Importance Optimizing treatment decisions in metastatic breast cancer (MBC) can alleviate patients’ burden and improve quality of life. Whether 18 F-fluorodeoxyglucose positron emission tomography (FDG-PET) can be used to better estimate outcomes is unknown. Objective To evaluate clinical utility of early metabolic change on FDG-PET for improving outcome estimation compared with standard diagnostic evaluation in patients with newly diagnosed MBC. Design, Setting, and Participants The multicenter IMPACT-MBC clinical cohort trial enrolled patients with nonrapidly progressive, newly diagnosed MBC from August 2013 to May 2018, before initiation of first-line systemic therapy. Baseline assessment included metastasis biopsy procedure and FDG-PET and CT imaging. Early FDG-PET was performed after 2 weeks of treatment, and CT response evaluation after 8 weeks. Clinical utility was defined as the ability of early FDG-PET to estimate progressive disease (PD) on CT, progression-free survival (PFS), and overall survival (OS). Data were analyzed from October 19, 2025, to February 13, 2026. Intervention Early FDG-PET or standard-of-care (SOC) biopsy-based treatment. Main Outcomes and Measures Clinical utility of molecular imaging to improve outcome estimation of standard diagnostics defined as the capacity to identify poor patient outcomes. Measures were PD at 8 weeks, PFS, and OS. Results The analysis included 200 patients (median [range] age, 61 [32-84] years; 198 females [99%] and 2 males [1%]). Non-PD on early FDG-PET had a negative predictive value (NPV) of 94.7% (95% CI, 89.5%-97.4%) for non-PD on 8-week CT. This was similar in all MBC subtypes and bone-only disease. Patients with SOC treatment and non-PD on early FDG-PET (n = 133) had a median PFS of 19.4 (95% CI, 15.2-22.8) months and OS of 39.4 (95% CI, 33.7-48.3) months compared to 4.1 (95% CI, 3.3-15.5) months and 18.5 (95% 3 CI, 7.0-33.0) months, respectively ( P < .001 for both). Patients with non-PD on 8-week CT but with PD on early FDG-PET had a median (IQR) PFS and OS of 9.5 (4.1-18.1) and 19.4 (8.7-33.0) months compared to 22.3 (15.3-96.1) months and 40.1 (23.4-72.7) months without PD. Conclusions and Relevance In this clinical cohort trial of patients with nonrapidly progressive, newly diagnosed MBC before initiation of first-line systemic therapy, early FDG-PET after only 2 weeks of treatment identified patients with MBC with distinct long-term outcomes. Incorporating early FDG-PET can improve outcome estimation of standard CT assessment. Trial Registration ClinicalTrials.gov Identifier: NCT01957332

Score chart with predicted probability (%) to remain on WW at 12 months This model was based on the number of IMDC Risk factors (0, 1, 2), the number or involved organ sites (0 - 4) and the geometric mean [¹⁸F]FDG SUVmax as a continuous variable. The underlying formula is 100*(exp(-0.531)^exp(0.198*[IMDC score] + 0.039*[No of affected organ sites] + 0.170*[geometric mean [¹⁸F]FDG SUVmax] - 1.09))

Flow-chart patients according to RECIST-defined PD. *All patients had clinical disease progression; no CT-imaging was performed before initiation of systemic treatment ** In total 7 patients choose best supportive care. Three other patients underwent radiotherapy or surgery of all target lesions.

Flow diagram of patient enrolment. * Four patients were unfit for systemic treatment due to clinical deterioration resulting from rapid disease progression (n=3) or comorbidity and age (n=1). Three other patients did not wat systemic treatment.

The primary aim of this study was to assess whether there is an association between pretreatment fluorine-18-labelled fluorodeoxyglucose([18F]FDG) positron-emission tomography (PET) dissemination features and survival outcomes: overall survival (OS) and progression-free survival (PFS), in metastatic melanoma patients treated with immune-checkpoint inhibitors. The secondary aim was to assess the added value of dissemination features to conventional PET metrics and clinical characteristics with respect to survival outcome prediction. We included 80 consecutive patients with metastatic/unresectable melanoma treated with first-line immunotherapy. On a patient level, eighteen dissemination features and five conventional PET metrics: maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), peak standardized uptake value (SUVpeak), total metabolically active tumour volume (MATV) and total total lesion glycolysis (TLG) were extracted. From the eighteen dissemination features, five provided quantitative measures on spatial distribution, ten on SUV variability and three on tumour volume variability. Furthermore, clinical characteristics were collected. Univariable and multivariable Cox regression analyses were used to assess the association of OS and PFS with the conventional PET metrics, dissemination features and clinical characteristics. The final models were internally validated using bootstrapping. The spatial dissemination features DmaxPatient, DmaxBulk and SpreadBulk and volume dissemination feature DvolPatient on pretreatment [18F]FDG PET/CT were associated with OS. DmaxBulk and SpreadBulk were also associated with PFS. The spatial dissemination feature DmaxBulk, which measures the distance between the largest lesion and any other lesion within the studied metastatic melanoma patients, showed an independent association with OS (hazard ratio = 2.1) and PFS (hazard ratio = 1.9). Conventional PET metrics were not associated with OS nor PFS. The validated dissemination model, clinical model and combination model showed similar low discriminative ability with an Area Under the Curve (AUC) of 0.61-0.66 for OS and an AUC of 0.59-0.66 for PFS. Limitations of our study results were the lack of an available external cohort for further validation and the retrospective design. Future research could include features from other imaging modalities, non-tumour characteristics and other clinical characteristics for model improvement.

3576 Background: The use of anti-Epidermal Growth Factor Receptor monoclonal antibody therapy (anti-EGFR mAb) for patients with metastatic colorectal cancer (mCRC) is ongoing subject of research. Initially, absence of mutations in KRASand NRAS oncogenes was identified as biomarker for response, however, not all patients benefitted. Molecular imaging to assess metabolic response could serve as an early biomarker for treatment response. We evaluated the predictive performance of early evaluation of metabolic rate with [18F]FDG PET/CT and baseline and after 1 intravenous anti-EGFR mAb administration to distinguish patients with and without clinical benefit. Methods: The multicenter IMPACT-CRC study (NCT02117466) prospectively included patients with RASwild-type mCRC starting treatment with biweekly monotherapy anti-EGFR mAb (cetuximab or panitumumab) as second or third line treatment. Clinical benefit was defined as partial, response (PR)complete response (CR) and stable disease (SD) according to RECIST (version 1.1) with CT-imaging at 8 weeks. Patients underwent an [18F]FDG PET/CT at baseline and 2 weeks after start therapy prior to the second treatment cycle. Change in sum Total Lesion Glycolysis (TLG, defined as metabolic active tumor volume (MATV) times mean standard uptake value corrected for lean body mass (SULmean)) of 5 lesions according to van Helden et al (PLoS One 2016 May 19;11(5):e0155178) was evaluated as a predictive biomarker for clinical benefit using a predetermined data-driven threshold. Tumor sidedness and BRAF mutations were determined. Results: Seventy-five out of 80 participating patients were evaluable for metabolic response: The mean change in sum TLG was -58% (SD 19%) for patient with clinical benefit (n=57) versus -1·9% (SD 36%) without clinical benefit (n=18); P =0·003. A threshold of < -15% change in sum TLG had a 100% negative predictive value for clinical benefit. Metabolic responders had a longer progression-free survival (PFS) compared to metabolic non-responders (6.5 versus 1·7 months ( P<0·001)). Sixty-five (out of 80) patients had RAS/BRAF wild-type (wt) left-sided mCRC, with a 91% clinical benefit rate (30% PR and 61% SD) and a median PFS of 5·7 months (95% CI 5·2 – 10). Conclusions: Early [18F]FDG PET/CT after a single dose of anti-EGFR mAb therapy demonstrates a 100% negative predictive value for clinical benefit. Selection of patients with left-sided RASwt/ BRAFwt mCRC successfully identifies the majority (91%) of patients with clinical benefit from anti-EGFR monotherapy. For mCRC patients with inconclusive mutational screens early [18F]FDG PET/CT evaluation may have clinical value to predict treatment benefit. Clinical trial information: NCT02117466 .

Abstract Purpose: Watchful waiting (WW) can be considered for patients with metastatic clear-cell renal cell carcinoma (mccRCC) with good or intermediate prognosis, especially those with <2 International Metastatic RCC Database Consortium criteria and ≤2 metastatic sites [referred to as watch and wait (“W&W”) criteria]. The IMaging PAtients for Cancer drug SelecTion-Renal Cell Carcinoma study objective was to assess the predictive value of [18F]FDG PET/CT and [89Zr]Zr-DFO-girentuximab PET/CT for WW duration in patients with mccRCC. Experimental Design: Between February 2015 and March 2018, 48 patients were enrolled, including 40 evaluable patients with good (n = 14) and intermediate (n = 26) prognosis. Baseline contrast-enhanced CT, [18F]FDG and [89Zr]Zr-DFO-girentuximab PET/CT were performed. Primary endpoint was the time to disease progression warranting systemic treatment. Maximum standardized uptake values (SUVmax) were measured using lesions on CT images coregistered to PET/CT. High and low uptake groups were defined on the basis of median geometric mean SUVmax of RECIST-measurable lesions across patients. Results: The median WW time was 16.1 months [95% confidence interval (CI): 9.0–31.7]. The median WW period was shorter in patients with high [18F]FDG tumor uptake than those with low uptake (9.0 vs. 36.2 months; HR, 5.6; 95% CI: 2.4–14.7; P < 0.001). Patients with high [89Zr]Zr-DFO-girentuximab tumor uptake had a median WW period of 9.3 versus 21.3 months with low uptake (HR, 1.7; 95% CI: 0.9–3.3; P = 0.13). Patients with “W&W criteria” had a longer median WW period of 21.3 compared with patients without: 9.3 months (HR, 1.9; 95% CI: 0.9–3.9; Pone-sided = 0.034). Adding [18F]FDG uptake to the “W&W criteria” improved the prediction of WW duration (P < 0.001); whereas [89Zr]Zr-DFO-girentuximab did not (P = 0.53). Conclusions: In patients with good- or intermediate-risk mccRCC, low [18F]FDG uptake is associated with prolonged WW. This study shows the predictive value of the “W&W criteria” for WW duration and shows the potential of [18F]FDG-PET/CT to further improve this.

Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.

We investigated whether the outcome prediction of patients with aggressive B-cell lymphoma can be improved by combining clinical, molecular genotype, and radiomics features. MYC, BCL2, and BCL6 rearrangements were assessed using fluorescence in situ hybridization. Seventeen radiomics features were extracted from the baseline positron emission tomography-computed tomography of 323 patients, which included maximum standardized uptake value (SUVmax), SUVpeak, SUVmean, metabolic tumor volume (MTV), total lesion glycolysis, and 12 dissemination features pertaining to distance, differences in uptake and volume between lesions, respectively. Logistic regression with backward feature selection was used to predict progression after 2 years. The predictive value of (1) International Prognostic Index (IPI); (2) IPI plus MYC; (3) IPI, MYC, and MTV; (4) radiomics; and (5) MYC plus radiomics models were tested using the cross-validated area under the curve (CV-AUC) and positive predictive values (PPVs). IPI yielded a CV-AUC of 0.65 ± 0.07 with a PPV of 29.6%. The IPI plus MYC model yielded a CV-AUC of 0.68 ± 0.08. IPI, MYC, and MTV yielded a CV-AUC of 0.74 ± 0.08. The highest model performance of the radiomics model was observed for MTV combined with the maximum distance between the largest lesion and another lesion, the maximum difference in SUVpeak between 2 lesions, and the sum of distances between all lesions, yielding an improved CV-AUC of 0.77 ± 0.07. The same radiomics features were retained when adding MYC (CV-AUC, 0.77 ± 0.07). PPV was highest for the MYC plus radiomics model (50.0%) and increased by 20% compared with the IPI (29.6%). Adding radiomics features improved model performance and PPV and can, therefore, aid in identifying poor prognosis patients.

Purpose: Currently, guidelines for PET with 18F-fluorodeoxy-glucose (FDG-PET) interpretation for assessment of therapy response in oncology primarily involve visual evaluation of FDG-PET/CT scans. However, quantitative measurements of the metabolic activity in tumors may be even more useful in evaluating response to treatment. Guidelines based on such measurements, including the European Organization for Research and Treatment of Cancer Criteria and PET Response Criteria in Solid Tumors, have been proposed. However, more rigorous analysis of response criteria based on FDG-PET measurements is needed to adopt regular use in practice.Experimental Design: Well-defined boundaries of repeatability and reproducibility of quantitative measurements to discriminate noise from true signal changes are a needed initial step. An extension of the meta-analysis from de Langen and colleagues (2012) of the test-retest repeatability of quantitative FDG-PET measurements, including mean, maximum, and peak standardized uptake values (SUVmax, SUVmean, and SUVpeak, respectively), was performed. Data from 11 studies in the literature were used to estimate the relationship between the variance in test-retest mea-surements with uptake level and various study-level, patient-level, and lesion-level characteristics.Results: Test-retest repeatability of percentage fluctuations for all three types of SUV measurement (max, mean, and peak) improved with higher FDG uptake levels. Repeatability in all three SUV measurements varied for different lesion locations. Worse repeat-ability in SUVmean was also associated with higher tumor volumes.Conclusions: On the basis of these results, recommendations regarding SUV measurements for assessing minimal detectable changes based on repeatability and reproducibility are proposed. These should be applied to differentiate between response categories for a future set of FDG-PET-based criteria that assess clinically significant changes in tumor response.

AbstractPurpose: Currently, guidelines for PET with 18F-fluorodeoxyglucose (FDG-PET) interpretation for assessment of therapy response in oncology primarily involve visual evaluation of FDG-PET/CT scans. However, quantitative measurements of the metabolic activity in tumors may be even more useful in evaluating response to treatment. Guidelines based on such measurements, including the European Organization for Research and Treatment of Cancer Criteria and PET Response Criteria in Solid Tumors, have been proposed. However, more rigorous analysis of response criteria based on FDG-PET measurements is needed to adopt regular use in practice. Experimental Design: Well-defined boundaries of repeatability and reproducibility of quantitative measurements to discriminate noise from true signal changes are a needed initial step. An extension of the meta-analysis from de Langen and colleagues (2012) of the test–retest repeatability of quantitative FDG-PET measurements, including mean, maximum, and peak standardized uptake values (SUVmax, SUVmean, and SUVpeak, respectively), was performed. Data from 11 studies in the literature were used to estimate the relationship between the variance in test–retest measurements with uptake level and various study-level, patient-level, and lesion-level characteristics. Results: Test–retest repeatability of percentage fluctuations for all three types of SUV measurement (max, mean, and peak) improved with higher FDG uptake levels. Repeatability in all three SUV measurements varied for different lesion locations. Worse repeatability in SUVmean was also associated with higher tumor volumes. Conclusions: On the basis of these results, recommendations regarding SUV measurements for assessing minimal detectable changes based on repeatability and reproducibility are proposed. These should be applied to differentiate between response categories for a future set of FDG-PET–based criteria that assess clinically significant changes in tumor response.

Abstract Background FDG-PET/CT has a high negative predictive value to detect residual nodal disease in patients with locally advanced squamous cell head and neck cancer after completing concurrent chemoradiotherapy (CCRT). However, the positive predictive value remains suboptimal due to inflammation after radiotherapy, generating unnecessary further investigations and possibly even surgery. We report the results of a preplanned secondary end point of the ECLYPS study regarding the potential advantages of dual time point FDG-PET/CT imaging (DTPI) in this setting. Standardized dedicated head and neck FDG-PET/CT images were obtained 12 weeks after CCRT at 60 and 120 min after tracer administration. We performed a semiquantitative assessment of lymph nodes, and the retention index (RI) was explored to optimize diagnostic performance. The reference standard was histology, negative FDG-PET/CT at 1 year, or > 2 years of clinical follow-up. The time-dependent area under the receiver operator characteristics (AUROC) curves was calculated. Results In total, 102 subjects were eligible for analysis. SUV values increased in malignant nodes (median SUV1 = 2.6 vs. SUV2 = 2.7; P = 0.04) but not in benign nodes (median SUV1 = 1.8 vs. SUV2 = 1.7; P = 0.28). In benign nodes, RI was negative although highly variable (median RI = − 2.6; IQR 21.2), while in malignant nodes RI was positive (median RI = 12.3; IQR 37.2) and significantly higher (P = 0.018) compared to benign nodes. A combined threshold (SUV1 ≥ 2.2 + RI ≥ 3%) significantly reduced the amount of false-positive cases by 53% (P = 0.02) resulting in an increased specificity (90.8% vs. 80.5%) and PPV (52.9% vs. 37.0%), while sensitivity (60.0% vs. 66.7%) and NPV remained comparably high (92.9% vs. 93.3%). However, AUROC, as overall measure of benefit in diagnostic accuracy, did not significantly improve (P = 0.62). In HPV-related disease (n = 32), there was no significant difference between SUV1, SUV2, and RI in malignant and benign nodes, yet this subgroup was small. Conclusions DTPI did not improve the overall diagnostic accuracy of FDG-PET/CT to detect residual disease 12 weeks after chemoradiation. Due to differences in tracer kinetics between malignant and benign nodes, DTPI improved the specificity, but at the expense of a loss in sensitivity, albeit minimal. Since false negatives at the 12 weeks PET/CT are mainly due to minimal residual disease, DTPI is not able to significantly improve sensitivity, but repeat scanning at a later time (e.g. after 12 months) could possibly solve this problem. Further study is required in HPV-associated disease.

Purpose Biomarkers that can accurately predict outcome in DLBCL patients are urgently needed. Radiomics features extracted from baseline [ 18 F]-FDG PET/CT scans have shown promising results. This study aims to investigate which lesion- and feature-selection approaches/methods resulted in the best prediction of progression after 2 years. Methods A total of 296 patients were included. 485 radiomics features ( n = 5 conventional PET, n = 22 morphology, n = 50 intensity, n = 408 texture) were extracted for all individual lesions and at patient level, where all lesions were aggregated into one VOI. 18 features quantifying dissemination were extracted at patient level. Several lesion selection approaches were tested (largest or hottest lesion, patient level [all with/without dissemination], maximum or median of all lesions) and compared to the predictive value of our previously published model. Several data reduction methods were applied (principal component analysis, recursive feature elimination (RFE), factor analysis, and univariate selection). The predictive value of all models was tested using a fivefold cross-validation approach with 50 repeats with and without oversampling, yielding the mean cross-validated AUC (CV-AUC). Additionally, the relative importance of individual radiomics features was determined. Results Models with conventional PET and dissemination features showed the highest predictive value (CV-AUC: 0.72–0.75). Dissemination features had the highest relative importance in these models. No lesion selection approach showed significantly higher predictive value compared to our previous model. Oversampling combined with RFE resulted in highest CV-AUCs. Conclusion Regardless of the applied lesion selection or feature selection approach and feature reduction methods, patient level conventional PET features and dissemination features have the highest predictive value. Trial registration number and date: EudraCT: 2006–005174-42, 01–08-2008.

Consensus about a standard segmentation method to derive metabolic tumor volume (MTV) in classical Hodgkin lymphoma (cHL) is lacking, and it is unknown how different segmentation methods influence quantitative PET features. Therefore, we aimed to evaluate the delineation and completeness of lesion selection and the need for manual adaptation with different segmentation methods, and to assess the influence of segmentation methods on the prognostic value of MTV, intensity, and dissemination radiomics features in cHL patients. Methods: We analyzed a total of 105 18F-FDG PET/CT scans from patients with newly diagnosed (n = 35) and relapsed/refractory (n = 70) cHL with 6 segmentation methods: 2 fixed thresholds on SUV4.0 and SUV2.5, 2 relative methods of 41% of SUVmax (41max) and a contrast-corrected 50% of SUVpeak (A50P), and 2 combination majority vote (MV) methods (MV2, MV3). Segmentation quality was assessed by 2 reviewers on the basis of predefined quality criteria: completeness of selection, the need for manual adaptation, and delineation of lesion borders. Correlations and prognostic performance of resulting radiomics features were compared among the methods. Results: SUV4.0 required the least manual adaptation but tended to underestimate MTV and often missed small lesions with low 18F-FDG uptake. SUV2.5 most frequently included all lesions but required minor manual adaptations and generally overestimated MTV. In contrast, few lesions were missed when using 41max, A50P, MV2, and MV3, but these segmentation methods required extensive manual adaptation and overestimated MTV in most cases. MTV and dissemination features significantly differed among the methods. However, correlations among methods were high for MTV and most intensity and dissemination features. There were no significant differences in prognostic performance for all features among the methods. Conclusion: A high correlation existed between MTV, intensity, and most dissemination features derived with the different segmentation methods, and the prognostic performance is similar. Despite frequently missing small lesions with low 18F-FDG avidity, segmentation with a fixed threshold of SUV4.0 required the least manual adaptation, which is critical for future research and implementation in clinical practice. However, the importance of small, low 18F-FDG-avidity lesions should be addressed in a larger cohort of cHL patients.

To compare the predictive value of new immunotherapy-specific fluorine-18-labeled glucose Positron Emission Tomography/Computed Tomography ([18F]FDG PET/CT) response criteria to conventional PET/CT criteria for overall survival (OS) in melanoma and lung cancer patients treated with immunotherapy. MEDLINE (Ovid), Embase, Scopus, Web of Science and the Cochrane Library databases were searched until June 4, 2021, in line with the PRISMA statement. Two reviewers independently screened resulting records. Quality assessment was performed according to Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and/or Quality in Prognostic Studies (QUIPS) criteria. PET/CT response assessment was divided in immunotherapy PET/CT response criteria, conventional PET/CT response criteria, and individual Δ[18F]FDG/PET CT metrics. The main outcome measure extracted was the univariate hazard ratio (HR) for OS. Fifteen studies (n = 565) were included, with ten studies (225 NSCLC, 178 melanoma cases) reporting on PET/CT response criteria and five studies (126 NSCLC, 36 melanoma cases) on individual Δ[18F]FDG PET/CT metrics. Until 2016, conventional criteria: EORTC and PERCIST1.0 were applied; since then, several new, modified criteria emerged: imPERCIST, PERCIMT, PECRIT and iPERCIST. For both NSCLC and melanoma, univariate HRs did not show substantial differences between immunotherapy and conventional PET/CT response criteria, with overlapping confidence intervals. No individual Δ[18F]FDG PET/CT metric can yet be recommended. ΔTMTV in melanoma and ΔSUVmax in NSCLC showed the highest univariate HRs. There is insufficient evidence to decide whether the predictive value of immunotherapy PET/CT criteria is superior to conventional ones for OS, in melanoma and lung cancer treated with immunotherapy. A different research strategy is needed to reach the answer: PET/CT research should focus on directly comparing (modifications of) immunotherapy and conventional PET/CT criteria within a homogenous population with standardized PET timing, immunotherapy categories and OS definition. A consortium-based comprehensive database with individual patient data could be the solution.

Acquisition time and injected activity of 18F-fluorodeoxyglucose (18F-FDG) PET should ideally be reduced. However, this decreases the signal-to-noise ratio (SNR), which impairs the diagnostic value of these PET scans. In addition, 89Zr-antibody PET is known to have a low SNR. To improve the diagnostic value of these scans, a Convolutional Neural Network (CNN) denoising method is proposed. The aim of this study was therefore to develop CNNs to increase SNR for low-count 18F-FDG and 89Zr-antibody PET. Super-low-count, low-count and full-count 18F-FDG PET scans from 60 primary lung cancer patients and full-count 89Zr-rituximab PET scans from five patients with non-Hodgkin lymphoma were acquired. CNNs were built to capture the features and to denoise the PET scans. Additionally, Gaussian smoothing (GS) and Bilateral filtering (BF) were evaluated. The performance of the denoising approaches was assessed based on the tumour recovery coefficient (TRC), coefficient of variance (COV; level of noise), and a qualitative assessment by two nuclear medicine physicians. The CNNs had a higher TRC and comparable or lower COV to GS and BF and was also the preferred method of the two observers for both 18F-FDG and 89Zr-rituximab PET. The CNNs improved the SNR of low-count 18F-FDG and 89Zr-rituximab PET, with almost similar or better clinical performance than the full-count PET, respectively. Additionally, the CNNs showed better performance than GS and BF.