Search

Background: [18F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs' quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [18F]FDG PET solid tumour treatment response assessments, while comparing "standard PET" to "AI denoised half-duration PET" ("AI PET") during follow-up. Results: 110 patients referred for baseline and follow-up standard digital [18F]FDG PET/CT were prospectively included. "Standard" EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a "gold standard" were compared to "mixed" classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to "UHD") or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTCUHD or EARL2 or PERCISTUHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen's kappa = 0.86 (95% CI: 0.78–0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients. Conclusions: Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [18F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory. [ABSTRACT FROM AUTHOR]

Given the constant pressure to increase patient throughput while respecting radiation protection, global body PET image quality (IQ) is not satisfactory in all patients. We first studied the association between IQ and other variables, in particular body habitus, on a digital PET/CT. Second, to improve and homogenize IQ, we evaluated a deep learning PET denoising solution (Subtle PETTM) using convolutional neural networks. We analysed retrospectively in 113 patients visual IQ (by a 5-point Likert score in two readers) and semi-quantitative IQ (by the coefficient of variation in the liver, CVliv) as well as lesion detection and quantification in native and denoised PET. In native PET, visual and semi-quantitative IQ were lower in patients with larger body habitus (p < 0.0001 for both) and in men vs. women (p ≤ 0.03 for CVliv). After PET denoising, visual IQ scores increased and became more homogeneous between patients (4.8 ± 0.3 in denoised vs. 3.6 ± 0.6 in native PET; p < 0.0001). CVliv were lower in denoised PET than in native PET, 6.9 ± 0.9% vs. 12.2 ± 1.6%; p < 0.0001. The slope calculated by linear regression of CVliv according to weight was significantly lower in denoised than in native PET (p = 0.0002), demonstrating more uniform CVliv. Lesion concordance rate between both PET series was 369/371 (99.5%), with two lesions exclusively detected in native PET. SUVmax and SUVpeak of up to the five most intense native PET lesions per patient were lower in denoised PET (p < 0.001), with an average relative bias of −7.7% and −2.8%, respectively. DL-based PET denoising by Subtle PETTM allowed [18F]FDG PET global image quality to be improved and homogenized, while maintaining satisfactory lesion detection and quantification. DL-based denoising may render body habitus adaptive PET protocols unnecessary, and pave the way for the improvement and homogenization of PET modalities. [ABSTRACT FROM AUTHOR]

At present, 18F-fluorodesoxyglucose (18FDG) positron emission tomography (PET)/computed tomography (CT) cannot be used to omit a bone marrow biopsy (BMB) among initial staging procedures in follicular lymphoma (FL). The additional diagnostic value of skeletal textural features on baseline 18FDG-PET/CT in diffuse large B-cell lymphoma (DLBCL) patients has given promising results. The aim of this study is to evaluate the value of 18FDG-PET/CT radiomics for the diagnosis of bone marrow involvement (BMI) in FL patients. This retrospective bicentric study enrolled newly diagnosed FL patients addressed for baseline 18FDG PET/CT. For visual assessment, examinations were considered positive in cases of obvious bone focal uptakes. For textural analysis, the skeleton volumes of interest (VOIs) were automatically extracted from segmented CT images and analysed using LifeX software. BMB and visual assessment were taken as the gold standard: BMB −/PET − patients were considered as bone-NEGATIVE patients, whereas BMB +/PET −, BMB −/PET + and BMB +/PET + patients were considered bone-POSITIVE patients. A LASSO regression algorithm was used to select features of interest and to build a prediction model. Sixty-six consecutive patients were included: 36 bone-NEGATIVE (54.5%) and 30 bone-POSITIVE (45.5%). The LASSO regression found variance_GLCM, correlation_GLCM, joint entropy_GLCM and busyness_NGLDM to have nonzero regression coefficients. Based on ROC analysis, a cut-off equal to − 0.190 was found to be optimal for the diagnosis of BMI using PET pred.score. The corresponding sensitivity, specificity, PPV and NPV values were equal to 70.0%, 83.3%, 77.8% and 76.9%, respectively. When comparing the ROC AUCs with using BMB alone, visual PET assessment or PET pred.score, a significant difference was found between BMB versus visual PET assessments (p = 0.010) but not between BMB and PET pred.score assessments (p = 0.097). Skeleton texture analysis is worth exploring to improve the performance of 18FDG-PET/CT for the diagnosis of BMI at baseline in FL patients. [ABSTRACT FROM AUTHOR]

Aim: To evaluate the use of digital 18F-FDG PET/CT with small-voxels reconstruction for detecting in-transit metastases in melanoma patients with primary lesion located on the upper or lower limbs, in comparison with standard reconstruction and European Association of Nuclear Medicine Research limited (EARL)-compliant reconstruction mimicking former generation PET systems.Methods: Forty-six PET examinations acquired in list mode on a Vereos digital PET/CT system were reconstructed with (1) the standard reconstruction [2 iterations, 10 subsets (2i10s), point-spread function (PSF) modelling and time-of-flight enabled, no post-filtering and voxel size of 2 mm], (2) a small-voxel reconstruction using 1 mm voxels otherwise using the same parameters, (3) an EARL-compliant reconstruction mimicking a former generation system. Comparison of results across these reconstructions was made for a blind randomized review using a 3-point scale for the presence of in-transit metastases and image quality as well as for tumour-to-background (T/B) ratios and noise level in reference organs.Results: Seven of the thirty-two EARL-compliant images classified as negative moved to positive on 1mmPSF images, and 5 of the 6 EARL-compliant images classified as indeterminate moved to positive on 1mmPSF images (P = 0.01). Amongst a total of 20 PET examinations classified as positive using the 1mmPSF reconstruction, fifteen were considered true positive, five false positive results occurred. Twenty-four patients with 1 mm PSF images were classified as negative, none of those under active surveillance experienced in-transit metastases during the 17 months following their PET examination. The positive likelihood ratio for the 1 mm reconstruction was much higher than that observed for EARL-compliant images (14.7 vs 7.82). Importantly, negative likelihood ratios for the 1 mm and 1mmPSF reconstruction were almost perfect. Compared to EARL-compliant data, T/B ratios extracted from the 1mmPSF showed a 2.84-fold increase (P < 0.001). A similar pattern of statistically significant increase was observed for noise level in organs of reference. Image quality for the torso was found to be significantly lower for 1mmPSF reconstruction (P = 0.03). Image quality for the limbs was found to be better for 1mmPSF (P < 0.001).Conclusion: Digital PET with small-voxel reconstruction brings an additional value for the detection of in-transit metastases by reducing the number of indeterminate findings and making up for falsely negative scans using former generation PET systems. An acquisition encompassing lower or upper limbs as appropriate should be performed. [ABSTRACT FROM AUTHOR]

Introduction: We aimed to investigate whether 18F-FDG PET metabolic heterogeneity reflects the heterogeneity of estrogen receptor (ER) and progesterone receptor (PR) expressions within luminal non-metastatic breast tumors and if it could help in identifying patients with worst event-free survival (EFS). Materials and methods: On 38 PET high-resolution breast bed positions, a single physician drew volumes of interest encompassing the breast tumors to extract SUVmax, histogram parameters and textural features. High-resolution immunochemistry (IHC) scans were analyzed to extract Haralick parameters and descriptors of the distribution shape. Correlation between IHC and PET parameters were explored using Spearman tests. Variables of interest to predict the EFS status at 8 years (EFS-8y) were sought by means of a random forest classification. EFS-8y analyses were then performed using univariable Kaplan-Meier analyses and Cox regression analysis. When appropriate, Mann-Whitney tests and Spearman correlations were used to explore the relationship between clinical data and tumoral PET heterogeneity variables. Results: For ER expression, correlations were mainly observed with 18F-FDG histogram parameters, whereas for PR expression correlations were mainly observed with gray-level co-occurrence matrix (GLCM) parameters. The strongest correlations were observed between skewness_ER and uniformity_HISTO (ρ = −0.386, p = 0.017) and correlation_PR and entropy_GLCM (ρ = 0.540, p = 0.001), respectively. The median follow-up was 6.5 years and the 8y-EFS was 71.0%. Random forest classification found age, clinical stage, SUVmax, skewness_ER, kurtosis_ER, entropy_HISTO, and uniformity_HISTO to be variables of importance to predict the 8y-EFS. Univariable Kaplan-Meier survival analyses showed that skewness_ER was a predictor of 8y-EFS (66.7 ± 27.2 versus 19.1 ± 15.2, p = 0.018 with a cut-off value set to 0.163) whereas other IHC and PET parameters were not. On multivariable analysis including age, clinical stage and skewness_ER, none of the parameters were independent predictors. Indeed, skewness_ER was significantly higher in youngest patients (ρ = −0.351, p = 0.031) and in clinical stage III tumors (p = 0.023). Conclusion: A heterogeneous distribution of ER within the tumor in IHC appeared as an EFS-8y prognosticator in luminal non-metastatic breast cancers. Interestingly, it appeared to be correlated with PET histogram parameters which could therefore become potential non-invasive prognosticator tools, provided these results are confirmed by further larger and prospective studies. [ABSTRACT FROM AUTHOR]

Aim: To perform a comprehensive analysis of discordances between contrast-enhanced CT (ceCT) and 18F-FDG PET/CT in the evaluation of the extra-cerebral treatment monitoring in patients with stage IV melanoma. Materials and methods: We conducted a retrospective monocentric observational study over a 3-year period in patients referred for 18F-FDG PET/CT and ceCT in the framework of therapy monitoring of immune checkpoint (ICIs) as of January 2017. Imaging reports were analyzed by two physicians in consensus. The anatomical site responsible for discordances, as well as induced changes in treatment were noted. Results: Eighty patients were included and 195 pairs of scans analyzed. Overall, discordances occurred in 65 cases (33%). Eighty percent of the discordances (52/65) were due to 18F-FDG PET/CT scans upstaging the patient. Amongst these discordances, 17/52 (33%) led to change in patient's management, the most frequent being radiotherapy of a progressing site. ceCT represented 13/65 (20%) of discordances and induced changes in patients' management in 2/13 cases (15%). The most frequent anatomical site involved was subcutaneous for 18F-FDG PET/CT findings and lung or liver for ceCT. Conclusions: Treatment monitoring with 18F-FDG PET/CT is more efficient than ceCT and has a greater impact in patient's management. [ABSTRACT FROM AUTHOR]

Aims: (1) To perform a comprehensive analysis of the time elapsed between the last G-CSF injection and the PET/CT examination on the biodistribution of 18F-FDG, with emphasis on liver, spleen, and bone marrow uptake, and (2) to investigate whether an inversion of the liver to spleen ratio affects the Deauville scoring. Materials and methods: Retrospectively included were 74 consecutive diffuse large B cell lymphoma (DLBCL) patients referred for baseline and interim examinations and receiving immunochemotherapy with various G-CSF regimens. A comprehensive evaluation considering baseline metabolic active tumour volume (MATV), factors affecting liver uptake, the type of G-CSF, and the time elapsed between chemotherapy/G-CSF and interim PET/CTs was performed. Results: Mean (± SD) percentage variations between baseline and interim PET/CTs (i-PET/CT) for bone marrow (%Variation_BONE), liver (%Variation_LIVER) and spleen (%Variation_SPLEEN) were equal to 32.0 ± 46.9%, 16.1 ± 42.8%, and 10.6 ± 51.1 %, respectively. %Variation_LIVER and %Variation_SPLEEN were higher in patients using lenograstim, but this was linked to lower uptakes at baseline and was therefore likely not due to G-CSF itself. The mean delay between G-CSF injection and i-PET/CT acquisition was not an independent explanatory variable for %Variation_BONE, %Variation_LIVER, and %Variation_SPLEEN. On the contrary, %Variation_BONE and %Variation_SPLEEN were negatively correlated to the time-lapse between the end of chemotherapy and i-PET/CT: ρ = − 0.342 (p = 0.010) and ρ = − 0.529 (p < 0.0001), respectively. Patients with a time-lapse since the last injection of chemotherapy < 17 days displayed higher bone and spleen SUVmaxEARL. %Variation_LIVER was positively correlated to baseline MATV: ρ = 0.243 (p = 0.039). Patients displaying a high baseline MATV ≥ 177 cc had significantly lower liver SUVmaxEARL at baseline. This difference was no longer observed at i-PET/CT, after tumours had shrunk. Conclusions: Neither the type of G-CSF used nor the time elapsed between its last injection and i-PET/CT examination independently influences bone, hepatic, or splenic uptakes at i-PET/CT. The major determinant for the occurrence of a bone or spleen hypermetabolism on i-PET/CT is the time elapsed between the chemotherapy and the examination, which should be maintained above 15 days. Inversion of the liver to spleen ratio appeared to be due to increased spleen hypermetabolism on i-PET/CT, making unlikely an impact on the Deauville scoring. [ABSTRACT FROM AUTHOR]

Background: [ 18 F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs' quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [ 18 F]FDG PET solid tumour treatment response assessments, while comparing "standard PET" to "AI denoised half-duration PET" ("AI PET") during follow-up., Results: 110 patients referred for baseline and follow-up standard digital [ 18 F]FDG PET/CT were prospectively included. "Standard" EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a "gold standard" were compared to "mixed" classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to "UHD") or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTC UHD or EARL2 or PERCIST UHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen's kappa = 0.86 (95% CI: 0.78-0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients., Conclusions: Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [ 18 F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory., (© 2024. The Author(s).)

Introduction: The yield per elution of a 68 Ge/ 68 Ga generator decreases during its lifespan. This affects the number of patients injected per elution or the injected dose per patient, thereby negatively affecting the cost of examinations and the quality of PET images due to increased image noise. We aimed to investigate whether AI-based PET denoising can offset this decrease in image quality parameters., Methods: All patients addressed to our PET unit for a 68 Ga-DOTATOC PET/CT from April 2020 to February 2021 were enrolled. Forty-four patients underwent their PET scans according to Protocol&#95;FixedDose (150 MBq) and 32 according to Protocol&#95;WeightDose (1.5 MBq/kg). Protocol&#95;WeightDose examinations were processed using the Subtle PET software (Protocol&#95;WeightDose AI ). Liver and vascular SUV mean were recorded as well as SUVmax, SUVmean and metabolic tumour volume (MTV) of the most intense tumoural lesion and its background SUVmean. Liver and vascular coefficients of variation (CV), tumour-to-background and tumour-to-liver ratios were calculated., Results: The mean injected dose of 2.1 (0.4) MBq/kg per patient was significantly higher in the Protocol&#95;FixedDose group as compared to 1.5 (0.1) MBq/kg for the Protocol&#95;WeightDose group. Protocol&#95;WeightDose led to noisier images than Protocol&#95;FixedDose with higher CVs for liver (15.57% ± 4.32 vs. 13.04% ± 3.51, p = 0.018) and blood-pool (28.67% ± 8.65 vs. 22.25% ± 10.37, p = 0.0003). Protocol&#95;WeightDose AI led to less noisy images than Protocol&#95;WeightDose with lower liver CVs (11.42% ± 3.05 vs. 15.57% ± 4.32, p < 0.0001) and vascular CVs (16.62% ± 6.40 vs. 28.67% ± 8.65, p < 0.0001). Tumour-to-background and tumour-to-liver ratios were lower for protocol&#95;WeightDose AI : 6.78 ± 3.49 vs. 7.57 ± 4.73 ( p = 0.01) and 5.96 ± 5.43 vs. 6.77 ± 6.19 ( p < 0.0001), respectively. MTVs were higher after denoising whereas tumour SUVmax were lower: the mean% differences in MTV and SUVmax were + 11.14% (95% CI = 4.84-17.43) and -3.92% (95% CI = -6.25 to -1.59)., Conclusion: The degradation of PET image quality due to a reduction in injected dose at the end of the 68 Ge/ 68 Ga generator lifespan can be effectively counterbalanced by using AI-based PET denoising., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Quak, Weyts, Jaudet, Prigent, Foucras and Lasnon.)

Despite the feminization of the medical workforce, women do not have the same career perspectives as men. In nuclear medicine, little information is available on the sex gap regarding prominent author positions in scientific articles. Therefore, the purpose of this study was to evaluate recent trends in the sex distribution of first and last authorship of articles published in nuclear medicine journals. Methods: We conducted a bibliometric analysis of first and last author sex of articles published from 2014 to 2020 in 15 nuclear medicine journals. Manuscript title, article type, journal impact factor, date of publication, and first and last name and country of provenance of first and last authors were noted. The Gender API software was used to determine author sex. All statistics were descriptive. Results: Women represented 32.8% of first authors and 19.6% of last authors. Female authorship increased from 28.2% (428 of 1,518 articles) in 2014 to 35.5% (735 of 2,069 articles; relative increase, 72%) in 2020 ( P < 0.001) for first authors and from 15.6% (237 of 1,518 articles) in 2014 to 20.5% (424 of 2,069 articles; relative increase, 79%) in 2020 ( P < 0.001) for last authors. Parity was forecast for 2035 for first authors and 2052 for last authors. Female authorship increased in Europe for first authors ( P = 0.014) and last authors ( P < 0.001), in high-ranking journals for first authors ( P = 0.004) and last authors ( P < 0.001), and in other journal ranks for last authors ( P = 0.01). Female first and last authorship rose for original articles ( P = 0.02 and P = 0.01, respectively) and case reports ( P < 0.001 and P = 0.002, respectively). Regarding collaborations, the proportion of articles produced by male first and last authors decreased from 62.2% in 2014 to 52.9% in 2020 in favor of female first and last authors (odds ratio, 1.07; P < 0.001), male first and female last authors (odds ratio, 1.05; P < 0.001), and female first and male last authors (odds ratio, 1.03; P < 0.001). Conclusion: Female first and last authorship in nuclear medicine journals increased substantially from 2014 to 2020, in particular in high-ranking journals, in Europe, and for original articles and case reports. Male-to-male collaborations decreased by 10% in favor of all other collaborations. Parity can be foreseen in a few decades., (© 2022 by the Society of Nuclear Medicine and Molecular Imaging.)

Introduction: We aimed to investigate whether 18 F-FDG PET metabolic heterogeneity reflects the heterogeneity of estrogen receptor (ER) and progesterone receptor (PR) expressions within luminal non-metastatic breast tumors and if it could help in identifying patients with worst event-free survival (EFS)., Materials and Methods: On 38 PET high-resolution breast bed positions, a single physician drew volumes of interest encompassing the breast tumors to extract SUV max , histogram parameters and textural features. High-resolution immunochemistry (IHC) scans were analyzed to extract Haralick parameters and descriptors of the distribution shape. Correlation between IHC and PET parameters were explored using Spearman tests. Variables of interest to predict the EFS status at 8 years (EFS-8y) were sought by means of a random forest classification. EFS-8y analyses were then performed using univariable Kaplan-Meier analyses and Cox regression analysis. When appropriate, Mann-Whitney tests and Spearman correlations were used to explore the relationship between clinical data and tumoral PET heterogeneity variables., Results: For ER expression, correlations were mainly observed with 18 F-FDG histogram parameters, whereas for PR expression correlations were mainly observed with gray-level co-occurrence matrix (GLCM) parameters. The strongest correlations were observed between skewness&#95; ER and uniformity&#95; HISTO (ρ = -0.386, p = 0.017) and correlation&#95; PR and entropy&#95; GLCM (ρ = 0.540, p = 0.001), respectively. The median follow-up was 6.5 years and the 8y-EFS was 71.0%. Random forest classification found age, clinical stage, SUV max , skewness&#95; ER , kurtosis&#95; ER , entropy&#95; HISTO , and uniformity&#95; HISTO to be variables of importance to predict the 8y-EFS. Univariable Kaplan-Meier survival analyses showed that skewness&#95; ER was a predictor of 8y-EFS (66.7 ± 27.2 versus 19.1 ± 15.2, p = 0.018 with a cut-off value set to 0.163) whereas other IHC and PET parameters were not. On multivariable analysis including age, clinical stage and skewness&#95; ER , none of the parameters were independent predictors. Indeed, skewness&#95; ER was significantly higher in youngest patients (ρ = -0.351, p = 0.031) and in clinical stage III tumors (p = 0.023)., Conclusion: A heterogeneous distribution of ER within the tumor in IHC appeared as an EFS-8y prognosticator in luminal non-metastatic breast cancers. Interestingly, it appeared to be correlated with PET histogram parameters which could therefore become potential non-invasive prognosticator tools, provided these results are confirmed by further larger and prospective studies., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Aide, Elie, Blanc-Fournier, Levy, Salomon and Lasnon.)