Deep learning-based radiomics does not improve residual cancer burden prediction post-chemotherapy in LIMA breast MRI trial - Takeaways - MDSpire

Deep learning-based radiomics does not improve residual cancer burden prediction post-chemotherapy in LIMA breast MRI trial

  • By

  • Markus H. A. Janse

  • Liselore M. Janssen

  • Elian J. M. Wolters-van der Ben

  • Maaike R. Moman

  • Max A. Viergever

  • Paul J. van Diest

  • Kenneth G. A. Gilhuijs

  • August 6, 2025

  • 0 min

Share

  • 1

    Neoadjuvant chemotherapy is increasingly used for locally advanced breast cancer, correlating with improved survival outcomes.

  • 2

    Deep learning-based radiomics was evaluated for predicting residual cancer burden after chemotherapy but did not show improvement over standard clinical predictors.

  • 3

    Dynamic contrast-enhanced MRI is the most sensitive method for visualizing breast lesions, yet lacks specificity for reliably identifying pathological complete response.

  • 4

    The study utilized a retrospective training cohort and a prospective test cohort to assess the predictive value of deep radiomics in breast cancer.

  • 5

    Histopathological evaluation of resection specimens was crucial for determining residual cancer burden and classifying patient responses to neoadjuvant chemotherapy.

Original Source(s)

Deep learning-based radiomics does not improve residual cancer burden prediction post-chemotherapy in LIMA breast MRI trial

  • by Markus H. A. Janse, Liselore M. Janssen, Elian J. M. Wolters-van der Ben, Maaike R. Moman, Max A. Viergever, Paul J. van Diest, Kenneth G. A. Gilhuijs

  • August 6, 2025

Related Content

The Illusion of Enhancement: AI, Economic Factors, and Workforce Replacement in Radiology

Bridging radiology and pathology: domain-generalized cross-modal learning for clinical applications

Evaluation of SPIO-Enhanced MRI in Distinguishing Metastatic Lymph Nodes from Reactive Hyperplasia in Breast Cancer: Diagnostic Efficacy and Correlation with VEGF-C Levels