Pretreatment Positron Emission Tomography Research Articles

Development and Validation of Prognostic Models Using Radiomic Features from Pre-Treatment Positron Emission Tomography (PET) Images in Head and Neck Squamous Cell Carcinoma (HNSCC) Patients.

High-dimensional radiomics features derived from pre-treatment positron emission tomography (PET) images offer prognostic insights for patients with head and neck squamous cell carcinoma (HNSCC). Using 124 PET radiomics features and clinical variables (age, sex, stage of cancer, site of cancer) from a cohort of 232 patients, we evaluated four survival models-penalized Cox model, random forest, gradient boosted model and support vector machine-to predict all-cause mortality (ACM), locoregional recurrence/residual disease (LR) and distant metastasis (DM) probability during 36, 24 and 24 months of follow-up, respectively. We developed models with five-fold cross-validation, selected the best-performing model for each outcome based on the concordance index (C-statistic) and the integrated Brier score (IBS) and validated them in an independent cohort of 102 patients. The penalized Cox model demonstrated better performance for ACM (C-statistic = 0.70, IBS = 0.12) and DM (C-statistic = 0.70, IBS = 0.08) while the random forest model displayed better performance for LR (C-statistic = 0.76, IBS = 0.07). We conclude that the ML-based prognostic model can aid clinicians in quantifying prognosis and determining effective treatment strategies, thereby improving favorable outcomes in HNSCC patients.

Parametric Response Mapping of Co-Registered Ivim MRI and PET to Identify Radioresistant Sub-Volumes in Locally Advanced Cervical Carcinoma Undergoing CCRT

To investigate parametric response mapping (PRM) of co-registered positron emission tomography (PET) and intravoxel incoherent motion (IVIM) MRI in locally advanced cervical carcinoma patients to identify sub-volumes that may predict treatment response to adjuvant concurrent chemoradiation therapy (CCRT). Pre- and on-treatment (∼after four weeks of CCRT) diffusion weighted images (DWIs) MRI and pre-treatment PET were performed on 20 cervical cancer patients (median [range] age: 63 [41 to 85]; FIGO staging: 3 IIB, 1 IIIB, 10 IIIC1, 4 IIIC2, 2 IVA; histology: 11 squamous cell carcinoma, 4 endocervical adenocarcinoma; LN status: 4 negative, 16 positive). IVIM MRI maps were generated by Bayesian fitting of a two-compartment IVIM model to the DWIs to produce three-dimensional diffusion coefficient (D) and perfusion fraction (f). Three-dimensional IVIM D and f maps were co-registered to PET standardized uptake value (SUV) maps. Population means of PET SUV, IVIM D and f from pre-treatment scans were calculated to generate thresholds to identify low versus high metabolic (μSUV) regions, low versus high diffused (μD) regions as well as low versus high perfused (μf) regions, respectively. PRM maps were generated using voxel-wise joint histogram analysis to classify voxels within the tumor as highly metabolic and with low cellular density (SUV↑D↑), highly metabolic and with high cellular density (SUV↑D↓), metabolically inactive and with high cellular density (SUV↓D↓), or metabolically inactive and with low cellular density (SUV↓D↑) tissue based on the population mean thresholds. Similar PRM maps were generated using the joint histogram analysis with SUV and f. Summary statistics for these and other imaging parameters were calculated pre- and on-treatment. Univariate analysis was performed to determine relationships between relative change in gross tumor volume (ΔGTV) and pre-treatment imaging measurements. In tumors, on- versus pre-treatment tumor volume (p<.001) significantly decreased, while IVIM f (p = .002) and D (p = .03) significantly increased. Pre-treatment tumor volume (r = .45, p = .04) and PRM SUV↑D↓ (r = .65, p = .002) regions were positively related with ΔGTV, while pre-treatment IVIM D (r = -.64, p = .002), PRM SUV↓f↑ (r = -.52, p = .02) and PRM SUV↓D↑ (r = -.74, p<.001) regions were negatively related with ΔGTV. The latter PRM result suggests that larger regions of low cellular density (as represented by elevated D) + low metabolism result in a reduced change in tumor volume on-treatment, potentially representing a radioresistant sub-volume. PRM, generated from PET and IVIM MRI, was applied to patients with locally advanced cervical carcinoma and radioresistant sub-volumes were identified which may predict treatment response. The complementary information provided from PET and IVIM, combined using PRM, may assist in decision-making to individualize therapies, such as with image guided brachytherapy, to improve patient outcomes.

A Radiomics-Based Classifier for the Progression of Oropharyngeal Cancer Treated with Definitive Radiotherapy.

In this study, we investigated whether radiomics features from pre-treatment positron emission tomography (PET) images could be used to predict disease progression in patients with HPV-positive oropharyngeal cancer treated with definitive proton or x-ray radiotherapy. Machine learning models were built using a dataset from Mayo Clinic, Rochester, Minnesota (n = 72) and tested on a dataset from Mayo Clinic, Phoenix, Arizona (n = 22). A total of 71 clinical and radiomics features were considered. The Mann-Whitney U test was used to identify the top 2 clinical and top 20 radiomics features that were significantly different between progression and progression-free patients. Two dimensionality reduction methods were used to define two feature sets (manually filtered or machine-driven). A forward feature selection scheme was conducted on each feature set to build models of increased complexity (number of input features from 1 to 6) and evaluate model robustness and overfitting. The machine-driven features had superior performance and were less prone to overfitting compared to the manually filtered features. The four-variable Gaussian Naïve Bayes model using the 'Radiation Type' clinical feature and three machine-driven features achieved a training accuracy of 79% and testing accuracy of 77%. These results demonstrate that radiomics features can provide risk stratification beyond HPV-status to formulate individualized treatment and follow-up strategies.

Comparison of machine learning approaches for POD24 prediction based on pretreatment PET in follicular lymphoma patients (on behalf of CALYM/LYSA groups)

Introduction: Follicular Lymphoma (FL) is the second most common non-Hodgkin lymphoma in adults and is heterogeneous with 20% of poor-outcome patients relapsing/progressing within 24 months (POD24) of first treatment start (Casulo et al., JCO 2015). Early identification of those POD24 patients is critical but remains elusive. We initiated a collaboration between the academic CALYM Carnot Institute and the private company Euranova aiming at developing interpretable artificial intelligence (AI) models based on Positron Emission Tomography (PET) images to predict POD24. Methods: The dataset was based on the LYSA group RELEVANCE (RE) trial (Morshhauser et al, NEJM 2018) and on real-life (RL) datasets from two french hospitals (Dijon, Toulouse). Patients with FL diagnosis confirmation on biopsy, high tumor burden criteria (GELF >0) and PET images were enrolled in this retrospective study (Table 1). The input data, including PET images, tumor segmentation masks if available, and clinical data, are hosted on CALYM’s cloud based data lake Lymphoma Data Hub. After quality controls and data preprocessing, several POD24 predictive models based on pretreatment images were developed. A deep convolutional neural network with 3D ResNet architecture pretrained on 3D medical images and enriched with clinical data was trained on PET images with a binary cross entropy loss. A machine learning (ML) model based on the XGBoost boosting algorithm was trained on tabular radiomics features after extraction of 851 radiomics features for each tumor and features aggregation at patient’s level by using only the 3 tumors with largest volumes. Models were cross-validated on the RE cohort with leave-one-out method and tested on the RL cohorts (Figure 1). Results: The ML approach achieved more promising results than the deep learning (DL) model on the RE cohort with an AUC of 0.61 for ML vs. 0.56 for DL. Interestingly, in this ML model, SUVmax and new radiomics features, such as major axis length, came out as the most predictive features. For now the external validation of the ML model on RL cohorts is slightly more limited with an AUC of 0.51. Improvement of this result is expected owing to the ongoing enrichment of the cohort with additional external data. Finally, regarding the treatment’s impact on the model’s performance, preliminary data showed better results when training on the R-CHOP cohort only. Validation is underway, and will be presented at the meeting. Keywords: Bioinformatics, Computational and Systems Biology, Indolent non-Hodgkin lymphoma, PET-CT No conflicts of interests pertinent to the abstract.

Prognostic value of pretreatment FDG PET/CT in uterine cervical cancer according to two major histologic types: squamous cell carcinoma and adenocarcinoma.

The aim of this study was to assess the prognostic value of pretreatment Positron emission tomography / computed tomography using 18F-fluorodeoxyglucose (FDG-PET/CT) in cervical cancer according to two major histologic types. Eighty-three squamous cell carcinoma (SCC) patients and 35 adenocarcinoma (AC) patients who underwent pretreatment FDG-PET/CT were retrospectively analyzed. Maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) of the primary tumor were calculated. Kaplan-Meier analyses were used to compare correlations between each PET parameter and overall survival (OS). The prognostic values of imaging and clinical parameters were assessed using uni- and multivariable Cox proportional hazard models. SUVmax, SUVmean, and TLG were significantly higher in SCC than in AC (p<0.01 each). No significant difference in MTV was seen between the two groups (p=0.10). As for Kaplan-Meier analyses, in SCC, patients with SUVmax, SUVmean, MTV, and TLG exceeding cutoff values tended to show worse OS than patients with lower values (p=0.07, p=0.27, p<0.01, and p=0.01, respectively, for OS). On the other hand, in AC, patients with MTV and TLG exceeding cutoff values showed significantly worse PFS and OS (p<0.01 each for OS), while SUVmax and SUVmean were unrelated to OS (p=0.91 and p=0.83, respectively for OS). As for multivariable analyses, in SCC, TLG was identified as an independent prognostic factor for OS (p=0.01). In AC, MTV was identified as an independent prognostic factor for OS (p=0.02). Our preliminary data suggest that FDG-PET/CT would be useful for predicting prognosis in cervical cancer, although the clinical significance of quantitative values may differ according to histopathological type.

Pretreatment PET Metrics and Clinical Outcomes of Anal Cancer in Patients Living with and without HIV

<h3>Purpose/Objective(s)</h3> This study investigates the association between pre-treatment positron emission tomography (PET) metrics and clinical outcomes in anal squamous cell carcinoma (ASCC) patients treated with definitive radiation therapy (RT). We hypothesize that pre-treatment PET metrics may differentially predict clinical outcomes in ASCC patients without HIV infection (HIV-) and ASCC patients living with HIV (PLWH) with detectable or undetectable viral load (VL). <h3>Materials/Methods</h3> Patients treated with definitive RT for non-metastatic ASCC between 2005 - 2021 at a single institution were retrospectively identified, and clinical and demographic data, including HIV status and pretreatment VL, were tabulated. Pre-treatment PETs were imported to MIM, and semiautomatic gradient-based segmentation tool algorithms (PET_Edge) were used to calculate PET metrics, including maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG). Cox proportional hazard modeling was used to investigate the association between primary tumor PET metrics and clinical outcomes, including overall survival (OS), progression free survival (PFS), and loco-regional control (LRC) <h3>Results</h3> 141 ASCC patients were identified, 49 of whom were PLWH. 12 had detectable HIV VL. The median follow-up time was 51.8 months (IQR: 0.5-191.2 months). There were 22 loco-regional failures and 24 deaths. 3- and 5- year LRC was 85.6% and 83.3%, 3- and 5- year PFS was 75.9% and 71.6%, and 3- and 5- year OS was 89.3% and 86.6% for the entire cohort. There was no significant difference in LRC, PFS, or OS between PLWH and HIV- patients (p>0.50). PLWH with detectable VL had similar LRC and PFS but trended towards worse 5-year OS than did HIV- patients (66.3% vs 89.7%, p=0.16). MTV and TLG from primary tumors were significantly associated with LRC, PFS, and OS for all patients and in sub-group analysis for HIV-, PLWH, and PLWH with undetectable VL (p<0.05). SUVmax was significantly associated with LRC, PFS, and OS for all patients, and on sub-group analysis only for HIV- patients (p<0.05). On multivariable analysis, after adjusting for stage and Charlson Comorbidity Index, MTV split at median was significantly associated with LRC (HR 3.59 (95% CI:1.21-10.6), p=0.02) and PFS (HR 3.12 (95%CI:1.48-6.56), p=0.003), and TLG split at median was significantly associated with LRC (HR 4.36 (95%CI:1.36-14.0), p=0.01) and PFS (HR 3.13 (95%CI:1.48-6.64), p=0.003). <h3>Conclusion</h3> Patients with ASCC had similar outcomes regardless of HIV status. Advanced pre-treatment PET metrics, especially MTV and TLG, may have prognostic or risk-stratification utility in HIV- patients and undetectable PLWH with ASCC, but were not as strongly associated with clinical outcomes for PLWH with detectable VL, perhaps due to small numbers of patients with detectable VL in this cohort.

Prospective Evaluation of Interim FDG-PET Imaging during Chemoradiation for Anal SCC

<h3>Purpose/Objective(s)</h3> De-escalation of therapy for anal squamous cell carcinoma is under investigation in multiple prospective randomized trials. Imaging metrics from (F-18) fluorodeoxyglucose positron emission tomography (PET) before and during chemoradiation may serve as a biomarker to tailor treatment and aid in appropriate patient and dose selection. <h3>Materials/Methods</h3> From June 2012 to July 2021, 56 patients with anal canal cancer were enrolled in two prospective studies (30 and 26 patients, respectively) of PET prior to and during CRT after receiving ∼30 Gy. PET metrics of the primary site were calculated for the pre-treatment and interim images, including maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) based on 40% SUVmax (MTV40, TLG40) or SUV 2.5 (MTV2.5, TLG2.5) thresholds. Associations between absolute pre-treatment and interim PET metrics and freedom from local/regional recurrence (FFLR) were investigated using the Cox proportional hazards method. Local/regional recurrence was defined as primary or nodal (in-field) recurrence. No adjustment was made for multiple comparisons. <h3>Results</h3> Forty-four patients were eligible for analysis. Patients with non-squamous cell histology (adenocarcinoma, melanoma) (3 patients), recurrent anal cancer (1 patient), metastatic disease (1 patient), and incomplete studies due to treatment toxicity or patient choice (7 patients) were excluded. Median follow-up was 2.4 years. Clinical stage was T3 or T4 in 43% of patients, and 52% were node positive. Seven patients have expired and disease recurrence patterns following treatment included local/regional (5 patients) and distant disease (7 patients). On univariate analysis, age, T and N stage, duration of treatment, and HIV status did not significantly correlate with FFLR. TLG2.5 (1.05 [0.99-1.11]) was marginally associated with FFLR. No pretreatment metrics or other interim metrics were significantly associated with FFLR. Multivariate analysis was not conducted given the small number of events (N=5). <h3>Conclusion</h3> In this expanded pilot study, characteristics of PET acquired during treatment of anal canal cancer were not significantly associated with FFLR. Given the limited number of FFLR events, definitive conclusions about the utility of interim PET cannot be drawn. The correlation of various PET metrics with FFLR warrants further investigation to determine if interim PET as an imaging biomarker can be used to personalize treatment, potentially in the setting of dose de-escalation.

Could 18-FDG PET-CT Radiomic Features Predict the Locoregional Progression-Free Survival in Inoperable or Unresectable Oesophageal Cancer?

Simple SummaryAlmost 20% of patients with a locally advanced oesophageal cancer presented long-term local control after exclusive chemoradiotherapy (CRT) and could potentially avoid surgery and its morbidity and mortality. With the aim of identifying the patients that would present long-term locoregional control, we analysed in this study the potential of some pre-treatment positron-emission tomography-computed tomography (PET-CT)-based features in predicting long-term responses and local control in patients treated with definitive CRT. Our results show that radiomics allows for the identification of patients with long-term locoregional control. If confirmed on larger populations, our results could allow the identification of patients who are good responders to CRT, and who could potentially avoid surgery.Background: We evaluated the value of pre-treatment positron-emission tomography–computed tomography (PET-CT)-based radiomic features in predicting the locoregional progression-free survival (LR-PFS) of patients with inoperable or unresectable oesophageal cancer. Material and Methods: Forty-six patients were included and 230 radiomic parameters were extracted. After a principal component analysis (PCA), we identified the more robust radiomic parameters, and we used them to develop a heatmap. Finally, we correlated these radiomic features with LR-PFS. Results: The median follow-up time was 17 months. The two-year LR-PFS and PFS rates were 35.9% (95% CI: 18.9–53.3) and 21.6% (95%CI: 10.0–36.2), respectively. After the correlation analysis, we identified 55 radiomic parameters that were included in the heatmap. According to the results of the hierarchical clustering, we identified two groups of patients presenting statistically different median LR-PFSs (22.8 months vs. 9.9 months; HR = 2.64; 95% CI 0.97–7.15; p = 0.0573). We also identified two radiomic features (“F_rlm_rl_entr_per” and “F_rlm_2_5D_rl_entr”) significantly associated with LR-PFS. Patients expressing a “F_rlm_2_5D_rl_entr” of <3.3 had a better median LR- PFS (29.4 months vs. 8.2 months; p = 0.0343). Patients presenting a “F_rlm_rl_entr_per” of <4.7 had a better median LR-PFS (50.4 months vs. 9.9 months; p = 0.0132). Conclusion: We identified two radiomic signatures associated with a lower risk of locoregional relapse after CRT.

Novel Harmonization Method for Multi-Centric Radiomic Studies in Non-Small Cell Lung Cancer.

The purpose of this multi-centric work was to investigate the relationship between radiomic features extracted from pre-treatment computed tomography (CT), positron emission tomography (PET) imaging, and clinical outcomes for stereotactic body radiation therapy (SBRT) in early-stage non-small cell lung cancer (NSCLC). One-hundred and seventeen patients who received SBRT for early-stage NSCLC were retrospectively identified from seven Italian centers. The tumor was identified on pre-treatment free-breathing CT and PET images, from which we extracted 3004 quantitative radiomic features. The primary outcome was 24-month progression-free-survival (PFS) based on cancer recurrence (local/non-local) following SBRT. A harmonization technique was proposed for CT features considering lesion and contralateral healthy lung tissues using the LASSO algorithm as a feature selector. Models with harmonized CT features (B models) demonstrated better performances compared to the ones using only original CT features (C models). A linear support vector machine (SVM) with harmonized CT and PET features (A1 model) showed an area under the curve (AUC) of 0.77 (0.63–0.85) for predicting the primary outcome in an external validation cohort. The addition of clinical features did not enhance the model performance. This study provided the basis for validating our novel CT data harmonization strategy, involving delta radiomics. The harmonized radiomic models demonstrated the capability to properly predict patient prognosis.

Comparison of lung cancer aggressiveness in patients who never smoked compared to those who smoked

ObjectivesTo determine whether radiographic measures of tumor aggressiveness differ by smoking status. Materials and MethodsAll patients diagnosed with non-small-cell lung cancer(NSCLC) ≤ 30 mm in maximum diameter, without clinical evidence of metastasis who had both pre-treatment PET scans and two CT scans at least 90 days apart in a prospective cohort, the Initiative for Early Lung Cancer Research on Treatment(IELCART) at Mount Sinai between 2016 and 2020 were identified. Comparison of two measures of tumor aggressiveness, positron emission tomography(PET) SUVmax and tumor volume doubling time(VDT) by smoking status was performed. ResultsOf 417 patients identified, 158 patients had pre-treatment PET scans and at least two CT scans available. The two measures of tumor aggressiveness, SUVmax and VDT values were significantly different between patients who had never smoked and those who smoked: patients who never smoked had lower median SUVmax[2.5(IQR: 1.1–4.8) vs. 4.2(IQR:2.1–9.2),p = 0.002] and longer median VDT[(372.6 days vs. 225.6 days,p = 0.001)] compared to those who smoked. Using multivariable analyses, when adjusting for age and sex alone, SUVmax(p = 0.004) and VDT(p = 0.0001) remained significantly different by smoking status. The final multivariable analysis, adjusted for all three co-variates(sex, age and tumor histology) showed no significant difference in SUVmax and VDT by smoking status [SUVmax(p = 0.25) and VDT(p = 0.06)]. ConclusionSmoking history does not influence VDT or PET SUVmax measures of lung cancer aggressiveness.

Deep learning based time-to-event analysis with PET, CT and joint PET/CT for head and neck cancer prognosis

ObjectivesRecent studies have shown that deep learning based on pre-treatment positron emission tomography (PET) or computed tomography (CT) is promising for distant metastasis (DM) and overall survival (OS) prognosis in head and neck cancer (HNC). However, lesion segmentation is typically required, resulting in a predictive power susceptible to variations in primary and lymph node gross tumor volume (GTV) segmentation. This study aimed at achieving prognosis without GTV segmentation, and extending single modality prognosis to joint PET/CT to allow investigating the predictive performance of combined- compared to single-modality inputs. MethodsWe employed a 3D-Resnet combined with a time-to-event outcome model to incorporate censoring information. We focused on the prognosis of DM and OS for HNC patients. For each clinical endpoint, five models with PET and/or CT images as input were compared: PET-GTV, PET-only, CT-GTV, CT-only, and PET/CT-GTV models, where -GTV indicates that the corresponding images were masked using the GTV contour. Publicly available delineated CT and PET scans from 4 different Canadian hospitals (293) and the MAASTRO clinic (74) were used for training by 3-fold cross-validation (CV). For independent testing, we used 110 patients from a collaborating institution. The predictive performance was evaluated via Harrell's Concordance Index (HCI) and Kaplan-Meier curves. ResultsIn a 5-year time-to-event analysis, all models could produce CV HCIs with median values around 0.8 for DM and 0.7 for OS. The best performance was obtained with the PET-only model, achieving a median testing HCI of 0.82 for DM and 0.69 for OS. Compared with the PET/CT-GTV model, the PET-only still had advantages of up to 0.07 in terms of testing HCI. The Kaplan-Meier curves and corresponding log-rank test results also demonstrated significant stratification capability of our models for the testing cohort. ConclusionDeep learning-based DM and OS time-to-event models showed predictive capability and could provide indications for personalized RT. The best predictive performance achieved by the PET-only model suggested GTV segmentation might be less relevant for PET-based prognosis.

Negative Association of Smoking History With Clinically Manifest Cardiac Sarcoidosis: A Case-Control Study

BackgroundThe etiology of sarcoidosis is still unknown and is likely related to a genetic susceptibility to unidentified environmental trigger(s). Our group and others have extensively described a specific phenotype of primarily Caucasian patients who have clinically manifest cardiac sarcoidosis (CS). In this study, we sought to explore whether smoking is associated with this specific phenotype of sarcoidosis. MethodsWe performed a case-control study. Cases with clinically manifest CS were prospectively enrolled in the Cardiac Sarcoidosis Multi-Center Prospective Cohort Study (CHASM-CS registry; NCT01477359) and answered a standardized smoking history questionnaire. Cases were matched 10:1 with controls from the Ontario Health Study. Pretreatment positron emission tomography scans with 18F-fluorodeoxyglucose were compared for smokers vs nonsmokers. ResultsEighty-seven cases met the inclusion criteria. A total of 82 of 87 (94.3%) answered the questionnaire and were matched with 820 controls. A clear negative association of sarcoidosis and smoking was found, with 23 of 82 CS cases (28.0%) being current or ex-smokers, vs 392 of 820 controls (47.8%; P = 0.0006). CS patients with a smoking history had significantly less lifetime consumption (8.31 ± 9.20 pack-years) than the controls (15.34 ± 10.84 pack-years; P < 0.003). On 18F-fluorodeoxyglucose-positron emission tomography scan, the mean standardized uptake value of the left ventricle was 4.2 ± 8.98 in lifetime nonsmokers vs 2.89 ± 2.07 in patients with a smoking history (P < 0.0001). ConclusionsWe describe a strong negative association between smoking history and clinically manifest CS. Nonsmokers had more severe myocardial inflammation (greater mean standardized uptake value of the left ventricle) than did patients with a smoking history. Further research is needed to understand these associations and whether they have therapeutic potential.

T Stage and Pretreatment Standardized Uptake Values Predict Tumor Recurrence With 5-Fraction SABR in Early-Stage Non-Small Cell Lung Cancer

PurposeFive-fraction stereotactic ablative radiotherapy (SABR) regimens are frequently used to treat centrally located early-stage non-small cell lung cancer or disease in the proximity of the chest wall as a means of optimizing tumor control and reducing treatment toxicity. However, increasing these SABR regimens to 5 fractions may reduce tumor control outcomes. We sought to identify the clinical parameters predictive of treatment failures with these 5-fraction courses. MethodsNinety patients with T1-2 non-small cell lung cancer were treated with 50 or 60 Gy in 5 fractions. Failure over time was modeled using cumulative incidences of local, regional, or distant failure, with death as a competing risk. Cox proportional hazards analysis for incidences of failure was performed to control for patient variables. ResultsOf 90 patients, 24 of 53 patients with T1 tumors and 19 of 37 patients with T2 tumors received 50 Gy SABR, and the other 47 patients received 60 Gy. Two-year overall survival and progression-free survival for the whole cohort were 75.8% and 59.3%, respectively. Total SABR dose (50 vs 60 Gy) did not influence survival nor failure rates at 2 and 5 years. Within 2 years of treatment, 7.8% of all patients developed local failure. For all patient and tumor characteristics evaluated, only T stage and pretreatment positron emission tomography standardized uptake values served as predictors of local, regional, and distant failure at 2 and 5 years posttreatment on univariate and multivariable analysis. ConclusionsFive-fraction SABR provides excellent in-field control. T2 and high fluorodeoxyglucose uptake tumors have increased failure rates, suggesting the potential need for adjuvant therapies, which are being assessed in randomized phase 3 trials.

Correlating Quantitative Para-Aortic Lymph Node Computed Tomography Parameters With Fluorodeoxyglucose Positron Emission Tomography for Cervical Cancer Staging: Possible Solution for Resource Constrained Countries.

The aim of the study was to determine the most accurate quantitative morphological parameters on computed tomography (CT) that correlate with fluorodeoxyglucose (FDG)-avid para-aortic nodes (PANs) in patients with cervical cancer. A single-institution retrospective evaluation was performed of women with cervical cancer who underwent pretreatment positron emission tomography (PET)/CT and radiotherapy therapy planning CT between 2009 and 2020. A node-by-node correlation between pretreatment CT and PET/CT was performed for the reference standard of FDG avidity for short- and long-axis diameters, volume, and long-/short-axis ratio (L/S). The FDG-avid PANs were defined as PET-positive and non-FDG-avid PANs from patients without PET-determined PAN metastasis were defined as PET negative. Area under the receiver operator curve was calculated to access diagnostic accuracy of the different quantitative parameters. A total of 94 women (mean age ± standard deviation, 52 ± 13 years) with cervical cancer were included. Forty-seven patients had PET-positive PANs (181 PET-positive PANs) and 47 patients had no PET-positive PANs (141 PET-negative PANs). The area under the receiver operator curve for volume (0.945) was greater ( P < 0.001) than that of short axis (0.895), long axis (0.885), and L/S (0.583). At a specificity set point of 0.90 (127/141 PANs), the cutoff for volume was 0.443 cm 3 or greater (0.85 sensitivity [154/181 PANs]; 95% confidence interval, 0.83-0.93) and for short-axis diameter was 5.9 mm or greater (0.75 sensitivity [135/181 PANs]; 95% confidence interval, 0.68-0.81). Para-aortic lymph node volume demonstrated that improved node-by-node correlation between CT and PET/CT compared with short-axis diameter, long-axis diameter, and L/S and is an alternative to improve detection of PAN suspicious of metastatic diseases in locations without access to PET/CT.

Pretreatment Positron Emission Tomography with 18F-Fluorodeoxyglucose May Be a Useful New Predictor of Early Progressive Disease following Atezolizumab plus Bevacizumab in Patients with Unresectable Hepatocellular Carcinoma

Background and Aims: The aim of this study was to identify the utility of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG-PET/CT) as a predictor of early progressive disease (e-PD) in patients with hepatocellular carcinoma (HCC) treated with atezolizumab plus bevacizumab (Atezo/Bev). Methods: Twenty consecutive patients with measurable intrahepatic target nodules who received Atezo/Bev treatment were reviewed. The oncological aggressiveness of tumors estimated by ¹⁸F-FDG-PET/CT was analyzed using the rate of e-PD within 12 weeks and early progression-free survival (e-PFS) and overall survival (OS). Multivariate analysis was used to identify potential confounders for PD during Atezo/Bev therapy. Results: Using the Response Evaluation Criteria in Solid Tumors version 1.1, a tumor-to-normal liver ratio (TLR) ≥2, indicating higher oncological aggressiveness in HCCs, was associated with lower objective response rates compared with TLR values <2 (18% vs. 33%, respectively). Moreover, TLR values ≥2 were significantly associated with higher e-PD rates compared with TLR values <2 (64% vs. 11%, respectively) and worse e-PFS (p = 0.021). In multivariate analysis, TLR ≥2 showed marginal significance as a predictor of e-PD (p = 0.053), and utility as a predictor for worse e-PFS (hazard ratio, 7.153; 95% confidence interval, 1.258–40.689; p = 0.027). In contrast, no significant differences in OS with/without e-PD were observed during the treatment course. In this study, 8 patients experienced e-PD and almost 40% of patients experienced acceptable disease control following subsequent lenvatinib treatment. Conclusion: Pretreatment ¹⁸F-FDG-PET/CT may be a useful new predictor of e-PD and may enable early decision-making based on early treatment changes following Atezo/Bev treatment of HCC.

A positron emission tomography radiomic signature for distant metastases risk in oropharyngeal cancer patients treated with definitive chemoradiotherapy.

Disease recurrence and distant metastases (DM) are major concerns for oropharyngeal cancer (OPC) patients receiving definitive chemo-radiotherapy. Here, we investigated whether pre-treatment primary tumor positron emission tomography (PET) features could predict progression-free survival (PFS) or DM. Primary tumors were delineated on pre-treatment PET scans for patients treated between 2005 and 2018 using gradient-based segmentation. Radiomic image features were extracted, along with SUV metrics. Features with zero variance and strong correlation to tumor volume, stage, p16 status, age or smoking were excluded. A random forest model was used to identify features associated with PFS. Kaplan-Meier methods, Cox regression and logistic regression with receiver operating characteristics (ROC) and 5-fold cross-validated areas-under-the-curve (CV-AUCs) were used. A total of 114 patients were included. With median follow-up 40months (range: 3-138months), 14 patients had local recurrence, 21 had DM and 38 died. Two-year actuarial local control, distant control, PFS and overall survival was 89%, 84%, 70% and 84%, respectively. The wavelet_LHL_GLDZM_LILDE feature slightly improved PFS prediction compared to clinical features alone (CV-AUC 0.73 vs. 0.71). Age>65years (HR=2.64 (95%CI: 1.36-5.2), p=0.004) and p16-negative disease (HR=3.38 (95%CI: 1.72-6.66), p<0.001) were associated with poor PFS. A binary radiomic classifier strongly predicted DM with multivariable HR=3.27 (95%CI: 1.15-9.31), p=0.027, specifically for patients with p16-negative disease with 2-year DM-free survival 83% for low-risk vs. 38% for high-risk patients (p=0.004). A radiomics signature strongly associated with DM risk could provide a tool for improved risk stratification, potentially adding adjuvant immunotherapy for high-risk patients.

Texture analysis of PET images for predicting response to induction chemotherapy for oral squamous cell carcinoma

We evaluated whether texture analysis of positron emission tomography (PET) scans could predict the response to induction chemotherapy (ICT) in patients with oral squamous cell carcinoma (OSCC). Our retrospective cohort study included 21 patients with OSCC who underwent ICT. We extracted 31 textural indices from pretreatment PET scans and performed receiver operating characteristic curve (ROC) analysis to evaluate these indices’ efficacy in predicting ICT response. The area under the ROC curve was statistically significant for one texture index: short-zone emphasis (SZE; p = 0.041).

Pretreatment Positron Emission Tomography with 18F-Fluorodeoxyglucose May Be a Useful New Predictor of Overall Prognosis Following Lenvatinib Treatment

Background and Aim: The aim of this study was to identify the utility of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG-PET/CT) as a predictor of overall prognosis in patients with hepatocellular carcinoma treated with lenvatinib. Methods: Forty-eight consecutive patients who received lenvatinib treatment were reviewed. The oncological aggressiveness of tumors estimated using ¹⁸F-FDG-PET/CT was investigated by the analysis of progression-free survival (PFS), post-progression survival (PPS), and overall survival (OS). Multivariate analysis was used to identify potential confounders for OS during lenvatinib therapy. Results: Using the Modified Response Evaluation Criteria in Solid Tumors, a tumor-to-normal liver ratio (TLR) ≥2, indicating higher oncological aggressiveness in HCCs, was associated with a better objective response to lenvatinib than a TLR <2 (78 vs. 62%), resulting in a similar PFS (p = 0.751). Because of a significantly worse PPS, OS with a TLR ≥2 was poor compared to a TLR < 2 (p = 0.012). Multivariate analysis confirmed that a TLR ≥ 2 was associated with poor OS (hazard ratio, 2.709; 95% CI, 1.140–6.436; p = 0.024). Analysis of 24 patients who received a repeat ¹⁸F-FDG-PET/CT showed that daily changes expressed as ΔTLR × 10³/day over the treatment course tended to be different among the types of subsequent treatment. A R0 resection and lenvatinib-TACE sequential therapy provided good disease control (median, −4.593 and −0.024, respectively) compared with other treatments (median, 5.278) (p = 0.075). Conclusion: Lenvatinib has acceptable disease control regardless of estimated tumor differentiation. A high TLR (≥2) is a poor prognostic factor of OS following lenvatinib treatment, while ΔTLR × 10³/day provides useful information of disease control status.

Pretreatment CT and PET radiomics predicting rectal cancer patients in response to neoadjuvant chemoradiotherapy.

The purpose of this study was to characterize pre-treatment non-contrast computed tomography (CT) and 18F-fluorodeoxyglucose positron emission tomography (PET) based radiomics signatures predictive of pathological response and clinical outcomes in rectal cancer patients treated with neoadjuvant chemoradiotherapy (NACR T). An exploratory analysis was performed using pre-treatment non-contrast CT and PET imaging dataset. The association of tumor regression grade (TRG) and neoadjuvant rectal (NAR) score with pre-treatment CT and PET features was assessed using machine learning algorithms. Three separate predictive models were built for composite features from CT + PET. The patterns of pathological response were TRG 0 (n = 13; 19.7%), 1 (n = 34; 51.5%), 2 (n = 16; 24.2%), and 3 (n = 3; 4.5%). There were 20 (30.3%) patients with low, 22 (33.3%) with intermediate and 24 (36.4%) with high NAR scores. Three separate predictive models were built for composite features from CT + PET and analyzed separately for clinical endpoints. Composite features with α = 0.2 resulted in the best predictive power using logistic regression. For pathological response prediction, the signature resulted in 88.1% accuracy in predicting TRG 0 vs. TRG 1-3; 91% accuracy in predicting TRG 0-1 vs. TRG 2-3. For the surrogate of DFS and OS, it resulted in 67.7% accuracy in predicting low vs. intermediate vs. high NAR scores. The pre-treatment composite radiomics signatures were highly predictive of pathological response in rectal cancer treated with NACR T. A larger cohort is warranted for further validation.

Differentiating gastric cancer and gastric lymphoma using texture analysis (TA) of positron emission tomography (PET).

Background:Texture analysis (TA) can quantify intra-tumor heterogeneity using standard medical images. The present study aimed to assess the application of positron emission tomography (PET) TA in the differential diagnosis of gastric cancer and gastric lymphoma.Methods:The pre-treatment PET images of 79 patients (45 gastric cancer, 34 gastric lymphoma) between January 2013 and February 2018 were retrospectively reviewed. Standard uptake values (SUVs), first-order texture features, and second-order texture features of the grey-level co-occurrence matrix (GLCM) were analyzed. The differences in features among different groups were analyzed by the two-way Mann-Whitney test, and receiver operating characteristic (ROC) analysis was used to estimate the diagnostic efficacy.Results:InertiaGLCM was significantly lower in gastric cancer than that in gastric lymphoma (4975.61 vs. 11,425.30, z = −3.238, P = 0.001), and it was found to be the most discriminating texture feature in differentiating gastric lymphoma and gastric cancer. The area under the curve (AUC) of inertiaGLCM was higher than the AUCs of SUVmax and SUVmean (0.714 vs. 0.649 and 0.666, respectively). SUVmax and SUVmean were significantly lower in low-grade gastric lymphoma than those in high grade gastric lymphoma (3.30 vs. 11.80, 2.40 vs. 7.50, z = −2.792 and −3.007, P = 0.005 and 0.003, respectively). SUVs and first-order grey-level intensity features were not significantly different between low-grade gastric lymphoma and gastric cancer. EntropyGLCM12 was significantly lower in low-grade gastric lymphoma than that in gastric cancer (6.95 vs. 9.14, z = −2.542, P = 0.011) and had an AUC of 0.770 in the ROC analysis of differentiating low-grade gastric lymphoma and gastric cancer.Conclusions:InertiaGLCM and entropyGLCM were the most discriminating features in differentiating gastric lymphoma from gastric cancer and low-grade gastric lymphoma from gastric cancer, respectively. PET TA can improve the differential diagnosis of gastric neoplasms, especially in tumors with similar degrees of fluorodeoxyglucose uptake.