMCID: PMC8218114 DOI: 10.1186/s41824-020-00078-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2020] [Accepted: 05/06/2020] [Indexed: 12/22/2022] Open
Abstract
BACKGROUND According to published data, radiomics features differ between lesions of refractory/relapsing HL patients from those of long-term responders. However, several methodological aspects have not been elucidated yet. PURPOSE The study aimed at setting up a methodological framework in radiomics applications in Hodgkin's lymphoma (HL), especially at (a) developing a novel feature selection approach, (b) evaluating radiomic intra-patient lesions' similarity, and (c) classifying relapsing refractory (R/R) vs non-(R/R) patients. METHODS We retrospectively included 85 patients (male:female = 52:33; median age 35 years, range 19-74). LIFEx (www.lifexsoft.org) was used for [18F]FDG-PET/CT segmentation and feature extraction. Features were a-priori selected if they were highly correlated or uncorrelated to the volume. Principal component analysis-transformed features were used to build the fingerprints that were tested to assess lesions' similarity, using the silhouette. For intra-patient similarity analysis, we used patients having multiple lesions only. To classify patients as non-R/R and R/R, the fingerprint considering one single lesion (fingerprint_One) and all lesions (fingerprint_All) was tested using Random Undersampling Boosting of Tree Ensemble (RUBTE). RESULTS HL fingerprints included up to 15 features. Intra-patient lesion similarity analysis resulted in mean/median silhouette values below 0.5 (low similarity especially in the non-R/R group). In the test set, the fingerprint_One classification accuracy was 62% (78% sensitivity and 53% specificity); the classification by RUBTE using fingerprint_All resulted in 82% accuracy (70% sensitivity and 88% specificity). CONCLUSIONS Lesion similarity analysis was developed, and it allowed to demonstrate that HL lesions were not homogeneous within patients in terms of radiomics signature. Therefore, a random target lesion selection should not be adopted for radiomics applications. Moreover, the classifier to predict R/R vs non-R/R performed the best when all the lesions were used.
Collapse
Affiliation(s)
- Martina Sollini
- Humanitas University, Via Rita Levi Montalcini 4, MI 20090 Pieve Emanuele, Italy
- Humanitas Clinical and Research Center – IRCCS -, via Manzoni 56, 20089 Rozzano, MI Italy
| | - Margarita Kirienko
- Humanitas University, Via Rita Levi Montalcini 4, MI 20090 Pieve Emanuele, Italy
| | - Lara Cavinato
- Humanitas Clinical and Research Center – IRCCS -, via Manzoni 56, 20089 Rozzano, MI Italy
- MOX–Modelling and Scientific Computing lab., Department of Mathematics, Politecnico di Milano, Milano, Italy
| | - Francesca Ricci
- Humanitas Clinical and Research Center – IRCCS -, via Manzoni 56, 20089 Rozzano, MI Italy
| | - Matteo Biroli
- Humanitas University, Via Rita Levi Montalcini 4, MI 20090 Pieve Emanuele, Italy
| | - Francesca Ieva
- MOX–Modelling and Scientific Computing lab., Department of Mathematics, Politecnico di Milano, Milano, Italy
- CADS–Center for Analysis, Decision, and Society, Human Technopole, Milano, Italy
| | | | | | | | - Pier Luigi Zinzani
- Institute of Hematology “Seràgnoli”, University of Bologna, Bologna, Italy
| | - Stefano Fanti
- Nuclear Medicine, AOU S.Orsola-Malpighi, Bologna, Italy
| | - Anna Guidetti
- Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- University of Milan, Milan, Italy
| | | | - Paolo Corradini
- Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
- University of Milan, Milan, Italy
| | - Ettore Seregni
- Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
| | - Carmelo Carlo-Stella
- Humanitas University, Via Rita Levi Montalcini 4, MI 20090 Pieve Emanuele, Italy
- Humanitas Clinical and Research Center – IRCCS -, via Manzoni 56, 20089 Rozzano, MI Italy
| | - Arturo Chiti
- Humanitas University, Via Rita Levi Montalcini 4, MI 20090 Pieve Emanuele, Italy
- Humanitas Clinical and Research Center – IRCCS -, via Manzoni 56, 20089 Rozzano, MI Italy
| |
Collapse
|