Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 2, 2026

Enhancing Tumor Content through Tumor Macrodissection

Enhancing Tumor Content through Tumor Macrodissection

Published on: February 12, 2022

A deep learning-based prognostic model for diffuse large B-cell lymphoma incorporating PET/CT imaging features.

Man Wang^1,2, Siyuan Wu³, Qishan Cen³

¹Department of Oncology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.

Frontiers in Oncology

|July 1, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Loss of mammalian glutaminase orthologs impairs sperm function in <i>Caenorhabditis elegans</i>.

iScience·2023

Same author

Involvement of RNA chaperone hfq in the regulation of antibiotic resistance and virulence in Shigella sonnei.

Research in microbiology·2023

Same author

Copy number variations mediate major pathological response to induction chemo-immunotherapy in unresectable stage IIIA-IIIB lung cancer.

Lung cancer (Amsterdam, Netherlands)·2023

Same author

Recent advances in exploiting carrageenans as a versatile functional material for promising biomedical applications.

International journal of biological macromolecules·2023

Same author

Arising Concerns of Atypical Manifestations in Patients with Hand, Foot, and Mouth Disease.

Vaccines·2023

Same author

Long-term outcomes of relmacabtagene autoleucel in Chinese patients with relapsed/refractory large B-cell lymphoma: Updated results of the RELIANCE study.

Cytotherapy·2023

Same journal

Explainable incremental-value analysis of apparent diffusion coefficient and arterial spin labeling radiomics for ATRX status prediction in glioblastoma.

Frontiers in oncology·2026

Same journal

Study-level factors associated with hematoma after ultrasound-guided vacuum-assisted breast lesion excision: a systematic review and meta-analysis using a T-P-B framework.

Frontiers in oncology·2026

Same journal

Feasibility and strategy analysis of radiotherapy consolidation following immunotherapy for stage IV esophageal squamous cell carcinoma.

Frontiers in oncology·2026

Same journal

Anastomosing hemangioma of the kidney: a case report.

Frontiers in oncology·2026

Same journal

Machine learning-based prediction of prolonged air leak after uniportal video-assisted thoracic surgery segmentectomy.

Frontiers in oncology·2026

Same journal

Past present and future of radiosensitization in cervical cancer.

Frontiers in oncology·2026

See all related articles

This summary is machine-generated.

A new prognostic model using PET/CT deep features and clinical data accurately predicts 3-year survival in diffuse large B-cell lymphoma (DLBCL) patients. This fusion model offers a valuable tool for personalized precision treatment strategies.

Area of Science:

Oncology
Radiology
Medical Imaging

Background:

Diffuse large B-cell lymphoma (DLBCL) is an aggressive non-Hodgkin lymphoma requiring effective prognostic tools.
Current prognostic models may not fully capture the complexity of DLBCL for personalized treatment.

Purpose of the Study:

To develop and validate a prognostic prediction model for DLBCL using deep features from PET/CT imaging.
To integrate radiomics features with clinical data for enhanced survival prediction.

Main Methods:

Retrospective analysis of PET/CT and clinical data from 209 DLBCL patients.
Extraction of deep radiomics features, dimensionality reduction, and machine learning model development (LR, SVM, KNN, RF, XGBoost, LightGBM).
Fusion of the optimal radiomics model with clinical features; performance evaluation using accuracy, AUC, sensitivity, specificity, DCA, and KM survival analysis.

Keywords:

deep features diffuse large B-cell lymphoma fusion model machine learning prognostic prediction

More Related Videos

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Related Experiment Videos

Last Updated: Jul 2, 2026

Enhancing Tumor Content through Tumor Macrodissection

Enhancing Tumor Content through Tumor Macrodissection

Published on: February 12, 2022

Predictive Immune Modeling of Solid Tumors

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Main Results:

Age, IPI score, and tumor diameter were independent risk factors for survival.
The Logistic Regression radiomics model achieved high predictive performance (AUC 0.950).
The fusion model demonstrated superior performance on the test set (AUC 0.974), showing significant clinical utility for prognostic risk prediction.

Conclusions:

A fusion model combining PET/CT deep features and clinical data provides a reliable prognostic tool for DLBCL.
This model shows substantial promise for clinical application and guiding personalized treatment decisions in DLBCL patients.