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

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

  • By

  • Man Wang

  • Siyuan Wu

  • Qishan Cen

  • Haiyan Yang

  • Shengsheng Zhou

  • Jinfeng Qiu

  • Shengcai Huang

  • Zhigang Peng

  • June 16, 2026

  • 0 min

Share

Objective:

To create and validate a prognostic prediction model leveraging deep features from PET/CT imaging for personalized treatment in DLBCL patients.

Approach:
    Key Findings:
    • Age, AB group, IPI score, serum β2-microglobulin level, and maximum tumor diameter identified as independent risk factors for 3-year survival.
    • Logistic Regression model achieved an accuracy of 0.865 and AUC of 0.950.
    • Fusion model attained an accuracy of 0.921 and AUC of 0.974 on the test set.
    Interpretation:

    Limitations:
    • Retrospective nature of the study may introduce bias.
    • Generalizability of the model needs further validation in diverse populations.
    Conclusion:

Original Source(s)

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

  • by Man Wang, Siyuan Wu, Qishan Cen, Haiyan Yang, Shengsheng Zhou, Jinfeng Qiu, Shengcai Huang, Zhigang Peng

  • June 16, 2026

Related Content

Primary cutaneous adenoid cystic carcinoma of the right forearm: a case report and dermoscopic features

Exploratory identification of candidate biomarkers and molecular contributors to paclitaxel-induced peripheral neuropathy in patients with breast cancer through proteomic analysis

Narrow Networks and Coverage Changes Among Medicare Advantage Beneficiaries With Cancer