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

Nicolò Capobianco,Michel Meignan,Catherine Thieblemont,Ludovic Sibille,Olivier Casasnovas,Sven Zuehlsdorff,Laetitia Vercellino,Irène Buvat,Bruce Spottiswoode,Anne-Ségolène Cottereau

doi:10.2967/jnumed.120.242412

Abstract

Total metabolic tumor volume (TMTV), calculated from 18F-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 18F-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 (TMTVPARS) was estimated as the sum of the volumes of ROIs classified as suspicious uptake. The reference TMTV (TMTVREF) was measured by 2 experienced readers using independent semiautomatic software. The TMTVPARS was compared with the TMTVREF in terms of prognostic value for progression-free survival (PFS) and overall survival (OS). Results: TMTVPARS was significantly correlated with the TMTVREF (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 TMTVREF region. Both TMTV results were predictive of PFS (hazard ratio, 2.3 and 2.6 for TMTVPARS and TMTVREF, respectively; P < 0.001) and OS (hazard ratio, 2.8 and 3.7 for TMTVPARS and TMTVREF, respectively; P < 0.001). Conclusion: TMTVPARS 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.

Highlights

Using deep learning for rapidly discarding physiologic uptake may considerably simplify Total metabolic tumor volume (TMTV) estimation, reduce observer variability, and facilitate the use of TMTV as a predictive factor in diffuse large B-cell lymphoma (DLBCL) patients
After a median follow-up of 5 y, 86 patients presented with a progression-free survival (PFS) event and 51 patients had an overall survival (OS) event; the 4-y survival rates were 69% for PFS and 83% for OS
PET/CT images were acquired using different scanner models from different vendors as summarized in Supplemental Table 1

Summary

Introduction

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. FDG PET/CT baseline studies is a promising prognostic factor in diffuse large B-cell lymphoma (DLBCL) [1,2] and other types of lymphoma [3,4,5]. Baseline TMTV, which estimates the total metabolic tumor burden at diagnosis, has been proposed as an alternative prognostic tool for early risk stratification. Recent studies have suggested that, despite these differences, most methods yielded similar accuracy in predicting patient prognosis when applied in similar patient groups [11,12], emphasizing the strong prognostic power of baseline TMTV. Regardless of the criteria used for delineating tumor regions, all methods for deriving TMTV require extensive and time-consuming manual input from an experienced reader.

Methods

Results

Conclusion