Deep-Learning (18)F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma

Total metabolic tumor volume (TMTV), calculated from (18)F-FDG PET/CT baseline studies, is a prognostic factor in diffuse large B-cell lymphoma (DLBCL) whose measurement requires the segmentation of all malignant foci throughout the body. No consensus currently exists regarding the most accurate approach for such segmentation. Further, all methods still require extensive manual input from an experienced reader. We examined whether an artificial intelligence–based method could estimate TMTV with a comparable prognostic value to TMTV measured by experts. Methods: Baseline (18)F-FDG PET/CT scans of 301 DLBCL patients from the REMARC trial (NCT01122472) were retrospectively analyzed using a prototype software (PET Assisted Reporting System [PARS]). An automated whole-body high-uptake segmentation algorithm identified all 3-dimensional regions of interest (ROIs) with increased tracer uptake. The resulting ROIs were processed using a convolutional neural network trained on an independent cohort and classified as nonsuspicious or suspicious uptake. The PARS-based TMTV (TMTV(PARS)) was estimated as the sum of the volumes of ROIs classified as suspicious uptake. The reference TMTV (TMTV(REF)) was measured by 2 experienced readers using independent semiautomatic software. The TMTV(PARS) was compared with the TMTV(REF) in terms of prognostic value for progression-free survival (PFS) and overall survival (OS). Results: TMTV(PARS) was significantly correlated with the TMTV(REF) (ρ = 0.76; P < 0.001). Using PARS, an average of 24 regions per subject with increased tracer uptake was identified, and an average of 20 regions per subject was correctly identified as nonsuspicious or suspicious, yielding 85% classification accuracy, 80% sensitivity, and 88% specificity, compared with the TMTV(REF) region. Both TMTV results were predictive of PFS (hazard ratio, 2.3 and 2.6 for TMTV(PARS) and TMTV(REF), respectively; P < 0.001) and OS (hazard ratio, 2.8 and 3.7 for TMTV(PARS) and TMTV(REF), respectively; P < 0.001). Conclusion: TMTV(PARS) was consistent with that obtained by experts and displayed a significant prognostic value for PFS and OS in DLBCL patients. Classification of high-uptake regions using deep learning for rapidly discarding physiologic uptake may considerably simplify TMTV estimation, reduce observer variability, and facilitate the use of TMTV as a predictive factor in DLBCL patients.