Intratumoral Heterogeneity of Pretreatment 18F-FDG PET Images Predict Disease Progression in Patients With Nasal Type Extranodal Natural Killer/T-cell Lymphoma

Intratumoral metabolic heterogeneity by 18F-FDG PET/CT to predict prognosis for patients with thymic epithelial tumors

BACKGROUND

The aim of the present study was to evaluate the impact of intratumoral metabolic heterogeneity and quantitative 18F-FDG PET/CT imaging parameters in predicting patient outcomes in thymic epithelial tumors (TETs).

METHODS

This retrospective study included 100 patients diagnosed with TETs who underwent pretreatment 18F-FDG PET/CT. The maximum and mean standardized uptake values (SUVmax and SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) on PET/CT were measured. Heterogeneity index-1 (HI-1; standard deviation [SD] divided by SUVmean) and heterogeneity index-2 (HI-2; linear regression slopes of the MTV according with different SUV thresholds), were evaluated as heterogeneity indices. Associations between these parameters and patient survival outcomes were analyzed.

RESULTS

The univariate analysis showed that Masaoka stage, TNM stage, WHO classification, SUVmax, SUVmean, TLG, and HI-1 were significant prognostic factors for progression-free survival (PFS), while MTV, HI-2, age, gender, presence of myasthenia gravis, and maximum tumor diameter were not. Subsequently, multivariate analyses showed that HI-1 (p < 0.001) and TNM stage (p = 0.002) were independent prognostic factors for PFS. For the overall survival analysis, TNM stage, WHO classification, SUVmax, and HI-1 were significant prognostic factors in the univariate analysis, while TNM stage remained an independent prognostic factor in multivariate analyses (p = 0.024). The Kaplan Meier survival analyses showed worse prognoses for patients with TNM stages III and IV and HI-1 ≥ 0.16 compared to those with stages I and II and HI-1 < 0.16 (log-rank p < 0.001).

CONCLUSION

HI-1 and TNM stage were independent prognostic factors for progression-free survival in TETs. HI-1 generated from baseline 18F-FDG PET/CT might be promising to identify patients with poor prognosis.

Prognostic Value of 18F-FDG PET/CT Radiomics in Extranodal Nasal-Type NK/T Cell Lymphoma

OBJECTIVE

To investigate the prognostic utility of radiomics features extracted from 18F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL).

MATERIALS AND METHODS

A total of 126 adults with ENKTCL who underwent 18F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3. Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient's radiomics scores (RadPFS and RadOS). Kaplan-Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell's C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve.

RESULTS

Kaplan-Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell's C-index: 0.805 in the validation cohort) and OS (Harrell's C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance.

CONCLUSION

The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.

Extranodal NK/T-cell lymphoma with localized relapse in bone marrow of lower leg detected using PET-CT

Extranodal natural killer (NK)/T-cell lymphoma (ENKTL) is a rare subtype of non-Hodgkin lymphoma (NHL) with poor prognosis, particularly in relapsed or refractory patients. Thus, timely detection of relapse and appropriate disease management are crucial. We present two patients with ENKTL, wherein positron emission tomography-computed tomography (PET-CT) with total-body coverage after induction therapy, detected newly relapsed regions in the bone marrow of the lower leg prior to progression. Case 1: A 47-year-old woman with nasal obstruction, showing 18F-fluoro-deoxyglucose (FDG) uptake in the nasal cavity (Lugano stage IE). After induction therapy (RT-2/3 DeVIC), PET-CT revealed abnormal uptake only in the right fibula. Case 2: A 68-year-old man with a skin nodule/ulcer and an enlarged right inguinal lymph node was diagnosed with advanced ENKTL. A PET-CT scan revealed abnormal uptake in the subcutaneous mass of the right medial thigh, lymph nodes, and descending colon (Lugano stage IV). After induction therapy, PET-CT revealed new abnormal uptake only in the left tibia. In both patients, CT-guided biopsy confirmed ENKTL recurrence. Moreover, PET-CT with whole-body coverage was useful for the timely assessment of relapse and detection of asymptomatic bone involvement. This approach allowed for modifications to treatment strategies in certain patients.

Value of pre-treatment 18F-FDG PET/CT radiomics in predicting the prognosis of stage III-IV colorectal cancer

Background and purpose

To investigate the value of radiomics features extracted from pre-treatment ¹⁸F-FDG PET/CT in predicting the outcomes of stage III-IV colorectal cancer (CRC), which may assist in clinical management strategies and precise treatment of stage III-IV CRC.

Materials and methods

124 patients with pathologically confirmed stage III-IV CRC who underwent pre-treatment ¹⁸F-FDG PET/CT scans were enrolled in this study. The least absolute shrinkage and selection operator Cox regression (LASSO-Cox) was used to select radiomics features, and the radiomics scores (Rad-scores) were calculated to build radiomics models. The performance of radiomics models was represented by the concordance index (C-index) and compared with clinical models and complex model. The bootstrap resampling method was used to create validation sets. Additionally, nomograms were developed based on complex models.

Results

The C-indices of the radiomics model for predicting PFS and OS were 0.712 (95%CI: 0.680-0.744) and 0.758 (0.728-0.789), respectively. In the clinical model, these values were 0.690 (0.664-0.0.717) and 0.738 (0.709-0.767), respectively. However, in the complex model were 0.734 (0.705-0.762) and 0.780 (0.754-0.807), respectively. The Kaplan-Meier curves demonstrated that the radiomics model could effectively separate patients with stage III-IV stage CRC into high- and low-risk groups (p < 0.001). Multivariate Cox regression analysis confirmed the independent prognostic value of Rad-scores.

Conclusion

Pre-treatment ¹⁸F-FDG PET/CT radiomics features can stratify the risk of patients with stage III-IV CRC and accurately predict their outcomes. These findings could be clinically valuable for precision treatment and management decisions in stage III-IV CRC.

Application of 18 F-fluorodeoxyglucose PET/CT radiomic features and machine learning to predict early recurrence of non-small cell lung cancer after curative-intent therapy

OBJECTIVE

To predict the recurrence of non-small cell lung cancer (NSCLC) within 2 years after curative-intent treatment using a machine-learning approach with PET/CT-based radiomics.

PATIENTS AND METHODS

A total of 77 NSCLC patients who underwent pretreatment 18 F-fluorodeoxyglucose PET/CT were retrospectively analyzed. Five clinical features (age, sex, tumor stage, tumor histology, and smoking status) and 48 radiomic features extracted from primary tumors on PET were used for binary classifications. These were ranked, and a subset of useful features was selected based on Gini coefficient scores in terms of associations with relapsed status. Areas under the receiver operating characteristics curves (AUC) were yielded by six machine-learning algorithms (support vector machine, random forest, neural network, naive Bayes, logistic regression, and gradient boosting). Model performances were compared and validated via random sampling.

RESULTS

A PET/CT-based radiomic model was developed and validated for predicting the recurrence of NSCLC during the first 2 years after curation. The most important features were SD and variance of standardized uptake value, followed by low-intensity short-zone emphasis and high-intensity zone emphasis. The naive Bayes model with the 15 best-ranked features displayed the best performance (AUC: 0.816). Prediction models using the five best PET-derived features outperformed those using five clinical variables.

CONCLUSION

The machine learning model using PET-derived radiomic features showed good performance for predicting the recurrence of NSCLC during the first 2 years after a curative intent therapy. PET/CT-based radiomic features may help clinicians improve the risk stratification of relapsed NSCLC.

Prognostic Value of Radiomic Features of 18F-FDG PET/CT in Patients With B-Cell Lymphoma Treated With CD19/CD22 Dual-Targeted Chimeric Antigen Receptor T Cells

Objective

In the present study, we aimed to evaluate the prognostic value of PET/CT-derived radiomic features for patients with B-cell lymphoma (BCL), who were treated with CD19/CD22 dual-targeted chimeric antigen receptor (CAR) T cells. Moreover, we explored the relationship between baseline radiomic features and the occurrence probability of cytokine release syndrome (CRS).

Methods

A total of 24 BCL patients who received 18F-FDG PET/CT before CAR T-cell infusion were enrolled in the present study. Radiomic features from PET and CT images were extracted using LIFEx software, and the least absolute shrinkage and selection operator (LASSO) regression was used to select the most useful predictive features of progression-free survival (PFS) and overall survival (OS). Receiver operating characteristic curves, Cox proportional hazards model, and Kaplan-Meier curves were conducted to assess the potential prognostic value.

Results

Contrast extracted from neighbourhood grey-level different matrix (NGLDM) was an independent predictor of PFS (HR = 15.16, p = 0.023). MYC and BCL2 double-expressor (DE) was of prognostic significance for PFS (HR = 7.02, p = 0.047) and OS (HR = 10.37, p = 0.041). The combination of NGLDM_ContrastPET and DE yielded three risk groups with zero (n = 7), one (n = 11), or two (n = 6) factors (p &lt; 0.0001 and p = 0.0004, for PFS and OS), respectively. The PFS was 85.7%, 63.6%, and 0%, respectively, and the OS was 100%, 90.9%, and 16.7%, respectively. Moreover, there was no significant association between PET/CT variables and CRS.

Conclusions

In conclusion, radiomic features extracted from baseline 18F-FDG PET/CT images in combination with genomic factors could predict the survival outcomes of BCL patients receiving CAR T-cell therapy.

Role of Radiomics-Based Baseline PET/CT Imaging in Lymphoma: Diagnosis, Prognosis, and Response Assessment

Radiomic analysis provides information on the underlying tumour heterogeneity in lymphoma, reflecting the real-time evolution of malignancy. 2-Deoxy-2-[¹⁸F] fluoro-D-glucose positron emission tomography ([¹⁸F] FDG PET/CT) imaging is recommended before, during, and at the end of treatment for almost all lymphoma patients. This methodology offers high specificity and sensitivity, which can aid in accurate staging and assist in prompt treatment. Pretreatment [¹⁸F] FDG PET/CT-based radiomics facilitates improved diagnostic ability, guides individual treatment regimens, and boosts outcome prognosis based on heterogeneity as well as the biological, pathological, and metabolic status of the lymphoma. This technique has attracted considerable attention given its numerous applications in medicine. In the current review, we will briefly describe the basic radiomics workflow and types of radiomic features. Details of current applications of baseline [¹⁸F] FDG PET/CT-based radiomics in lymphoma will be discussed, such as differential diagnosis from other primary malignancies, diagnosis of bone marrow involvement, and response and prognostic prediction. We will also describe how this technique provides a unique noninvasive platform to assess tumour heterogeneity. Newly emerging PET radiotracers and multimodality technology will improve diagnostic specificity and further clarify tumor biology and even genetic variations in lymphoma, potentially promoting the development of precision medicine.

Radiomic Features of 18F-FDG PET in Hodgkin Lymphoma Are Predictive of Outcomes

Purpose

In the present study, we aimed to investigate whether the radiomic features of baseline ¹⁸F-FDG PET can predict the prognosis of Hodgkin lymphoma (HL).

Methods

A total 65 HL patients (training cohort: n = 49; validation cohort: n = 16) were retrospectively enrolled in the present study. A total of 47 radiomic features were extracted from pretreatment PET images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the most useful prognostic features in the training cohort. The distance between the two lesions that were the furthest apart (D_max) was recorded. The receiver operating characteristic (ROC) curve, Kaplan–Meier method, and Cox proportional hazards model were used to assess the prognostic factors.

Results

Long-zone high gray-level emphasis extracted from a gray-level zone-length matrix (LZHGE_GLZLM) (HR = 9.007; p=0.044) and Dmax (HR = 3.641; p=0.048) were independently correlated with 2-year progression-free survival (PFS). A prognostic stratification model was established based on both risk predictors, which could distinguish three risk categories for PFS (p=0.0002). The 2-year PFS was 100.0%, 64.7%, and 33.3%, respectively.

Conclusions

LZHGE_GLZLM and Dmax were independent prognostic factors for survival outcomes. Besides, we proposed a prognostic stratification model that could further improve the risk stratification of HL patients.

Glucose Metabolism Reprogramming of Primary Tumor and the Liver Is Associated With Disease-Free Survival in Patients With Early NSCLC

Purpose

Tumor promote disease progression by reprogramming their metabolism and that of distal organs, so it is of great clinical significance to study the changes in glucose metabolism at different tumor stages and their effect on glucose metabolism in other organs.

Methods

A retrospective single-centre study was conducted on 253 NSCLC (non-small cell lung cancer) patients with negative lymph nodes and no distant metastasis. According to the AJCC criteria, the patients were divided into different groups based on tumor size: stage IA, less than 3 cm (group 1, n = 121); stage IB, greater than 3-4 cm (group 2, n = 64); stage IIA, greater than 4-5 cm (group 3, n = 36); and stage IIB, greater than 5-7 cm (group 4, n = 32). All of the patients underwent baseline ¹⁸F-FDG PET/CT scans, and the primary lesion SUVmax (maximum standardized uptake value), liver SUVmean (mean standardized uptake value), spleen SUVmean, TLR (Tumor-to-liver SUV ratio) and TSR (Tumor-to-spleen SUV ratio) were included in the study, combined with clinical examination indicators to evaluate DFS (disease free survival).

Results

In NSCLC patients, with the increase in the maximum diameter of the tumor, the SUVmax of the primary lesion gradually increased, and the SUVmean of the liver gradually decreased. The primary lesion SUVmax, liver SUVmean, TLR and TSR were related to disease recurrence or death. The best predictive parameters were different when the tumor size differed. SUVmax had the highest efficiency when the tumor size was less than 4 cm (AUC:0.707 (95% CI, 0.430-0.984) tumor size < 3 cm), (AUC:0.726 (95% CI, 0.539-0.912) tumor size 3-4 cm), liver SUVmean had the highest efficiency when the tumor size was 4-5 cm (AUC:0.712 (95% CI, 0.535-0.889)), and TLR had the highest efficiency when the tumor size was 5-7 cm [AUC:0.925 (95%CI, 0.820-1.000)].

Conclusions

In patients with early NSCLC, glucose metabolism reprogramming occurs in the primary lesion and liver. With the increase in tumor size, different metabolic parameters should be selected to evaluate the prognosis of patients.

Assessment of the prognostic value of interim fluorodeoxyglucose positron emission tomography/computed tomography in nasal-type extranodal natural killer/T-cell lymphoma

Background

The prognostic value of interim positron emission tomography/computed tomography (PET/CT) for nasal-type extranodal natural killer/T-cell lymphoma (ENKTL) is controversial. We evaluated the prognostic value of interim PET/CT in ENKTL patients to facilitate risk stratification and guide clinical treatment.

Methods

Patients with ENKTL who received first-line chemotherapy based on L-asparaginase/pegaspargase with/without involved-field radiotherapy were recruited for this study. Pretreatment and interim PET/CT evaluations were performed. Interim PET/CT was evaluated via the maximum standardized uptake value (SUVmax) and the Deauville 5-point scale (DS); and the capacity to predict progression-free survival (PFS) and overall survival (OS) was evaluated. Receiver operating characteristic (ROC) curves were used to determine the optimal SUVmax cutoff. Fisher's exact test was used to analyze relationships between interim PET/CT results and clinical characteristics. Univariate and multivariate analyses were performed to examine the independent effects of interim PET/CT. The Cochran-Mantel-Haenszel test was used to assess the prognostic value of interim PET/CT at different timepoints.

Results

Overall, 129 ENKTL patients were enrolled. The optimal interim PET/CT SUVmax cut-off was 4.95. The median follow-up was 34 [2-90] months, in the low SUVmax group (≤4.95), the 2-year PFS and OS rates were 76.3% and 88.0%, respectively; in the high SUVmax group (>4.95), the PFS and OS rates were 15.6% and 44.5%, respectively. Likewise, for the DS 1-3 group, the PFS and OS rates were 78.9% and 91.2%, respectively; and in the DS 4 or 5 group, the rates of PFS and OS were 49.7% and 69.0%, respectively. In univariate analysis, interim PET/CT evaluation based on SUVmax and DS scores were both PFS and OS predictors. In multivariate analysis, SUVmax was independently significantly associated with PFS (P<0.001) and OS (P=0.002), and DS was independently significantly associated with PFS (P=0.004) but not OS (P=0.204). In the Cochran-Mantel-Haenszel testing, the SUVmax and DS were significantly associated with PFS and OS after adjustments for the interim PET/CT timing.

Conclusions

Interim PET/CT was of prognostic value concerning ENKTL. The SUVmax is an independent prognostic indicator of PFS and OS, while the DS is an independent prognostic indicator of PFS but not OS. The SUVmax is of greater prognostic value than DS.

A composite single-nucleotide polymorphism prediction signature for extranodal natural killer/T-cell lymphoma

Current prognostic scoring systems based on clinicopathologic variables are inadequate in predicting the survival and treatment response of extranodal natural killer/T-cell lymphoma (ENKTL) patients undergoing non-anthracyline-based treatment. We aimed to construct a classifier based on single-nucleotide polymorphisms (SNPs) for improving predictive accuracy and guiding clinical decision-making. The data of 722 patients with ENKTL from international multicenters were analyzed. A 7-SNP-based classifier was constructed using LASSO Cox regression in the training cohort (n=336) and further validated in the internal testing (n=144) and two external validation cohorts (n=142; n=100). The 7-SNP-based classifier showed good prognostic predictive efficacy in the training cohort and the three validation cohorts. Patients with high and low risk scores calculated by the classifier exhibited significantly different progression-free survival (PFS) and overall survival (OS) (all p<0.001). The 7-SNP-based classifier was further proved to be an independent prognostic factor by multivariate analysis, and its predictive accuracy was significantly better than clinicopathological risk variables. The application of the 7-SNP-based classifier was not affected by sample types. Notably, chemotherapy combined with radiotherapy significnalty improved PFS and OS versus radiotherapy alone in high risk Ann Anbor stage I patients, while there was no statistical difference between the two therapeutic modalities among low risk patients. A nomogram was constructed comprised of the classifier and clinicopathological variables, and showed remarkably better predictive accuracy than that of each variable alone. The 7-SNP-based classifier is a complement to existing risk stratification systems in ENKTL, which could have significant implications for clinical decision-making for ENKTL patients.

Dynamic evaluation of the prognostic value of 18F-FDG PET/CT in extranodal NK/T-cell lymphoma, nasal type

Extranodal natural killer/T-cell lymphoma, nasal-type (ENKTL) is a type of rare and distinct entity of non-Hodgkin lymphoma with poor prognosis. It is important to evaluate the early treatment response accurately to decide further treatment strategy. ¹⁸F-FDG PET/CT plays an important role in response evaluation and prognostic prediction in some kinds of lymphomas. However, data available regarding patients with ENKTL are limited. Thus, in this prospective study, we analyzed the prognostic value of ¹⁸F-FDG PET/CT in ENKTL. Thirty-four patients with newly diagnosed ENKTL were enrolled in this phase 2 study (NCT02825147, July 7, 2016). The patients received pre-, mid-, and end-treatment ¹⁸F-FDG PET/CT scans. Deauville score (DS), maximal standardized uptake values (SUVmax), and the change in SUVmax (ΔSUVmax) were recorded for response assessment. The median follow-up period was 42.2 months. The 2-year overall survival (OS) and progression-free survival (PFS) were 82.4% and 73.5%, respectively. Univariate analysis revealed that Ann Arbor stage (P < 0.002), mid-treatment DS (P = 0.005), mid-SUVmax (P = 0.001), mid-∆SUVmax (P = 0.004), end-treatment DS (P < 0.001), and end-SUVmax (P = 0.014) were prognostic factors for OS. Ann Arbor stage (P = 0.001), mid-treatment DS (P = 0.008), mid-SUVmax (P = 0.029), mid-∆SUVmax (P < 0.001), and end-treatment DS (P =0.021) were of prognostic significance for PFS. Multivariate analysis showed that mid-SUVmax (P = 0.042) and DS at the middle (P = 0.050) and end (P = 0.044) of treatment were significant independent predictors of PFS. ¹⁸F-FDG PET/CT is useful for predicting the prognosis of ENKTL.

Weakly supervised deep learning for determining the prognostic value of 18F-FDG PET/CT in extranodal natural killer/T cell lymphoma, nasal type

Purpose

To develop a weakly supervised deep learning (WSDL) method that could utilize incomplete/missing survival data to predict the prognosis of extranodal natural killer/T cell lymphoma, nasal type (ENKTL) based on pretreatment ¹⁸F-FDG PET/CT results.

Methods

One hundred and sixty-seven patients with ENKTL who underwent pretreatment ¹⁸F-FDG PET/CT were retrospectively collected. Eighty-four patients were followed up for at least 2 years (training set = 64, test set = 20). A WSDL method was developed to enable the integration of the remaining 83 patients with incomplete/missing follow-up information in the training set. To test generalization, these data were derived from three types of scanners. Prediction similarity index (PSI) was derived from deep learning features of images. Its discriminative ability was calculated and compared with that of a conventional deep learning (CDL) method. Univariate and multivariate analyses helped explore the significance of PSI and clinical features.

Results

PSI achieved area under the curve scores of 0.9858 and 0.9946 (training set) and 0.8750 and 0.7344 (test set) in the prediction of progression-free survival (PFS) with the WSDL and CDL methods, respectively. PSI threshold of 1.0 could significantly differentiate the prognosis. In the test set, WSDL and CDL achieved prediction sensitivity, specificity, and accuracy of 87.50% and 62.50%, 83.33% and 83.33%, and 85.00% and 75.00%, respectively. Multivariate analysis confirmed PSI to be an independent significant predictor of PFS in both the methods.

Conclusion

The WSDL-based framework was more effective for extracting ¹⁸F-FDG PET/CT features and predicting the prognosis of ENKTL than the CDL method.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05232-3.

Prognostic Value of Baseline Radiomic Features of 18F-FDG PET in Patients with Diffuse Large B-Cell Lymphoma

This study investigates whether baseline ¹⁸F-FDG PET radiomic features can predict survival outcomes in patients with diffuse large B-cell lymphoma (DLBCL). We retrospectively enrolled 83 patients diagnosed with DLBCL who underwent ¹⁸F-FDG PET scans before treatment. The patients were divided into the training cohort (n = 58) and the validation cohort (n = 25). Eighty radiomic features were extracted from the PET images for each patient. Least absolute shrinkage and selection operator regression were used to reduce the dimensionality within radiomic features. Cox proportional hazards model was used to determine the prognostic factors for progression-free survival (PFS) and overall survival (OS). A prognostic stratification model was built in the training cohort and validated in the validation cohort using Kaplan-Meier survival analysis. In the training cohort, run length non-uniformity (RLN), extracted from a gray level run length matrix (GLRLM), was independently associated with PFS (hazard ratio (HR) = 15.7, p = 0.007) and OS (HR = 8.64, p = 0.040). The International Prognostic Index was an independent prognostic factor for OS (HR = 2.63, p = 0.049). A prognostic stratification model was devised based on both risk factors, which allowed identification of three risk groups for PFS and OS in the training (p < 0.001 and p < 0.001) and validation (p < 0.001 and p = 0.020) cohorts. Our results indicate that the baseline ¹⁸F-FDG PET radiomic feature, RLN_GLRLM, is an independent prognostic factor for survival outcomes. Furthermore, we propose a prognostic stratification model that may enable tailored therapeutic strategies for patients with DLBCL.

The predictive value of pre-treatment 18F-FDG PET/CT on treatment outcome in early-stage extranodal natural killer/T-cell lymphoma

The diagnostic value of pretreatment ¹⁸F-FDG PET/CT in early-stage extranodal natural killer/T-cell lymphoma (ENKTL) is established, but its prognostic value is still unclear. We conducted ¹⁸F-FDG PET/CT-based quantitative and qualitative analysis as well as assessed related clinical parameters in 50 patients with recently diagnosed ENKTL and treated with methotrexate, etoposide, dexamethasone, and pegaspargase (MESA)-based therapy. Patients were followed-up for 38.6 ± 17.8 months. Six patients died of tumor-related disease, and six patients presented with persistence or recurrence. The estimates of the 2-year OS and PFS for the patients were 90.0% (SE: 4.0%) and 82.0% (SE: 5.0%), respectively. Survival curves were obtained using Kaplan-Meier analysis and compared using log rank test. Based on signifiacnt results of univariate analysis, we selected Epstein-Barr virus DNA (EB-DNA), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) for multivariate analysis. Finally, MTV was found to be the significant independent predictor of both OS (p = .038) and PFS (p = .039).

Development and validation of an 18F-FDG PET radiomic model for prognosis prediction in patients with nasal-type extranodal natural killer/T cell lymphoma

OBJECTIVES

To identify an ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET) radiomics-based model for predicting progression-free survival (PFS) and overall survival (OS) of nasal-type extranodal natural killer/T cell lymphoma (ENKTL).

METHODS

In this retrospective study, a total of 110 ENKTL patients were divided into a training cohort (n = 82) and a validation cohort (n = 28). Forty-one features were extracted from pretreatment PET images of the patients. Least absolute shrinkage and selection operator (LASSO) regression was used to develop the radiomic signatures (R-signatures). A radiomics-based model was built and validated in the two cohorts and compared with a metabolism-based model.

RESULTS

The R-signatures were constructed with moderate predictive ability in the training and validation cohorts (R-signature_PFS: AUC = 0.788 and 0.473; R-signature_OS: AUC = 0.637 and 0.730). For PFS, the radiomics-based model showed better discrimination than the metabolism-based model in the training cohort (C-index = 0.811 vs. 0.751) but poorer discrimination in the validation cohort (C-index = 0.588 vs. 0.693). The calibration of the radiomics-based model was poorer than that of the metabolism-based model (training cohort: p = 0.415 vs. 0.428, validation cohort: p = 0.228 vs. 0.652). For OS, the performance of the radiomics-based model was poorer (training cohort: C-index = 0.818 vs. 0.828, p = 0.853 vs. 0.885; validation cohort: C-index = 0.628 vs. 0.753, p < 0.05 vs. 0.913).

CONCLUSIONS

Radiomic features derived from PET images can predict the outcomes of patients with ENKTL, but the performance of the radiomics-based model was inferior to that of the metabolism-based model.

KEY POINTS

• The R-signatures calculated by using ¹⁸F-FDG PET radiomic features can predict the survival of patients with ENKTL. • The radiomics-based models integrating the R-signatures and clinical factors achieved good predictive values. • The performance of the radiomics-based model was inferior to that of the metabolism-based model in the two cohorts.

Prognostic Value of Pretreatment Radiomic Features of 18F-FDG PET in Patients With Hodgkin Lymphoma

PURPOSE

This study investigated whether a radiomic analysis of pretreatment F-FDG PET can predict prognosis in patients with Hodgkin lymphoma (HL).

METHODS

Forty-two patients who were diagnosed as having HL and underwent pretreatment F-FDG PET scans were retrospectively enrolled. For each patient, we extracted 450 radiomic features from PET images. The prognostic significance of the clinical and radiomic features was assessed in relation to progression-free survival (PFS) and overall survival (OS). Receiver operating characteristic curve, Cox proportional hazards regression, and Kaplan-Meier analyses were performed to examine the potential independent predictors and to evaluate the predictive value.

RESULTS

Intensity nonuniformity extracted from a gray-level run-length matrix and the Ann Arbor stage were independently associated with PFS (hazard ratio [HR] = 22.8, P < 0.001; HR = 7.6, P = 0.024) and OS (HR = 14.5, P = 0.012; HR = 8.5, P = 0.048), respectively. In addition, SUV kurtosis was an independent prognosticator for PFS (HR = 6.6, P = 0.026). We devised a prognostic scoring system based on these 3 risk predictors. The proposed scoring system further improved the risk stratification of the current staging classification (P < 0.001).

CONCLUSIONS

The radiomic feature intensity nonuniformity is an independent prognostic predictor of PFS and OS in patients with HL. We devised a prognostic scoring system, which may be more beneficial for patient risk stratification in guiding therapy compared with the current Ann Arbor staging system.

Impact of acquisition count statistics reduction and SUV discretization on PET radiomic features in pediatric 18F-FDG-PET/MRI examinations

PURPOSE

The evaluation of features robustness with respect to acquisition and post-processing parameter changes is fundamental for the reliability of radiomics studies. The aim of this study was to investigate the sensitivity of PET radiomic features to acquisition statistics reduction and standardized-uptake-volume (SUV) discretization in PET/MRI pediatric examinations.

METHODS

Twenty-seven lesions were detected from the analysis of twenty-one 18F-FDG-PET/MRI pediatric examinations. By decreasing the count-statistics of the original list-mode data (3 MBq/kg), injected activity reduction was simulated. Two SUV discretization approaches were applied: 1) resampling lesion SUV range into fixed bins numbers (FBN); 2) rounding lesion SUV into fixed bin size (FBS). One hundred and six radiomic features were extracted. Intraclass Correlation Coefficient (ICC), Spearman correlation coefficient and coefficient-of-variation (COV) were calculated to assess feature reproducibility between low tracer activities and full tracer activity feature values.

RESULTS

More than 70% of Shape and first order features, and around 70% and 40% of textural features, when using FBS and FBN methods respectively, resulted robust till 1.2 MBk/kg. Differences in median features reproducibility (ICC) between FBS and FBN datasets were statistically significant for every activity level independently from bin number/size, with higher values for FBS. Differences in median Spearman coefficient (i.e. patient ranking according to feature values) were not statistically significant, varying the intensity resolution (i.e. bin number/size) for either FBS and FBN methods.

CONCLUSIONS

For each simulated count-statistic level, robust PET radiomic features were determined for pediatric PET/MRI examinations. A larger number of robust features were detected when using FBS methods.

Primary adrenal extranasal NK/T cell lymphoma with subcutaneous involvement demonstrated on FDG PET/CT: A clinical case report

RATIONALE

Primary adrenal non-Hodgkin lymphomas are predominant diffuse large B cell lymphoma with frequently bilateral adrenal involvement, but the occurrence of nasal type extranodal NK/T cell lymphoma is relatively rare.

PATIENT CONCERNS

A 40-year-old woman complaining of left back pain for 2-month was admitted to our department.

DIAGNOSIS

Based on the feature of enhanced computed tomography (CT) images which showed huge bilateral well-defined adrenal masses with heterogeneous enhancement, she was tentatively diagnosed as having primary adrenal malignancy. Postoperative pathology revealed the diagnosis of primary adrenal Epstein-Barr virus-associated nasal type extranodal NK/T-cell lymphoma.

INTERVENTIONS

Then, she underwent F-fluoro-2-deoxy-D-glucose (F-FDG) positron emission tomography (PET)/CT examination for staging, which showed homogeneously increased FDG uptake in the right adrenal gland and left thigh subcutaneous lesion, as well as heterogeneous increased FDG uptake in the left adrenal gland region with no abnormal uptake in the nasal cavity. Subsequently, the patient has performed 7 cycles of gemcitabine, L-asparaginase, ifosfamide, dexamethasone, etoposide (GLIDE) regimen and autologous stem cell transplantation.

OUTCOMES

Fortunately, the subsequent 2 follow-up FDG PET/CT scans within 1 year revealed complete resolution with no abnormal FDG uptake in the initially involved sites after 7 cycles of GLIDE chemotherapy and autologous stem cell transplantation.

LESSONS

The enhanced CT and FDG PET/CT features of primary adrenal extranasal NK/T cell lymphoma are huge bilateral well-defined adrenal masses with heterogeneous enhancement, high FDG uptake, especially with subcutaneous involvement. And the awareness of this entity may help clinicians to differentiate it from other primary adrenal tumors and make reasonable therapeutic strategies. Besides, FDG PET/CT scan is very useful for the treatment follow-up of the primary adrenal extranasal NK/T cell lymphoma.

Positron emission tomography/computed tomography in the diagnosis, staging, and prognostic evaluation of natural killer/T-cell lymphoma

Natural killer/T-cell lymphoma (NKTL) is a rare subtype of non-Hodgkin's lymphoma that is associated with Epstein-Barr virus infection. The clinicopathological features of NKTL are unique among lymphomas. NKTL is an aggressive disease with a poor prognosis in the absence of effective treatment. Accurate diagnosis and staging are essential to ensure an appropriate treatment strategy and accurate prognosis of NKTL. ¹⁸F-Fluorodexoyglucose-positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) is a valuable technique in the diagnosis, staging, and prognostic evaluation of various types of malignant tumors, including NKTL. PET/CT imaging studies of patients with NKTL have shown that NKTL is ¹⁸F-FDG-avid and that PET/CT is superior to conventional methods in detecting cutaneous and extracutaneous lesions. We herein review recent PET/CT studies that have provided considerable insight into the diagnosis, staging, prognostic evaluation, and treatment effectiveness in patients with NKTL.

Modified fractal analysis of methionine positron emission tomography images for predicting prognosis in newly diagnosed patients with glioma

OBJECTIVE

To assess intratumoural metabolic heterogeneity using modified fractal analysis and to determine its prognostic significance in patients with glioma.

PATIENTS AND METHODS

A total of 57 patients with newly diagnosed glioma who underwent methionine PET-computed tomography between August 2012 and January 2017 were enrolled. The requirement for informed consent was waived for this retrospective study. Tumour-to-normal tissue ratio, metabolic tumour volume, total lesion methionine uptake and modified fractal dimension (m-FD) were calculated for each tumour using methionine PET-computed tomography. Associations between these indices and tumour grade and overall survival were analysed.

RESULTS

Overall, eight patients had grade II, 20 had grade III and 29 had grade IV tumours. The tumour-to-normal tissue ratios of grade III and grade IV tumours were significantly greater than that of grade II tumours. The metabolic tumour volume and total lesion methionine uptake of grade III tumours were significantly greater than those of grade II and grade IV tumours. The m-FD of grade IV tumours was significantly greater than those of grade II and grade III tumours. A total of 47 patients were followed up, and their prognoses were evaluated. Only the m-FD was significantly associated with a poor prognosis (P<0.05). Multivariate analyses identified age (>58 years) (hazard ratio: 5.73; 95.0% confidence interval: 1.4-29.9; P=0.015) and the m-FD (>0.87) (hazard ratio: 4.80; 95.0% confidence interval: 1.12-32.9; P=0.033) as independent prognostic factors for overall survival.

CONCLUSION

Intratumoural metabolic heterogeneity is a useful imaging biomarker in patients with glioma.

Radiomics in Oncological PET/CT: Clinical Applications

18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is widely used for staging, evaluating treatment response, and predicting prognosis in malignant diseases. FDG uptake and volumetric PET parameters such as metabolic tumor volume have been used and are still used as conventional PET parameters to assess biological characteristics of tumors. However, in recent years, additional features derived from PET images by computational processing have been found to reflect intratumoral heterogeneity, which is related to biological tumor features, and to provide additional predictive and prognostic information, which leads to the concept of radiomics. In this review, we focus on recent clinical studies of malignant diseases that investigated intratumoral heterogeneity on PET/CT, and we discuss its clinical role in various cancers.

Prognostic significance of standardized uptake value on F18-FDG PET/CT in patients with extranodal nasal type NK/T cell lymphoma: A multicenter, retrospective analysis

OBJECTIVES

The purpose of this study was to evaluate the value of parameters assessed with F18-flurodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) in predicting relapse free survival and overall survival in patients with extranodal nasal type NK/T cell lymphoma.

METHODS

Thirty-six patients with extranodal nasal type NK/T cell lymphoma, and who underwent PET/CT prior to curative treatment, were enrolled at five institutions. Volumes of interest covering the entire tumor volume were delineated on PET/CT images, and the maximum standardized uptake value (SUVmax), mean SUV (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were measured using thresholds of 40% of SUVmax. Furthermore, we compared the difference in F18-FDG avidity according to Epstein-Barr virus (EBV) infection status.

RESULTS

The SUVmax (p=0.041) and SUVmean (p=0.049) in patients who died were higher than the respective values of those who survived. A higher TLG (>45.8) was associated with relapse free survival (HR 7.856, p=0.034). Ann Arbor stage (III-IV, HR 14.12, p=0.004), and a higher SUVmax (>12.6, p=0.024) and SUVmean (>6.4, p=0.024) were associated with poor survival. However, neither the MTV nor the TLG (volumetric parameters) were significant predictors of death. The PET parameters SUVmax (p=0.181), SUVmean (p=0.237), MTV (p=0.636), and TLG (p=0.469) did not differ significantly between patients with and without EBV infections.

CONCLUSIONS

High TLG was the only significant predictive factor on relapse free survival. The SUVmax and SUVmean measured by F18-FDG PET/CT could be significant prognostic factors in patients with extranodal nasal type NK/T cell lymphoma.

18F-FDG PET for Detection of Primary Tracheobronchial T-/Natural Killer-Cell-Derived Posttransplant Lymphoproliferative Disorder After Lung Transplantation

Posttransplant lymphoproliferative disorder (PTLD) is a rare, but potentially devastating complication of solid organ transplantation. Epstein-Barr virus-associated PTLDs of T-cell origin are exceedingly rare. We present the case of a 20-year-old man with extranasal T-/natural killer-cell-derived PTLD after lung transplantation who underwent an F-FDG PET/CT scan for staging of disease. The F-FDG-PET scan demonstrated an unusual pattern of lymphomatous involvement limited to the recipients tracheobronchial tree without concomitant involvement of the donor's bronchi. This case highlights the potential of F-FDG PET/CT for sensitive detection and staging of uncommon manifestations of PTLD.

Elevated tumor-to-liver uptake ratio (TLR) from 18F-FDG-PET/CT predicts poor prognosis in stage IIA colorectal cancer following curative resection

Purpose

The prognostic value of the tumor-to-liver uptake ratio (TLR) from 18-fluoro-2-deoxyglucose positron emission tomography/computed tomography (¹⁸F–FDG-PET/CT) in the early stage of colorectal cancer (CRC) is unclear. Notably, some stage IIA CRC patients experience early recurrence even after curative resection and might benefit from neoadjuvant or adjuvant chemotherapy. This study aims to evaluate whether elevated TLR from ¹⁸F–FDG-PET/CT can predict poor prognosis in stage IIA CRC patients undergoing curative resection.

Methods

From April 2010 to December 2013, 504 consecutive CRC patients with different TNM stages (I-IV) underwent ¹⁸F–FDG-PET/CT scans at the 6th Affiliated Hospital of Sun Yat-Sen University. Among the patients, 118 with stage IIA CRC who accepted preoperative ¹⁸F–FDG-PET/CT scanning and were treated with curative surgery alone were reviewed retrospectively. The maximum standardized uptake value (SUVmax) in the primary tumor, TLR, and demographic, clinical, histopathological, and laboratory data were analyzed. Receiver operating characteristic (ROC) curve, univariate and multivariate analyses were performed to identify prognostic factors associated with patient disease-free survival (DFS) and overall survival (OS).

Results

ROC curve analysis demonstrated that TLR was superior to primary tumor SUVmax in predicting the risk of recurrence in stage IIA CRC. The optimal TLR cutoff was 6.2. Univariate analysis indicated that elevated TLR, tumor size, and lymphovascular/neural invasion correlated with DFS (P = 0.001, P = 0.002, and P = 0.001, respectively) and OS (P = 0.001, P = 0.003, and P < 0.001, respectively). The 1-, 3-, and 5-year DFS rates were 98.4%, 96.9%, and 96.9% for stage IIA CRC patients with lower TLR (≤6.2) versus 77.8%, 60.6%, and 60.6% for those with elevated TLR (>6.2), respectively. The 1-, 3-, and 5-year OS rates were 100.0%, 100.0%, and 98.3% for the patients with lower TLR versus 98.1%, 83.3%, and 74.3% for those with elevated TLR. Cox regression analysis showed that elevated TLR [>6.2; hazard ratio (HR): 3.109–57.463; P < 0.001] and tumor size (>4.4 cm; HR: 1.636–19.155; P = 0.006) were independent risk factors for DFS. Meanwhile, elevated TLR (>6.2; HR: 1.398–84.945; P = 0.023) and lymphovascular/neural invasion (positive; HR: 1.278–12.777; P = 0.017) were independent risk factors for OS.

Conclusion

Elevated TLR predicted worse DFS and OS for stage IIA CRC patients and might serve as a potential radiological index to identify candidates for neoadjuvant or adjuvant chemotherapy. Stage IIA CRC patients with elevated TLR should be monitored carefully for early detection of possible recurrence.

Pretreatment metabolic parameters measured by 18F-FDG-PET to predict the outcome of first-line chemotherapy in extensive-stage small-cell lung cancer

OBJECTIVE

Patients' pretreatment metabolic burden, as measured by radiotracer fluorine-18 fluorodeoxyglucose (F-FDG) PET/computed tomography (CT), has been shown to predict treatment outcome in various malignancies. However, its predictive role in extensive-stage small cell lung cancer (SCLC) has not been definitively determined. This retrospective study investigated the viability of using common pretreatment metabolic parameters, obtained through F-FDG-PET/CT, to predict outcomes of first-line chemotherapy in extensive-stage SCLC.

PARTICIPANTS AND METHODS

The study population comprised 154 consecutive patients with extensive-stage SCLC who underwent a pretreatment F-FDG-PET/CT scan and received standard first-line chemotherapy between January 2011 and December 2015.

RESULTS

Ten (6.5%) and 66 (42.9%) patients achieved a complete or a partial response, respectively (considered an objective response); 35 (22.7%) and 43 (27.9%) experienced stable or progressive disease. The metabolic tumor volume (MTV) was a significant factor for predicting an objective response. For predicting disease control (objective response or stable disease), MTV and total lesion glycolysis (TLG) were nonindependent factors.

CONCLUSION

Greater MTV and TLG could indicate a poorer response to first-line chemotherapy for patients with extensive-stage SCLC, but the predictive efficiency was not high enough for routine reliance. For patients who are not suitable to receive first-line chemotherapy, MTV and TLG may help guide clinical decisions.