Pulse.

a daily field guide to health research that matters

◆ Console

‹ Mon · 27 Jul 2026
Near-term implementable finding

The deep learning radiomics nomogram for risk stratification in multiple myeloma using automatic whole-body [18F]FDG PET/CT segmentation approach.

Advanced imaging analysis predicts multiple myeloma outcomes without repeated bone marrow biopsies, reducing invasive procedures.

This study develops and validates a deep learning radiomics nomogram integrating automated whole-body FDG PET/CT segmentation features with clinical variables for multiple myeloma risk stratification. The approach demonstrates that automated imaging analysis can predict outcomes non-invasively, potentially reducing the need for serial bone marrow biopsies in myeloma management.

What the study was

Study design
Retrospective cohort with multicenter validation
Population
Multiple myeloma patients undergoing whole-body FDG PET/CT
Category
Diagnostics
Maturity
Validated
Journal
European journal of nuclear medicine and molecular imaging

Why it surfaced

Cross-topic: AI/imaging (T4) + hematologic malignancy (T1). Automated DL segmentation + radiomics for whole-body PET/CT is a major technical advance. Validated approach in multiple myeloma, a cancer type with high unmet need for better non-invasive staging.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.