Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography.

Introduction: Our aim was to evaluate the performance in clinical research and in clinical routine of a research prototype, called positron emission tomography (PET) Assisted Reporting System (PARS) (Siemens Healthineers) and based on a convolutional neural network (CNN), which is designed to detect suspected cancer sites in fluorine-18 fluorodeoxyglucose (18F-FDG) PET/computed tomography (CT). Method: We retrospectively studied two cohorts of patients. The first cohort consisted of research-based patients who underwent PET scans as part of the initial workup for diffuse large B-cell lymphoma (DLBCL). The second cohort consisted of patients who underwent PET scans as part of the evaluation of miscellaneous cancers in clinical routine. In both cohorts, we assessed the correlation between manually and automatically segmented total metabolic tumor volumes (TMTVs), and the overlap between both segmentations (Dice score). For the research cohort, we also compared the prognostic value for progression-free survival (PFS) and overall survival (OS) of manually and automatically obtained TMTVs. Results: For the first cohort (research cohort), data from 119 patients were retrospectively analyzed. The median Dice score between automatic and manual segmentations was 0.65. The intraclass correlation coefficient between automatically and manually obtained TMTVs was 0.68. Both TMTV results were predictive of PFS (hazard ratio: 2.1 and 3.3 for automatically based and manually based TMTVs, respectively) and OS (hazard ratio: 2.4 and 3.1 for automatically based and manually based TMTVs, respectively). For the second cohort (routine cohort), data from 430 patients were retrospectively analyzed. The median Dice score between automatic and manual segmentations was 0.48. The intraclass correlation coefficient between automatically and manually obtained TMTVs was 0.61. Conclusion: The TMTVs determined for the research cohort remain predictive of total and PFS for DLBCL. However, the segmentations and TMTVs determined automatically by the algorithm need to be verified and, sometimes, corrected to be similar to the manual segmentation.

Reproducibility of Baseline Tumour Metabolic Volume Measurements in Diffuse Large B-Cell LymphomA: Is There a Superior Method?

The metabolic tumour volume (MTV) is an independent prognostic indicator in diffuse large B-cell lymphoma (DLBCL). However, its measurement is not standardised and is subject to wide variations depending on the method used. This study aimed to compare the reproducibility of MTV measurement as well as the thresholds obtained for each method and their prognostic values. The baseline MTV was measured in 239 consecutive patients treated at Henri Becquerel Centre by two blinded evaluators. Eight methods were compared: 3 absolute (SUV (standardised uptake value) ≥ 2.5; SUV≥ liver SUVmax; SUV≥ PERCIST SUV), 1 percentage SUV threshold method (SUV ≥ 41% SUVmax) and 4 adaptive methods (Daisne, Nestle, Fitting, Black). The intraclass correlation coefficients were excellent, from 0.91 to 0.96, for the absolute SUV methods, Black and Nestle methods, and good for 41% SUVmax, Fitting and Daisne methods (0.82 to 0.88), with a significantly lower variability with absolute methods compared to 41% SUVmax (p < 0.04). Thresholds were found to be specific to each segmentation method and ranged from 295 to 552 cm3. There was a strong correlation between the MTV and patient prognosis regardless of the segmentation method used (p = 0.001 for PFS and OS). The largest inter-observer cut-off variability was observed in the 41% SUVmax method, which resulted in more inter-observer disagreements in the classification of patients between high and low MTV groups. MTV measurements based on absolute SUV criteria were found to be significantly more reproducible than those based on 41% SUVmax criteria. The threshold was specific for each of eight segmentation methods, but all predicted prognosis.

Correction to: Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET/CT is an independent prognostic factor of diffuse large B-cell lymphoma.

A unit error concerning the tumor volume surface ratio (TVSR) is present throughout the article. The unit reported is "cm" but is actually "mm".

Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET/CT is an independent prognostic factor of diffuse large B-cell lymphoma.

INTRODUCTION: Our aim was to study the prognostic value of two new 18F-FDG PET biomarkers in diffuse large B-cell lymphoma (DLBCL). We examined the total tumor surface (TTS), describing the tumor-host interface, and the tumor volume surface ratio (TVSR), corresponding to the ratio between the total metabolic tumor volume (TMTV) and TTS, describing the tumor fragmentation. METHODS: We retrospectively included 215 patients with DLBCL. Patients underwent initial 18F-FDG PET/CT before R-CHOP (73%) or intensified R-CHOP (R-ACVBP) regimens (27%). The TMTV was measured using a fixed threshold value of 41% of SUVmax. To calculate TTS and TVSR, the surface was measured using an in-house software based on the marching cube algorithm. Spearman's rank correlation coefficient (ρ) was computed between TMTV, TTS, and TVSR, and ROC analysis was performed. Survival functions at 5 years were studied using a Kaplan-Meier method and uni/multivariate Cox analysis. RESULTS: TVSR was poorly correlated with TMTV (ρ = 0.5) and TTS (ρ = 0.26), while TTS was highly correlated with TMTV (ρ = 0.94) and was, therefore, excluded from the analysis. TMTV had the highest area under the ROC curve (0.711) and the best sensitivity (0.797), while TVSR had the best specificity (0.745). The optimal cut-off values to predict 5-year OS were 222 cm3 for TMTV and 6.0 mm for TVSR. Patients with high TMTV and TVSR had significantly worse prognosis in Kaplan-Meier and Cox univariate analysis. In a multivariate Cox analysis combining the International Prognostic Index (IPI), the type of chemotherapy, TMTV, and TVSR, all parameters were independent and significant prognostic factors (HR [95%CI]: IPI 1.4 [1.1-1.8], type of chemotherapy 4.5 [2.0-10.5], TMTV 2.8 [1.4-5.5], TVSR 2.1 [1.3-3.4]). A synergistic effect between TMTV and TVSR was observed in a Kaplan-Meier analysis combining the two parameters. CONCLUSIONS: TVSR measured on the initial 18F-FDG PET is an independent prognostic factor in DLBCL and has an additional prognostic value when combined with TMTV, IPI score and chemotherapy.

Combination of baseline FDG PET/CT total metabolic tumour volume and gene expression profile have a robust predictive value in patients with diffuse large B-cell lymphoma.

PURPOSE: This study evaluated the predictive significance of total metabolic tumour volume (TMTV) measured on baseline FDG PET/CT and its value in addition to gene expression profiling using a new method of gene analysis (rapid reverse transcriptase multiplex ligation-dependent probe amplification assay, RT-MLPA) in patients with diffuse large B-cell lymphoma treated with R-CHOP or R-CHOP-like chemotherapies. METHODS: The analysis included 114 patients. TMTV was measured using a 41% SUVmax threshold and tumours were classified into GCB or ABC subtypes according to the RT-MLPA assay. RESULTS: The median follow-up was 40 months. the 5-year progression-free survival (PFS) was 54% and the 5-year overall survival (OS) was 62%. The optimal TMTV cut-off value was 261 cm3. In 59 patients with a high TMTV the 5-year PFS and OS were 37% and 39%, respectively, in comparison with 72% and 83%, respectively, in 55 patients with a low TMTV (p = 0.0002 for PFS, p < 0.0001 for OS). ABC status was significantly associated with a worse prognosis. TMTV combined with molecular data identified three groups with very different outcomes: (1) patients with a low TMTV whatever their phenotype (n = 55), (2) patients with a high TMTV and GCB phenotype (n = 33), and (3) patients with a high TMTV and ABC phenotype (n = 26). In the three groups, 5-year PFS rates were 72%, 51% and 17% (p < 0.0001), and 5-year OS rates were 83%, 55% and 17% (p < 0.0001), respectively. In multivariate analysis, TMTV, ABC/GCB phenotype and International Prognostic Index were independent predictive factors for both PFS and OS (p < 0.05 for both). CONCLUSIONS: This integrated risk model could lead to more accurate selection of patients that would allow better individualization of therapy.