The clinical value of texture analysis of dual-time-point 18F-FDG-PET/CT imaging to differentiate between 18F-FDG-avid benign and malignant pulmonary lesions

Diagnostic performance of F-18 FDG PET/CT in differentiating autoimmune pancreatitis from pancreatic cancer: a systemic review and meta-analysis

OBJECTIVES

This study aims to evaluate the utility of F-18 FDG PET/CT in the non-invasive diagnosis of autoimmune pancreatitis (AIP) and differentiating it from pancreatic cancer (CaP) based on the amount and pattern of FDG uptake, as well as involvement of extra-pancreatic sites.

METHODS

A systematic search was conducted using PubMed, Scopus, Cochrane Library and Google Scholar. Only those studies that compared the findings of F-18 FDG PET/CT in terms of SUVmax, pattern of FDG uptake and presence of FDG-avid extra-pancreatic sites in both AIP and CaP were included. Studies were qualitatively assessed for risk of bias and publication bias. The diagnostic performance of parameters on PET/CT was examined through pooled sensitivity, specificity, diagnostic odd's ratio (DOR) and summary receiver operator characteristic (SROC) curve analysis.

RESULTS

Six studies were included with a total of 580 patients. 178 patients had AIP (Age 18-90 years, male, M: female, F ratio-8.4:1) and 402 patients had CaP (Age 22-88 years, M:F ratio-1.5:1). Type of AIP was reported in only 3 studies, with the included cases predominantly being type 1 AIP. All studies were retrospective with heterogeneity and a risk on patient selection and index test. The FDG uptake, expressed as SUVmax, was lower in AIP with a weighted mean difference of -3.11 (95% confidence interval, CI: -5.28 to -0.94). To diagnose AIP, the pooled sensitivity, specificity and DOR of diffuse pattern of FDG uptake were 0.59 (95% CI: 0.51-0.66), 0.89 (95% CI: 0.86-0.92) and 21.07 (95% CI: 5.07-88.32), respectively, with an area under curve (AUC) of 0.717 on SROC analysis. The pooled sensitivity, specificity and DOR of FDG-avid extra pancreatic sites were 0.55 (95% CI: 0.45-0.65), 0.58 (95% CI: 0.52-0.64) and 2.33 (95% CI: 1.40-3.89), respectively, with an AUC of 0.632.

CONCLUSION

On F-18 FDG PET/CT, a pancreatic lesion of AIP has a lower SUVmax value than CaP. A diffuse pattern of FDG uptake and presence of an extra-pancreatic FDG-avid site are nearly 21 times and twice more likely in AIP than CaP, respectively.

The prognostic value of bone marrow retention index and bone marrow-to-liver ratio of baseline 18F-FDG PET/CT in diffuse large B-cell lymphoma

OBJECTIVE

To determine prognostic value of bone marrow retention index (RI-bm) and bone marrow-to-liver ratio (BLR) measured on baseline dual-phase 18F-FDG PET/CT in a series of newly diagnosed patients with diffuse large B-cell lymphoma (DLBCL) treated homogeneously with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) chemotherapy.

PATIENTS AND METHODS

This prospective study enrolled 135 patients with newly diagnosed DLBCL. All patients underwent dual-phase 18F-FDG PET/CT. The following PET parameters were calculated for both tumor and bone marrow: maximum standardized uptake value (SUVmax) at both time points (SUVmax early and SUVmax delayed), SUVmax increment (SUVinc), RI, and BLR. Patients were treated with R-CHOP regimen and response at end of treatment was assessed.

RESULTS

The final analysis included 98 patients with complete remission. At a median follow-up of 22 months, 57 patients showed no relapse, 74 survived, and 24 died. The 2-year relapse-free survival (RFS) values for patients with higher and lower RI-bm were 20% and 65.1%, respectively (p < 0.001), and for patients with higher and lower BLR were 30.2% and 69.6%, respectively (p < 0.001). The 2-year overall survival (OS) values for patients with higher and lower RI-bm were 60% and 76.3%, respectively (p = 0.023), and for patients with higher and lower BLR were 57.3% and 78.6%, respectively (p = 0.035). Univariate analysis revealed that RI-bm and BLR were independent significant prognostic factors for both RFS and OS (hazard ratio [HR] = 4.02, p < 0.001, and HR = 3.23, p < 0.001, respectively) and (HR = 2.83, p = 0.030 and HR = 2.38, p = 0.041, respectively).

CONCLUSION

Baseline RI-bm and BLR were strong independent prognostic factors in DLBCL patients.

CLINICAL RELEVANCE STATEMENT

Bone marrow retention index (RI-bm) and bone marrow-to-liver ratio (BLR) could represent suitable and noninvasive positron emission tomography/computed tomography (PET/CT) parameters for predicting pretreatment risk in patients with newly diagnosed diffuse large B-cell lymphoma (DLBCL) who were treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) chemotherapy.

KEY POINTS

• Bone marrow retention index (RI-bm) and bone marrow-to-liver ratio (BLR) are powerful prognostic variables in diffuse large B-cell lymphoma (DLBCL) patients. • High BLR and RI-bm are significantly associated with poor overall survival (OS) and relapse-free survival (RFS). • RI-bm and BLR represent suitable and noninvasive risk indicators in DLBCL patients.

Value of [18F]AlF-NOTA-FAPI-04 PET/CT for differential diagnosis of malignant and various inflammatory lung lesions: comparison with [18F]FDG PET/CT

OBJECTIVE

Uptake of the imaging tracers [18F]AlF-NOTA-FAPI-04 and [18F]FDG varies in some inflammatory lesions, which may result in false-positive findings for malignancy on PET/CT. Our aim was to compare the [18F]AlF-NOTA-FAPI-04 and [18F]FDG PET/CT imaging features of malignant and various inflammatory lung lesions and to analyze their value for differential diagnosis.

METHODS

We retrospectively analyzed [18F]AlF-NOTA-FAPI-04 PET/CT scans from 67 cancer patients taken between December 2020 and January 2022, as well as the scans of 32 patients who also underwent [18F]FDG PET/CT imaging. The maximum and mean standardized uptake values (SUVmax and SUVmean, respectively) and lesion-to-background ratio (LBR) were calculated. The predictive capabilities of semiquantitative PET/CT parameters were analyzed by receiver operating characteristic curve analysis.

RESULTS

A total of 70 inflammatory and 37 malignant lung lesions were evaluated by [18F]AlF‑NOTA‑FAPI‑04 PET/CT, and 33 inflammatory and 26 malignant lung lesions also were evaluated by [18F]FDG PET/CT. Inflammatory lesions exhibited lower [18F]AlF-NOTA-FAPI-04 and [18F]FDG uptake compared to malignant lesions, with statistically significant differences in SUVmax, SUVmean, and LBR (all p < 0.001). [18F]AlF-NOTA-FAPI-04 uptake also varied among different types of inflammatory lesions (SUVmax, p = 0.005; SUVmean, p = 0.008; LBR, p < 0.001), with the highest uptake observed in bronchiectasis with infection, followed by postobstructive pneumonia, and the lowest in pneumonia. [18F]FDG uptake was higher in postobstructive pneumonia than in pneumonia (SUVmax, p = 0.009; SUVmean, p = 0.016; LBR, p = 0.004).

CONCLUSION

[18F]AlF-NOTA-FAPI-04/[18F]FDG PET/CT showed significantly lower uptake in inflammatory lesions than malignancies as well as variation in different types of inflammatory lesions, and thus, may be valuable for distinguishing malignant and various inflammatory findings.

CLINICAL RELEVANCE STATEMENT

Our study confirmed that the uptake of [18F]AlF-NOTA-FAPI-04/[18F]FDG PET/CT in inflammatory and malignant lung lesions is different, which is beneficial to distinguish inflammatory and malignant lung lesions in clinic.

KEY POINTS

• Malignant and different inflammatory lung lesions showed varying degrees of uptake of [18F]AlF-NOTA-FAPI-04 and [18F]FDG. • Inflammatory lung lesions showed significantly less uptake than malignancies, and uptake varied among different types of inflammatory lesions. • Both types of PET/CT could differentiate malignant and various inflammatory lung findings.

Role of multiple dual-phase 18F-FDG PET/CT metabolic parameters in differentiating adenocarcinomas from squamous cell carcinomas of the lung

Purpose

To evaluate the ability of multiple dual-phase 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) metabolic parameters to distinguish the histological subtypes of non-small cell lung cancer (NSCLC).

Methods

Data from 127 patients with non-small cell lung cancer who underwent preoperative dual-phase 18F-FDG PET/CT scanning at the PET-CT center of our hospital from December 2020 to October 2021 were collected, and the metabolic parameters of their primary lesions were measured and analyzed retrospectively. Intraclass correlation coefficients (ICC) were calculated for consistency between readers. Metabolic parameters in the early (SUVpeak, SUVmean, SUVmin, SUVmax, MTV, and TLG) and delayed phases (dpSUVpeak, dpSUVmean, dpSUVmin, dpSUVmax, dpMTV, and dpTLG) were calculated. We drew receiver operating characteristic (ROC) curves to compare the differences in different metabolic parameters between the adenocarcinoma (AC) and squamous cell carcinoma (SCC) groups and evaluated the ability of different metabolic parameters to distinguish AC from SCC.

Results

Inter-reader agreement, as assessed by the intraclass correlation coefficient (ICC), was good (ICC = 0.71, 95% CI:0.60-0.79). The mean MTV, SUVmax, TLG, SUVpeak, SUVmean, dpSUVmax, dpTLG, dpSUVpeak, dpSUVmean, and dpSUVmin of the tumors were significantly higher in SCC lesions than in AC lesions (P = 0.049, < 0.001, 0.016, < 0.001, 0.001, < 0.001, 0.018, < 0.001, 0.001, and 0.001, respectively). The diagnostic efficacy of the metabolic parameters in 18F-FDG PET/CT for differentiating adenocarcinoma from squamous cell carcinoma ranged from high to low as follows: SUVpeak (AUC = 0.727), SUVmax (AUC = 0.708), dpSUVmax (AUC = 0.699), dpSUVpeak (AUC = 0.698), TLG (AUC = 0.695), and dpTLG (AUC = 0.692), SUVmean (AUC = 0.690), dpSUVmean (AUC = 0.687), dpSUVmin (AUC = 0.680), SUVmin (AUC = 0.676), and MTV (AUC = 0.657).

Conclusions

Squamous cell carcinoma of the lung had higher mean MTV, SUVmax, TLG, SUVpeak, SUVmean, SUVmin, dpSUVpeak, dpSUVmean, dpSUVmin, dpSUVmax, and dpTLG than AC, which can be helpful tools in differentiating between the two. The metabolic parameters of the delayed phase (2 h after injection) 18F-FDG PET/CT did not improve the diagnostic efficacy in distinguishing lung AC from SCC. Conventional dual-phase 18F-FDG PET/CT is not recommended.

Assessment of Tissue Adequacy by EBUS in Conjunction with PET Scan and Operator's Experience

Mediastinal lymph node assessment is a crucial step in non-small cell lung cancer staging. Positron emission tomography (PET) has been the gold standard for the assessment of mediastinal lymphadenopathy, though it has limited specificity. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is quick, accurate, and a less invasive method for obtaining a diagnostic sample in contrast to mediastinoscopy. We performed a retrospective chart analysis of 171 patients to assess the adequacy of tissue obtained by EBUS for diagnosis and molecular profiling as well as the assessment of staging and lymph node (LN) stations diagnostic yield, in correlation to PET scan and the operator’s level of experience. A significantly increased tissue adequacy was observed based on the operators’ experience, with the highest adequacy noted in trained Interventional Pulmonologist (IP) (100%), followed by >5 years of experience (93.33%), and 88.89% adequacy with <5 years of experience (p = 0.0019). PET-CT scan 18F-fluorodeoxyglucose (FDG) uptake in levels 1, 2, and 3 LN had a tissue adequacy of 76.67%, 54.64%, and 35.56%, respectively (p = 0.0009). EBUS bronchoscopy method could be used to achieve an accurate diagnosis, with IP-trained operators yielding the best results. There is no correlation with PET scan positivity, indicating that both PET and EBUS are complementary methods needed for staging.

State of the Art: Lung Cancer Staging Using Updated Imaging Modalities

Lung cancer is among the most common mortality causes worldwide. This scientific article is a comprehensive review of current knowledge regarding screening, subtyping, imaging, staging, and management of treatment response for lung cancer. The traditional imaging modality for screening and initial lung cancer diagnosis is computed tomography (CT). Recently, a dual-energy CT was proven to enhance the categorization of variable pulmonary lesions. The National Comprehensive Cancer Network (NCCN) recommends usage of fluorodeoxyglucose positron emission tomography (FDG PET) in concert with CT to properly stage lung cancer and to prevent fruitless thoracotomies. Diffusion MR is an alternative to FDG PET/CT that is radiation-free and has a comparable diagnostic performance. For response evaluation after treatment, FDG PET/CT is a potent modality which predicts survival better than CT. Updated knowledge of lung cancer genomic abnormalities and treatment regimens helps to improve the radiologists’ skills. Incorporating the radiologic experience is crucial for precise diagnosis, therapy planning, and surveillance of lung cancer.

Semiquantitative analysis using whole-body dynamic F-18 fluoro-2-deoxy-glucose-positron emission tomography to differentiate between benign and malignant lesions

OBJECTIVES

To investigate whether whole-body dynamic positron emission tomography (PET) is useful for differentiating benign and malignant lesions.

METHODS

In this retrospective study, data from a cohort of 146 lesions from 187 patients who consecutively underwent whole-body dynamic PET scans at our hospital for suspected lesions in the lung, lymph nodes, liver, bone, esophagus, and colon were analyzed. Patients with malignant lymphomas, accumulations > 5 cm in length along the long axis of the esophagus, or lesions in the colon in which the site of accumulation moved during the imaging period were excluded. Patients were administered 3.7 MBq/kg of fluorine-18-fluorodeoxyglucose (F-18 FDG), and dynamic imaging was initiated 60 min after administration. We defined the 60-65, 65-70, 70-75, and 75-80 min time mark as the first, second, third, and fourth pass, respectively. The static image is the summed average of all the four pass images. We measured the accumulation in the mean image of the whole-body dynamic PET scan, which was arithmetically similar to the maximum standardized uptake value (SUVmax) throughout the whole-body static images obtained during 20 min of imaging (S-SUVmax). The ratio of SUVmax in the dynamic first pass(60-65 min after FDG administration) and fourth pass(75-80 min after FDG administration) was calculated as R-SUVmax.

RESULTS

The S-SUVmax in the lung, lymph nodes, and bone did not differ significantly between the benign and malignant groups. However, there was a significant difference in R-SUVmax, which was > 1 in most malignant lesions indicating an increase in accumulation during routine scan time. Significant differences were observed between benign and malignant lesions of the liver in both S-SUVmax and R-SUVmax values, with the latter being > 1 in most malignant lesions.

CONCLUSIONS

Whole-body dynamic PET for 20 min starting 1 h after FDG administration improved the accuracy of malignant lesion detection in the liver, lymph nodes, lung, and bone. The incremental improvement was small, and the FDG dynamics in the distribution of values between benign and malignant overlapped. Additional information from whole-body dynamic imaging can help detect malignant lesions in these sites without increasing patient burden or prolonging imaging time.

The value of diffusion kurtosis imaging, diffusion weighted imaging and 18F-FDG PET for differentiating benign and malignant solitary pulmonary lesions and predicting pathological grading

Objective

To explore the value of PET/MRI, including diffusion kurtosis imaging (DKI), diffusion weighted imaging (DWI) and positron emission tomography (PET), for distinguishing between benign and malignant solitary pulmonary lesions (SPLs) and predicting the histopathological grading of malignant SPLs.

Material and methods

Chest PET, DKI and DWI scans of 73 patients with SPL were performed by PET/MRI. The apparent diffusion coefficient (ADC), mean diffusivity (MD), mean kurtosis (MK), maximum standard uptake value (SUV_max), metabolic total volume (MTV) and total lesion glycolysis (TLG) were calculated. Student’s t test or the Mann–Whitney U test was used to analyze the differences in parameters between groups. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic efficacy. Logistic regression analysis was used to evaluate independent predictors.

Results

The MK and SUV_max were significantly higher, and the MD and ADC were significantly lower in the malignant group (0.59 ± 0.13, 10.25 ± 4.20, 2.27 ± 0.51[×10^-3 mm²/s] and 1.35 ± 0.33 [×10^-3 mm²/s]) compared to the benign group (0.47 ± 0.08, 5.49 ± 4.05, 2.85 ± 0.60 [×10^-3 mm²/s] and 1.67 ± 0.33 [×10^-3 mm²/s]). The MD and ADC were significantly lower, and the MTV and TLG were significantly higher in the high-grade malignant SPLs group (2.11 ± 0.51 [×10^-3 mm²/s], 1.35 ± 0.33 [×10^-3 mm²/s], 35.87 ± 42.24 and 119.58 ± 163.65) than in the non-high-grade malignant SPLs group (2.46 ± 0.46 [×10^-3 mm²/s], 1.67 ± 0.33[×10^-3 mm²/s], 20.17 ± 32.34 and 114.20 ± 178.68). In the identification of benign and malignant SPLs, the SUV_max and MK were independent predictors, the AUCs of the combination of SUV_max and MK, SUV_max, MK, MD, and ADC were 0.875, 0.787, 0.848, 0.769, and 0.822, respectively. In the identification of high-grade and non-high-grade malignant SPLs, the AUCs of MD, ADC, MTV, and TLG were 0.729, 0.680, 0.693, and 0.711, respectively.

Conclusion

DWI, DKI, and PET in PET/MRI are all effective methods to distinguish benign from malignant SPLs, and are also helpful in evaluating the pathological grading of malignant SPLs.

Diagnostic Performance of Machine Learning Models Based on 18F-FDG PET/CT Radiomic Features in the Classification of Solitary Pulmonary Nodules

Objectives

This study aimed to evaluate the ability of ¹⁸fluorine-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features combined with machine learning methods to distinguish between benign and malignant solitary pulmonary nodules (SPN).

Methods

Data of 48 patients with SPN detected on ¹⁸F-FDG PET/CT scan were evaluated retrospectively. The texture feature extraction from PET/CT images was performed using an open-source application (LIFEx). Deep learning and classical machine learning algorithms were used to build the models. Final diagnosis was confirmed by pathology and follow-up was accepted as the reference. The performances of the models were assessed by the following metrics: Sensitivity, specificity, accuracy, and area under the receiver operator characteristic curve (AUC).

Results

The predictive models provided reasonable performance for the differential diagnosis of SPNs (AUCs ~0.81). The accuracy and AUC of the radiomic models were similar to the visual interpretation. However, when compared to the conventional evaluation, the sensitivity of the deep learning model (88% vs. 83%) and specificity of the classic learning model were higher (86% vs. 79%).

Conclusion

Machine learning based on ¹⁸F-FDG PET/CT texture features can contribute to the conventional evaluation to distinguish between benign and malignant lung nodules.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

Different Prognostic Values of Dual-Time-Point FDG PET/CT Imaging Features According to Treatment Modality in Patients with Non-Small Cell Lung Cancer

This study was aimed to investigate whether dual-time-point F-18 fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) imaging features had different prognostic values according to the treatment modality in patients with non-small cell lung cancer (NSCLC). We retrospectively reviewed 121 NSCLC patients with surgical resection (surgery group) and 69 NSCLC patients with chemotherapy and/or radiotherapy (CRT group), who underwent pretreatment dual-time-point FDG PET/CT. The maximum standardized uptake value (SUV), metabolic tumor volume (MTV), total lesion glycolysis (TLG), SUV histogram entropy of primary cancer, and the percent changes in these parameters (Δparameters) were measured. In multivariate analysis, MTV, TLG, and entropy on both early and delayed PET/CT scans were significantly associated with progression-free survival (PFS) in the surgery group, but all Δparameters failed to show a significant association. In the CRT group, TLG on the early PET, maximum SUV on the delayed PET, ΔMTV, and ΔTLG were significant independent predictors for PFS. In the surgery group, patients with high values of MTV, TLG, and entropy had worse survival, whereas, in the CRT group, patients with high values of ΔMTV and ΔTLG had better survival. Dual-time-point FDG PET/CT parameters showed different prognostic values between the surgery and CRT groups of NSCLC patients.

Prognostic Value of Dual-Time-Point [18F]FDG PET/CT for Predicting Distant Metastasis after Treatment in Patients with Non-Small Cell Lung Cancer

This study aimed to evaluate the prognostic significance of 2-Deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) uptake in the bone marrow (BM) and primary tumors on dual-time-point (DTP) PET/CT for predicting progression-free survival (PFS) and distant metastasis-free survival (DMFS) in patients with non-small cell lung cancer (NSCLC). We retrospectively analyzed DTP [18F]FDG PET/CT images from 211 patients with NSCLC. The maximum standardized uptake value (SUV) of primary lung cancer and mean [18F]FDG uptake of the BM (BM SUV) were measured from early and delayed PET/CT images, and the percent changes in these parameters (∆maximum SUV and ∆BM SUV) were calculated. On multivariate survival analysis, the maximum SUV and BM SUV on both early and delayed PET/CT scans were significantly associated with PFS, while the ∆maximum SUV and ∆BM SUV failed to show statistical significance. For DMFS, the ∆maximum SUV and ∆BM SUV were independent predictors along with the TNM stage. Distant progression was observed only in 1.3% of patients with low ∆maximum SUV and ∆BM SUV, whereas 28.2% of patients with high ∆maximum SUV and ∆BM SUV experienced distant progression. The ∆maximum SUV and ∆BM SUV on DTP [18F]FDG PET/CT were significant independent predictors for DMFS in patients with NSCLC.

The Role of Histogram-Based Textural Analysis of 18F-FDG PET/CT in Evaluating Tumor Heterogeneity and Predicting the Prognosis of Invasive Lung Adenocarcinoma

OBJECTIVES

This study aimed to investigate the contributory role of histogram-based textural features (HBTFs) extracted from 18fluorinefluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) in tumoral heterogeneity (TH) evaluation and invasive lung adenocarcinoma (ILA) prognosis prediction.

METHODS

This retrospective study analyzed the data of 72 patients with ILA who underwent 18F-FDG PET/CT followed by surgical resection. The maximum standardized uptake value (SUVmax), metabolic tumor volume, and total lesion glycolysis values were calculated for each tumor. Additionally, HBTFs were extracted from 18F-FDG PET/CT images using the software program. ILA was classified into the following five histopathological subtypes according to the predominant pattern: Lepidic adenocarcinoma (LA), acinar adenocarcinoma, papillary adenocarcinoma, solid adenocarcinoma (SA), and micropapillary adenocarcinoma (MA). Differences between 18F-FDG PET/CT parameters and histopathological subtypes were evaluated using non-parametric tests. The study endpoints include overall survival (OS) and progression-free survival (PFS). The prognostic values of clinicopathological factors and 18F-FDG PET/CT parameters were evaluated using the Cox regression analyses.

RESULTS

The median SUVmax and entropy values were significantly higher in SA-MA, whereas lower in LA. The median energy-uniformity value of the LA was significantly higher than the others. Among all parameters, only skewness and kurtosis were significantly associated with lymph node involvement status. The median values for follow-up time, PFS, and OS were 31.26, 16.07, and 20.87 months, respectively. The univariate Cox regression analysis showed that lymph node involvement was the only significant predictor for PFS. The multivariate Cox regression analysis revealed that higher SUVmax (≥11.69) and advanced stage (IIB-IIIA) were significantly associated with poorer OS [hazard ratio (HR): 3.580, p=0.024 and HR: 7.608, p=0.007, respectively].

CONCLUSION

HBTFs were tightly associated with clinicopathological factors causing TH. Among the 18F-FDG PET/CT parameters, only skewness and kurtosis were associated with lymph node involvement, whereas SUVmax was the only independent predictor of OS. TH measurement with HBTFs may contribute to conventional metabolic parameters in guiding precision medicine for ILA.

Effects of tracer uptake time in non-small cell lung cancer 18F-FDG PET radiomics

Positron emission tomography (PET) radiomics applied to oncology allows the measurement of intra-tumoral heterogeneity. This quantification can be affected by image protocols hence there is an increased interest in understanding how radiomic expression on PET images is affected by different imaging conditions. To address that, this study explores how radiomic features are affected by changes in ¹⁸F-FDG uptake time, image reconstruction, lesion delineation, and radiomics binning settings. Methods: Ten non-small cell lung cancer (NSCLC) patients underwent ¹⁸F-FDG PET scans on two consecutive days. On each day, scans were obtained at 60min and 90min post-injection and reconstructed following EARL version 1 (EARL1) and with point-spread-function resolution modelling (PSF-EARL2). Lesions were delineated using thresholds at SUV=4.0, 40% of SUV_max, and with a contrast-based isocontour. PET image intensity was discretized with both fixed bin width (FBW) and fixed bin number (FBN) before the calculation of the radiomic features. Repeatability of features was measured with intraclass correlation (ICC), and the change in feature value over time was calculated as a function of its repeatability. Features were then classified on use-case scenarios based on their repeatability and susceptibility to tracer uptake time. Results: With PSF-EARL2 reconstruction, 40% of SUV_max lesion delineation, and FBW intensity discretization, most features (94%) were repeatable at both uptake times (ICC>0.9), 39% being classified for dual-time-point use-case for being sensitive to changes in uptake time, 39% were classified for cross-sectional studies with unclear dependency on time, 20% classified for cross-sectional use while being robust to tracer uptake time changes, and 6% were discarded for poor repeatability. EARL1 images had one less repeatable feature than PSF-EARL2 (Neighborhood Gray-Level Different Matrix Coarseness), the contrast-based delineation had the poorest repeatability of the delineation methods with 45% features being discarded, and FBN resulted in lower repeatability than FBW (45% and 6% features were discarded, respectively). Conclusion: Repeatability was maximized with PSF-EARL2 reconstruction, lesion delineation at 40% of SUV_max, and FBW intensity discretization. Based on their susceptibility to tracer uptake time, radiomic features were classified into specific NSCLC PET radiomics use-cases.

18F-FDG texture analysis predicts the pathological Fuhrman nuclear grade of clear cell renal cell carcinoma

PURPOSE

This article analyzes the image heterogeneity of clear cell renal cell carcinoma (ccRCC) based on positron emission tomography (PET) and positron emission tomography-computed tomography (PET/CT) texture parameters, and provides a new objective quantitative parameter for predicting pathological Fuhrman nuclear grading before surgery.

METHODS

A retrospective analysis was performed on preoperative PET/CT images of 49 patients whose surgical pathology was ccRCC, 27 of whom were low grade (Fuhrman I/II) and 22 of whom were high grade (Fuhrman III/IV). Radiological parameters and standard uptake value (SUV) indicators on PET and computed tomography (CT) images were extracted by using the LIFEx software package. The discriminative ability of each texture parameter was evaluated through receiver operating curve (ROC). Binary logistic regression analysis was used to screen the texture parameters with distinguishing and diagnostic capabilities and whose area under curve (AUC) > 0.5. DeLong's test was used to compare the AUCs of PET texture parameter model and PET/CT texture parameter model with traditional maximum standardized uptake value (SUVmax) model and the ratio of tumor SUVmax to liver SUVmean (SUL)model. In addition, the models with the larger AUCs among the SUV models and texture models were prospectively internally verified.

RESULTS

In the ROC curve analysis, the AUCs of SUVmax model, SUL model, PET texture parameter model, and PET/CT texture parameter model were 0.803, 0.819, 0.873, and 0.926, respectively. The prediction ability of PET texture parameter model or PET/CT texture parameter model was significantly better than SUVmax model (P = 0.017, P = 0.02), but it was not better than SUL model (P = 0.269, P = 0.053). In the prospective validation cohort, both the SUL model and the PET/CT texture parameter model had good predictive ability, and the AUCs of them were 0.727 and 0.792, respectively.

CONCLUSION

PET and PET/CT texture parameter models can improve the prediction ability of ccRCC Fuhrman nuclear grade; SUL model may be the more accurate and easiest way to predict ccRCC Fuhrman nuclear grade.

Baseline 18F-FDG PET textural features as predictors of response to chemotherapy in diffuse large B-cell lymphoma

PURPOSE

We sought to investigate the performance of radiomics analysis on baseline 18F-FDG PET/CT for predicting response to first-line chemotherapy in diffuse large B-cell lymphoma (DLBCL).

MATERIAL AND METHODS

Forty-five patients who received first-line rituximab, cyclophosphamide, doxorubicin, vincristine and prednisone (R-CHOP) chemotherapy for DLBCL were included in the study. Radiomics features and standard uptake value (SUV)-based measurements were extracted from baseline PET images for a total of 147 lesions. The selection of the most relevant features was made using the recursive feature elimination algorithm. A machine-learning model was trained using the logistic regression classifier with cross-validation to predict treatment response. The independent predictors of incomplete response were evaluated with multivariable regression analysis.

RESULTS

A total of 14 textural features were selected by the recursive elimination algorithm, achieving a feature-to-lesion ratio of 1:10. The accuracy and area under the receiver operating characteristic curve of the model for predicting incomplete response were 0.87 and 0.81, respectively. Multivariable analysis revealed that SUVmax and gray level co-occurrence matrix dissimilarity were independent predictors of lesions with incomplete response to first-line R-CHOP chemotherapy.

CONCLUSION

Increased textural heterogeneity in baseline PET images was found to be associated with incomplete response in DLBCL.

Generation of parametric Ki images for FDG PET using two 5-min scans

PURPOSE

The net uptake rate constant (K_i ) derived from dynamic imaging is considered the gold standard quantification index for FDG PET. In this study, we investigated the feasibility and assessed the clinical usefulness of generating K_i images for FDG PET using only two 5-min scans with population-based input function (PBIF).

METHODS

Using a Siemens Biograph mCT, 10 subjects with solid lung nodules underwent a single-bed dynamic FDG PET scan and 13 subjects (five healthy and eight cancer patients) underwent a whole-body dynamic FDG PET scan in continuous-bed-motion mode. For each subject, a standard K_i image was generated using the complete 0-90 min dynamic data with Patlak analysis (t* = 20 min) and individual patient's input function, while a dual-time-point K_i image was generated from two 5-min scans based on the Patlak equations at early and late scans with the PBIF. Different start times for the early (ranging from 20 to 55 min with an increment of 5 min) and late (ranging from 50 to 85 min with an increment of 5 min) scans were investigated with the interval between scans being at least 30 min (36 protocols in total). The optimal dual-time-point protocols were then identified. Regions of interest (ROI) were drawn on nodules for the lung nodule subjects, and on tumors, cerebellum, and bone marrow for the whole-body-imaging subjects. Quantification accuracy was compared using the mean value of each ROI between standard K_i (gold standard) and dual-time-point K_i , as well as between standard K_i and relative standardized uptake value (SUV) change that is currently used in clinical practice. Correlation coefficients and least squares fits were calculated for each dual-time-point protocol and for each ROI. Then, the predefined criteria for identifying a reliable dual-time-point K_i estimation for each ROI were empirically determined as: (1) the squared correlation coefficient (R² ) between standard K_i and dual-time-point K_i is larger than 0.9; (2) the absolute difference between the slope of the equality line (1.0) and that of the fitted line when plotting standard K_i versus dual-time-point K_i is smaller than 0.1; (3) the absolute value of the intercept of the fitted line when plotting standard K_i versus dual-time-point K_i normalized by the mean of the standard K_i across all subjects for each ROI is smaller than 10%. Using Williams' one-tailed t test, the correlation coefficient (R) between standard K_i and dual-time-point K_i was further compared with that between standard K_i and relative SUV change, for each dual-time-point protocol and for each ROI.

RESULTS

Reliable dual-time-point K_i images were obtained for all the subjects using our proposed method. The percentage error introduced by the PBIF on the dual-time-point K_i estimation was smaller than 1% for all 36 protocols. Using the predefined criteria, reliable dual-time-point K_i estimation could be obtained in 25 of 36 protocols for nodules and in 34 of 36 protocols for tumors. A longer time interval between scans provided a more accurate K_i estimation in general. Using the protocol of 20-25 min plus 80-85 or 85-90 min, very high correlations were obtained between standard K_i and dual-time-point K_i (R²  = 0.994, 0.980, 0.971 and 0.925 for nodule, tumor, cerebellum, and bone marrow), with all the slope values with differences ≤0.033 from 1 and all the intercept values with differences ≤0.0006 mL/min/cm³ from 0. The corresponding correlations were much lower between standard K_i and relative SUV change (R²  = 0.673, 0.684, 0.065, 0.246). Dual-time-point K_i showed a significantly higher quantification accuracy with respect to standard K_i than relative SUV change for all the 36 protocols (p < 0.05 using Williams' one-tailed t test).

CONCLUSIONS

Our proposed approach can obtain reliable K_i images and accurate K_i quantification from dual-time-point scans (5-min per scan), and provide significantly higher quantification accuracy than relative SUV change that is currently used in clinical practice.

Radiomics model of dual-time 2-[18F]FDG PET/CT imaging to distinguish between pancreatic ductal adenocarcinoma and autoimmune pancreatitis

OBJECTIVES

Pancreatic ductal adenocarcinoma (PDAC) and autoimmune pancreatitis (AIP) are diseases with a highly analogous visual presentation that are difficult to distinguish by imaging. The purpose of this research was to create a radiomics-based prediction model using dual-time PET/CT imaging for the noninvasive classification of PDAC and AIP lesions.

METHODS

This retrospective study was performed on 112 patients (48 patients with AIP and 64 patients with PDAC). All cases were confirmed by imaging and clinical follow-up, and/or pathology. A total of 502 radiomics features were extracted from the dual-time PET/CT images to develop a radiomics decision model. An additional 12 maximum intensity projection (MIP) features were also calculated to further improve the radiomics model. The optimal radiomics feature set was selected by support vector machine recursive feature elimination (SVM-RFE), and the final classifier was built using a linear SVM. The performance of the proposed dual-time model was evaluated using nested cross-validation for accuracy, sensitivity, specificity, and area under the curve (AUC).

RESULTS

The final prediction model was developed from a combination of the SVM-RFE and linear SVM with the required quantitative features. The multimodal and multidimensional features performed well for classification (average AUC: 0.9668, accuracy: 89.91%, sensitivity: 85.31%, specificity: 96.04%).

CONCLUSIONS

The radiomics model based on 2-[¹⁸F]fluoro-2-deoxy-D-glucose (2-[¹⁸F]FDG) PET/CT dual-time images provided promising performance for discriminating between patients with benign AIP and malignant PDAC lesions, which shows its potential for use as a diagnostic tool for clinical decision-making.

KEY POINTS

• The clinical symptoms and imaging visual presentations of PDAC and AIP are highly similar, and accurate differentiation of PDAC and AIP lesions is difficult. • Radiomics features provided a potential noninvasive method for differentiation of AIP from PDAC. • The diagnostic performance of the proposed radiomics model indicates its potential to assist doctors in making treatment decisions.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Quantitative FDG PET Assessment for Oncology Therapy

Simple Summary

PET enables quantitative assessment of tumour biology in vivo. Accumulation of F-18 fluorodeoxyglucose (FDG) may reflect tumour metabolic activity. Quantitative assessment of FDG uptake can be applied for treatment monitoring. Numerous studies indicated biochemical change assessed by FDG-PET as a more sensitive marker than morphological change. Those with complete metabolic response after therapy may show better prognosis. Assessment of metabolic change may be performed using absolute FDG uptake or metabolic tumour volume. More recently, radiomics approaches have been applied to FDG PET. Texture analysis quantifies intratumoral heterogeneity in a voxel-by-voxel basis. Combined with various machine learning techniques, these new quantitative parameters hold a promise for assessing tissue characterization and predicting treatment effect, and could also be used for future prognosis of various tumours.

Abstract

Positron emission tomography (PET) has unique characteristics for quantitative assessment of tumour biology in vivo. Accumulation of F-18 fluorodeoxyglucose (FDG) may reflect tumour characteristics based on its metabolic activity. Quantitative assessment of FDG uptake can often be applied for treatment monitoring after chemotherapy or chemoradiotherapy. Numerous studies indicated biochemical change assessed by FDG PET as a more sensitive marker than morphological change estimated by CT or MRI. In addition, those with complete metabolic response after therapy may show better disease-free survival and overall survival than those with other responses. Assessment of metabolic change may be performed using absolute FDG uptake in the tumour (standardized uptake value: SUV). In addition, volumetric parameters such as metabolic tumour volume (MTV) have been introduced for quantitative assessment of FDG uptake in tumour. More recently, radiomics approaches that focus on image-based precision medicine have been applied to FDG PET, as well as other radiological imaging. Among these, texture analysis extracts intratumoral heterogeneity on a voxel-by-voxel basis. Combined with various machine learning techniques, these new quantitative parameters hold a promise for assessing tissue characterization and predicting treatment effect, and could also be used for future prognosis of various tumours, although multicentre clinical trials are needed before application in clinical settings.

Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach

PURPOSE

This study was designed and performed to assess the ability of ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomics features combined with machine learning methods to differentiate between primary and metastatic lung lesions and to classify histological subtypes. Moreover, we identified the optimal machine learning method.

METHODS

A total of 769 patients pathologically diagnosed with primary or metastatic lung cancers were enrolled. We used the LIFEx package to extract radiological features from semiautomatically segmented PET and CT images within the same volume of interest. Patients were randomly distributed in training and validation sets. Through the evaluation of five feature selection methods and nine classification methods, discriminant models were established. The robustness of the procedure was controlled by tenfold cross-validation. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

Based on the radiomics features extracted from PET and CT images, forty-five discriminative models were established. Combined with appropriate feature selection methods, most classifiers showed excellent discriminative ability with AUCs greater than 0.75. In the differentiation between primary and metastatic lung lesions, the feature selection method gradient boosting decision tree (GBDT) combined with the classifier GBDT achieved the highest classification AUC of 0.983 in the PET dataset. In contrast, the feature selection method eXtreme gradient boosting combined with the classifier random forest (RF) achieved the highest AUC of 0.828 in the CT dataset. In the discrimination between squamous cell carcinoma and adenocarcinoma, the combination of GBDT feature selection method with GBDT classification had the highest AUC of 0.897 in the PET dataset. In contrast, the combination of the GBDT feature selection method with the RF classification had the highest AUC of 0.839 in the CT dataset. Most of the decision tree (DT)-based models were overfitted, suggesting that the classification method was not appropriate for practical application.

CONCLUSION

¹⁸F-FDG PET/CT radiomics features combined with machine learning methods can distinguish between primary and metastatic lung lesions and identify histological subtypes in lung cancer. GBDT and RF were considered optimal classification methods for the PET and CT datasets, respectively, and GBDT was considered the optimal feature selection method in our analysis.

Texture Analysis Improves the Value of Pretreatment 18F-FDG PET/CT in Predicting Interim Response of Primary Gastrointestinal Diffuse Large B-Cell Lymphoma

Objectives

To explore the application of pretreatment 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) texture analysis (TA) in predicting the interim response of primary gastrointestinal diffuse large B-cell lymphoma (PGIL-DLBCL).

Methods

Pretreatment 18F-FDG PET/CT images of 30 PGIL-DLBCL patients were studied retrospectively. The interim response was evaluated after 3-4 cycles of chemotherapy. The complete response (CR) rates in patients with different clinicopathological characteristics were compared by Fisher's exact test. The differences in the maximum standard uptake value (SUVmax), metabolic tumor volume (MTV), and texture features between the CR and non-CR groups were compared by the Mann-Whitney U test. Feature selection was performed according to the results of the Mann-Whitney U test and feature categories. The predictive efficacies of the SUVmax, MTV, and the selected texture features were assessed by receiver operating characteristic (ROC) analysis. A prediction probability was generated by binary logistic regression analysis.

Results

The SUVmax, MTV, some first-order texture features, volume, and entropy were significantly higher in the non-CR group. The energy was significantly lower in the non-CR group. The SUVmax, volume, and entropy were excellent predictors of the interim response, and the areas under the curves (AUCs) were 0.850, 0.805, and 0.800, respectively. The CR rate was significantly lower in patients with intestinal involvement. The prediction probability generated from the combination of the SUVmax, entropy, volume, and intestinal involvement had a higher AUC (0.915) than all single parameters.

Conclusions

TA has potential in improving the value of pretreatment PET/CT in predicting the interim response of PGIL-DLBCL. However, prospective studies with large sample sizes and validation analyses are needed to confirm the current results.