Baseline 18F-FDG PET/CT habitat radiomics versus dual-channel deep learning for predicting interim PET early metabolic response in diffuse large B-cell lymphoma: a comparative study - Takeaways - MDSpire

Baseline 18F-FDG PET/CT habitat radiomics versus dual-channel deep learning for predicting interim PET early metabolic response in diffuse large B-cell lymphoma: a comparative study

  • By

  • Yu He

  • Shun Wang

  • Yingchun Li

  • Xinyang Li

  • Jingkai Yi

  • Dan Wang

  • Kailin Qi

  • Yongjiang Li

  • Xiao Jiang

  • Yutang Yao

  • Ping Wu

  • Meng Zhao

  • Hao Lu

  • Taipeng Shen

  • Zhuzhong Cheng

  • Ying Kou

  • June 4, 2026

  • 0 min

Share

  • 1

    The study developed habitat radiomics and dual-channel deep learning models to predict early metabolic response in DLBCL patients using baseline 18F-FDG PET/CT.

  • 2

    A total of 148 patients were analyzed, with 101 classified as early metabolic responders and 47 as non-responders based on interim PET Deauville scores.

  • 3

    The habitat radiomics model (Habitat_MLP) outperformed the dual-channel deep learning model (DL_DenseNet161) with an AUC of 0.871 compared to 0.793.

  • 4

    Habitat_MLP demonstrated higher specificity (0.903) and accuracy (0.822) than DL_DenseNet161, indicating its robustness in predicting treatment response.

  • 5

    The findings suggest that habitat radiomics could serve as a valuable decision-support tool for pretreatment risk stratification in DLBCL.

Original Source(s)

Baseline 18F-FDG PET/CT habitat radiomics versus dual-channel deep learning for predicting interim PET early metabolic response in diffuse large B-cell lymphoma: a comparative study

  • by Yu He, Shun Wang, Yingchun Li, Xinyang Li, Jingkai Yi, Dan Wang, Kailin Qi, Yongjiang Li, Xiao Jiang, Yutang Yao, Ping Wu, Meng Zhao, Hao Lu, Taipeng Shen, Zhuzhong Cheng, Ying Kou

  • June 4, 2026

Related Content

CDK4/6-targeted therapy for gastrointestinal cancers: from resistance mechanisms to immuno-combination strategies guided by biomarkers

Direct comparison of efficacy of combining ivermectin versus five first-line chemotherapy drugs with recombinant methioninase against colon-cancer cells

Incidence and Survival of Gastro-Entero-Pancreatic Neuroendocrine Neoplasms in the Contemporary Era