PET-adapted approaches to primary therapy for advanced Hodgkin lymphoma

Lang, Noémie; Crump, Michael

doi:10.1177/2040620720914490

Cited by 12 publications

(8 citation statements)

References 72 publications

(129 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This must be a key target when creating any machine learning or AI-based model. In terms of HL, it would be the ability to balance side effects of escalated treatment, with the rates of EFS and toxicity varying between treatment regimens [ 31 ]. The advent of newer therapeutic strategies limits the use of predictive models made on retrospective data; future efforts should focus on validating imaging, genetic and clinical predictive features in carefully designed prospective, multi-centre clinical trials.…”

Section: Discussionmentioning

confidence: 99%

Utility of pre-treatment FDG PET/CT–derived machine learning models for outcome prediction in classical Hodgkin lymphoma

et al. 2022

View full text Add to dashboard Cite

Objectives Relapse occurs in ~20% of patients with classical Hodgkin lymphoma (cHL) despite treatment adaption based on 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography response. The objective was to evaluate pre-treatment FDG PET/CT–derived machine learning (ML) models for predicting outcome in patients with cHL. Methods All cHL patients undergoing pre-treatment PET/CT at our institution between 2008 and 2018 were retrospectively identified. A 1.5 × mean liver standardised uptake value (SUV) and a fixed 4.0 SUV threshold were used to segment PET/CT data. Feature extraction was performed using PyRadiomics with ComBat harmonisation. Training (80%) and test (20%) cohorts stratified around 2-year event-free survival (EFS), age, sex, ethnicity and disease stage were defined. Seven ML models were trained and hyperparameters tuned using stratified 5-fold cross-validation. Area under the curve (AUC) from receiver operator characteristic analysis was used to assess performance. Results A total of 289 patients (153 males), median age 36 (range 16–88 years), were included. There was no significant difference between training (n = 231) and test cohorts (n = 58) (p value > 0.05). A ridge regression model using a 1.5 × mean liver SUV segmentation had the highest performance, with mean training, validation and test AUCs of 0.82 ± 0.002, 0.79 ± 0.01 and 0.81 ± 0.12. However, there was no significant difference between a logistic model derived from metabolic tumour volume and clinical features or the highest performing radiomic model. Conclusions Outcome prediction using pre-treatment FDG PET/CT–derived ML models is feasible in cHL patients. Further work is needed to determine optimum predictive thresholds for clinical use. Key points • A fixed threshold segmentation method led to more robust radiomic features. • A radiomic-based model for predicting 2-year event-free survival in classical Hodgkin lymphoma patients is feasible. • A predictive model based on ridge regression was the best performing model on our dataset.

show abstract

Section: Discussionmentioning

confidence: 99%

Utility of pre-treatment FDG PET/CT–derived machine learning models for outcome prediction in classical Hodgkin lymphoma

et al. 2022

View full text Add to dashboard Cite

show abstract

“…If PET has Deauville score of 1–3, then bleomycin, which is more highly toxic, is dropped for the next 4 cycles with no significant difference in PFS at 3 years. About 20% will be persistently PET-positive and typically those patients would be switched to escBEACOPP [ 58 ]. However, this strategy of interim PET is being used less frequently now due to approval of brentuximab vedotin, a CD30-directed antibody-drug conjugate (A + AVD), in advanced HL, based on the ECHELON 1 trial.…”

Section: Hematologic Malignanciesmentioning

confidence: 99%

PET-CT in Clinical Adult Oncology: I. Hematologic Malignancies

Salem

Shah

Covington

et al. 2022

Cancers

View full text Add to dashboard Cite

PET-CT is an advanced imaging modality with many oncologic applications, including staging, assessment of response to therapy, restaging and evaluation of suspected recurrence. The goal of this 6-part series of review articles is to provide practical information to providers and imaging professionals regarding the best use of PET-CT for the more common adult malignancies. In the first article of this series, hematologic malignancies are addressed. The classification of these malignancies will be outlined, with the disclaimer that the classification of lymphomas is constantly evolving. Critical applications, potential pitfalls, and nuances of PET-CT imaging in hematologic malignancies and imaging features of the major categories of these tumors are addressed. Issues of clinical importance that must be reported by the imaging professionals are outlined. The focus of this article is on [18F] fluorodeoxyglucose (FDG), rather that research tracers or those requiring a local cyclotron. This information will serve as a resource for the appropriate role and limitations of PET-CT in the clinical management of patients with hematological malignancy for health care professionals caring for adult patients with hematologic malignancies. It also serves as a practical guide for imaging providers, including radiologists, nuclear medicine physicians and their trainees.

show abstract

“…In advanced stage disease, PET-adapted strategies should be favored whenever feasible [49][50][51]. Bleomycin omission should be strongly encouraged after two cycles of ABVD (doxorubicin, bleomycin, vinblastine and dacarbazine) for patients achieving a complete metabolic response at interim PET assessment [52] or from the start for frail patients. The BV-AVD (brentuximab-vedotin, doxorubicin, bleomycin, vinblastine and dacarbazine) regimen has shown a benefit in disease control (though not OS) compared to ABVD, but is associated with higher rates of neutropenia and febrile neutropenia, which lead to important risks during the preferable CoViD-19 pandemic [53].…”

Section: Hodgkin Lymphomamentioning

confidence: 99%

Evolving management strategies for lymphomas during the COVID-19 pandemic

Lang

Kuruvilla

2020

Leukemia & Lymphoma

Self Cite

View full text Add to dashboard Cite

The evolving CoViD-19 pandemic has raised unprecedented challenges for physicians who face significant constraints in medical resources and cancer therapies. The management of patients with lymphoma represents a unique challenge given the heterogeneity of the patient population and treatment goals as well as the myriad choices of therapy available to clinicians. Adaptation in clinical practice with the goal of maintaining appropriate continuity and quality of care while mitigating exposure risk has forced clinicians around the world to develop new standards of practice and can pose difficult ethical choices in vulnerable patient populations. Based on recommendations formulated by several medical groups and societies, this article provides an overview of the general and specific practical considerations that apply to the care of lymphoma patients during the outbreak. We hope to provide a practical framework to help guide physicians in their therapeutic choices and facilitate the ongoing management of this specific patient population.

show abstract

PET-adapted approaches to primary therapy for advanced Hodgkin lymphoma

Cited by 12 publications

References 72 publications

Utility of pre-treatment FDG PET/CT–derived machine learning models for outcome prediction in classical Hodgkin lymphoma

Utility of pre-treatment FDG PET/CT–derived machine learning models for outcome prediction in classical Hodgkin lymphoma

PET-CT in Clinical Adult Oncology: I. Hematologic Malignancies

Evolving management strategies for lymphomas during the COVID-19 pandemic

Contact Info

Product

Resources

About