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]

This study aimed to investigate if combining clinical characteristics with pre-therapeutic 18 F-fluorodeoxyglucose (18 F-FDG) positron emission tomography (PET) radiomics could predict the presence of molecular alteration(s) in key molecular targets in lung adenocarcinoma. This non-interventional monocentric study included patients with newly diagnosed lung adenocarcinoma referred for baseline PET who had tumour molecular analyses. The data were randomly split into training and test datasets. LASSO regression with 100-fold cross-validation was performed, including sex, age, smoking history, AJCC cancer stage and 31 PET variables. In total, 109 patients were analysed, and it was found that 63 (57.8%) patients had at least one molecular alteration. Using the training dataset (n = 87), the model included 10 variables, namely age, sex, smoking history, AJCC stage, excessKustosis_HISTO, sphericity_SHAPE, variance_GLCM, correlation_GLCM, LZE_GLZLM, and GLNU_GLZLM. The ROC analysis for molecular alteration prediction using this model found an AUC equal to 0.866 (p < 0.0001). A cut-off value set to 0.48 led to a sensitivity of 90.6% and a positive likelihood ratio (LR+) value equal to 2.4. After application of this cut-off value in the unseen test dataset of patients (n = 22), the test presented a sensitivity equal to 90.0% and an LR+ value of 1.35. A clinico-metabolic 18 F-FDG PET phenotype allows the detection of key molecular target alterations with high sensitivity and negative predictive value. Hence, it opens the way to the selection of patients for molecular analysis. [ABSTRACT FROM AUTHOR]

Purpose: We investigated whether artificial intelligence (AI)-based denoising halves PET acquisition time in digital PET/CT. Methods: One hundred ninety-five patients referred for [18F]FDG PET/CT were prospectively included. Body PET acquisitions were performed in list mode. Original "PET90" (90 s/bed position) was compared to reconstructed ½-duration PET (45 s/bed position) with and without AI-denoising, "PET45AI and PET45". Denoising was performed by SubtlePET™ using deep convolutional neural networks. Visual global image quality (IQ) 3-point scores and lesion detectability were evaluated. Lesion maximal and peak standardized uptake values using lean body mass (SULmax and SULpeak), metabolic volumes (MV), and liver SULmean were measured, including both standard and EARL1 (European Association of Nuclear Medicine Research Ltd) compliant SUL. Lesion-to-liver SUL ratios (LLR) and liver coefficients of variation (CVliv) were calculated. Results: PET45 showed mediocre IQ (scored poor in 8% and moderate in 68%) and lesion concordance rate with PET90 (88.7%). In PET45AI, IQ scores were similar to PET90 (P = 0.80), good in 92% and moderate in 8% for both. The lesion concordance rate between PET90 and PET45AI was 836/856 (97.7%), with 7 lesions (0.8%) only detected in PET90 and 13 (1.5%) exclusively in PET45AI. Lesion EARL1 SULpeak was not significantly different between both PET (P = 0.09). Lesion standard SULpeak, standard and EARL1 SULmax, LLR and CVliv were lower in PET45AI than in PET90 (P < 0.0001), while lesion MV and liver SULmean were higher (P < 0.0001). Good to excellent intraclass correlation coefficients (ICC) between PET90 and PET45AI were observed for lesion SUL and MV (ICC ≥ 0.97) and for liver SULmean (ICC ≥ 0.87). Conclusion: AI allows [18F]FDG PET duration in digital PET/CT to be halved, while restoring degraded ½-duration PET image quality. Future multicentric studies, including other PET radiopharmaceuticals, are warranted. [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]

In DLBCL, the Deauville scoring system (DS) is the standard for PET/CT response assessment. An alternative system, based on the semi-quantitative change in standardized uptake values, namely ΔSUVmax, has been reported to be more objective than the DS. We aimed to compare ΔSUVmax and DS for risk stratification of DLBCL patients on end-of-treatment (EoT) PET. 108 consecutive patients were included. 2-year EFS Kaplan–Meier survival analyses and Cox regression models were performed. 2-year EFS was significantly different between favorable ΔSUVmax (favΔ < −86.5%) and unfavorable ΔSUVmax (unfavΔ ≥ −86.5%) patients: 100.0% ± 0.0 versus 58.3% ± 14.2 (p = 0.001). On Cox multivariable regression, ΔSUVmax status was the only independent predictor of 2-year EFS, outperforming DS. Therefore, ΔSUVmax should be computed for non-responder patients, especially DS4, as the 2-year EFS is not different between responders and non-responders in the case of favΔ. Further studies are needed in order to confirm this hypothesis. [ABSTRACT FROM AUTHOR]

Background: Immune checkpoint inhibitors (ICIs) have significantly improved survival in advanced melanoma. There is a need for robust biomarkers to identify patients who do not respond. We analysed 14 baseline 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) metrics and their evolution to assess their correlation with patient outcome, compared with 7 established biological markers and 7 clinical variables. Methods: We conducted a retrospective monocentric observational study of 29 patients with advanced melanoma who underwent baseline 18F-FDG PET/CT, followed by an early monitoring PET/CT (iPET) scan after 1 month of treatment and follow-up studies at 3rd (M3PET) and 6th month (M6PET). 18F-FDG uptake in immune organs (spleen, bone marrow, ileocecal valve) and derived spleen-to-liver (SLR) and bone-to-liver (BLR) ratios were reviewed by two PET readers for reproducibility analysis purposes including 14 PET variables. The most reproducible indexes were used for evaluation as predictors of overall survival (OS) in comparison with PET response using imPERCIST5, whole-body metabolic active tumour volume (WB-MATV) and biological parameters (lactate dehydrogenases (LDH), reactive protein c (CRP), white blood count (WBC), absolute lymphocyte count (ALC), neutrophil to lymphocyte ratio (NLR) and derived neutrophils to lymphocyte ratio). Results: Strong reproducibility's (intraclass coefficients of correlation (ICC) > 0.90) were observed for spleen anterior SUVpeak, spleen MV, spleen TLG, spleen length and BLRmean. ICC for SLRmean and ileocecal SUVmean were 0.86 and 0.65, respectively. In the 1-year OS 1 group, SLRmean tended to increase at each time point to reach a significant difference at M6-PET (p = 0.019). The same trends were observed with spleen SUVpeak anterior and spleen length. In the 1-year OS 0 group, a significative increase of spleen length was found at iPET, as compared with baseline PET (p = 0.014) and M3-PET (p = 0.0239). Univariable Kaplan-Meier survival analysis found that i%var spleen length, M3%var SLRmean, baseline LDH, i%var NLR and response at M6PET were all predictors of 1-year OS. Conclusions: SLRmean is recommended as a prognosticator in melanoma patients under immunotherapy: its increase greater than 25% at 3 months, compared with baseline, was associated with poor outcome after ICIs. [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]

Objectives: To explore the prognostic value of positron emission tomography (PET) radiomic features in the field of diffuse large B cell lymphoma (DLBCL) treated with a first-line immunochemotherapy.Methods: One-hundred thirty-two patients newly diagnosed with DLBCL were retrospectively included. PET studies were reconstructed using an ordered subset expectation maximisation algorithm with point spread function modelling. The total metabolic tumour volume (MTV) was recorded for each patient, and the volume of interest structure of the largest target lesion was used to compute 18F-FDG textural parameters. Data was randomly split into training and validation datasets. Optimal cutoff values were determined by means of 2-year event-free survival (EFS) ROC analyses. Two-year EFS analyses were performed using Kaplan-Meier survival analyses and univariable and multivariable Cox regression models.Results: The median follow-up was 27 months, and the 2-year event-free survival (2y-EFS) was 77.3% in the entire population. ROC analyses for the 2y-EFS reached statistical significance for total MTV as well as four second-order metrics (homogeneity, contrast, correlation, dissimilarity) and five third-order metrics (LZE (Long-Zone Emphasis), LZLGE (Long-Zone Low-Grey Level Emphasis), LZHGE (Long-Zone High-Grey Level Emphasis), GLNU (Grey-Level Non-Uniformity) and ZP (Zone Percentage)). LZHGE displayed the highest ROC analysis accuracy (acc. = 0.76) and the best discriminant value on univariable Kaplan-Meier analysis (p < 0.0001, HR = 4.54). On multivariable analysis, including IPIaa, total MTV and LZHGE, LZHGE was the only independent predictor of 2y-EFS. These results were confirmed on the validation dataset.Conclusions: Baseline 18F-FDG PET heterogeneity of the largest lymphoma lesion is a promising predictor of 2y-EFS in newly diagnosed DLBCL treated with immunochemotherapy.Key Points: •18F-FDG metabolic heterogeneity emerges as a new tool for survival prognostication of patients and has been explored in many solid tumours with promising results. • Baseline18F-FDG PET heterogeneity of the largest lymphoma lesion is an independent predictor of 2y-EFS in newly diagnosed DLBCL treated with immunochemotherapy. • DLBCL patients presenting with a heterogeneous tumour displayed a worse prognosis. [ABSTRACT FROM AUTHOR]