Limited diagnostic value of Dual-Time-Point 18 F-FDG PET/CT imaging for classifying solitary pulmonary nodules in granuloma-endemic regions both at visual and quantitative analyses

A machine learning-based PET/CT model for automatic diagnosis of early-stage lung cancer

Objective

The aim of this study was to develop a machine learning-based automatic analysis method for the diagnosis of early-stage lung cancer based on positron emission tomography/computed tomography (PET/CT) data.

Methods

A retrospective cohort study was conducted using PET/CT data from 187 cases of non-small cell lung cancer (NSCLC) and 190 benign pulmonary nodules. Twelve PET and CT features were used to train a diagnosis model. The performance of the machine learning-based PET/CT model was tested and validated in two separate cohorts comprising 462 and 229 cases, respectively.

Results

The standardized uptake value (SUV) was identified as an important biochemical factor for the early stage of lung cancer in this model. The PET/CT diagnosis model had a sensitivity and area under the curve (AUC) of 86.5% and 0.89, respectively. The testing group comprising 462 cases showed a sensitivity and AUC of 85.7% and 0.87, respectively, while the validation group comprising 229 cases showed a sensitivity and AUC of 88.4% and 0.91, respectively. Additionally, the proposed model improved the clinical discrimination ability for solid pulmonary nodules (SPNs) in the early stage significantly.

Conclusion

The feature data collected from PET/CT scans can be analyzed automatically using machine learning techniques. The results of this study demonstrated that the proposed model can significantly improve the accuracy and positive predictive value (PPV) of SPNs at the early stage. Furthermore, this algorithm can be optimized into a robotic and less biased PET/CT automatic diagnosis system.

Molecular Imaging of Tuberculosis

Despite the introduction of many novel diagnostic techniques and newer treatment agents, tuberculosis (TB) remains a major cause of death from an infectious disease worldwide. With about a quarter of humanity harboring Mycobacterium tuberculosis, the causative agent of TB, the current efforts geared towards reducing the scourge due to TB must be sustained. At the same time, newer alternative modalities for diagnosis and treatment response assessment are considered. Molecular imaging entails the use of radioactive probes that exploit molecular targets expressed by microbes or human cells for imaging using hybrid scanners that provide both anatomic and functional features of the disease being imaged. Fluorine-18 fluorodeoxyglucose (FDG) is the most investigated radioactive probe for TB imaging in research and clinical practice. When imaged with positron emission tomography interphase with computed tomography (PET/CT), FDG PET/CT performs better than sputum conversion for predicting treatment outcome. At the end of treatment, FDG PET/CT has demonstrated the unique ability to identify a subset of patients declared cured based on the current standard of care but who still harbor live bacilli capable of causing disease relapse after therapy discontinuation. Our understanding of the pathogenesis and evolution of TB has improved significantly in the last decade, owing to the introduction of FDG PET/CT in TB research. FDG is a non-specific probe as it targets the host inflammatory response to Mycobacterium tuberculosis, which is not specifically different in TB compared with other infectious conditions. Ongoing efforts are geared towards evaluating the utility of newer probes targeting different components of the TB granuloma, the hallmark of TB lesions, including hypoxia, neovascularization, and fibrosis, in TB management. The most exciting category of non-FDG PET probes developed for molecular imaging of TB appears to be radiolabeled anti-tuberculous drugs for use in studying the pharmacokinetic characteristics of the drugs. This allows for the non-invasive study of drug kinetics in different body compartments concurrently, providing an insight into the spatial heterogeneity of drug exposure in different TB lesions. The ability to repeat molecular imaging using radiolabeled anti-tuberculous agents also offers an opportunity to study the temporal changes in drug kinetics within the different lesions during treatment.

FDG PET/CT signs of proven pulmonary hydatid cyst: is there any clue?

PURPOSE

Pulmonary hydatid cyst (PHC) can imitate many diseases. Sometimes, positron emission tomography/computed tomography (PET/CT) is performed in terms of malignancy exclusion for complicated cysts. Although some specific findings (doughnut sign) have been identified in hydatid cyst of the liver, there is no specific sign described for PHC. The aim of this study is to investigate the presence of a common finding in PHC patients scanned with PET/CT inadvertently.

MATERIALS AND METHODS

From January 2015 to 2020, patients proven to have PHC were analyzed retrospectively. From all the patients, only 17, having a previous PET/CT, were included the study. Lesions were evaluated in three groups according to FDG uptake: A, negative; B, focal; C, doughnut sign.

RESULTS

The total number of patients was 17. Nine of the patients were male and the median age was 41.94 + 14.68 (16-65) years. SUV max of the lesions ranged from 0.5 to 15.8 (mean ± SE: 4.68). According to the FDG uptake of the lesions, five were in Group A, two in Group B, and the remaining ten (58.8%) in Group C with doughnut sign. To correlate the CT findings with PET/CT findings, doughnut sign, which is a typical finding of hydatid cysts of liver, is seen in only four patients in Group 1-classified cysts which are non-complicated. But in Group 2 (n = 3) and 3(n = 4), the finding of doughnut sign is three in both groups.

CONCLUSIONS

PET/CT is not a recommended imaging technique for PHC, but in cases where a definitive diagnosis is difficult, interpreting PET/CT findings is significant. This study demonstrates that previously described doughnut sign for liver hydatid cysts is also common for perforated pulmonary cysts. According to our knowledge, this is the first largest series of determining PET/CT findings of PHC. Further larger series will contribute to the literature.

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.

Role of Imaging in a Case of Toxoplasmosis Presenting as Generalized Lymphadenopathy

Toxoplasmosis is caused by Toxoplasma gondii an obligate protozoan intracellular parasite. The disease has variable prevalence globally and is usually asymptomatic. Pregnant and immunocompromised people are at risk of getting infected. Enlarged lymph nodes are the most frequently observed clinical form of Toxoplasma in humans, mostly affecting posterior cervical nodes. Other organs usually affected are the brain and eyes. We present a case of toxoplasmosis with generalized lymphadenopathy mimicking metastasis in a lady with a previous history of operated pancreatic neoplasm.

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.

Diagnostic accuracy of visual analysis versus dual time-point imaging with 18F-FDG PET/CT for the characterization of indeterminate pulmonary nodules with low uptake

OBJECTIVE

To determine the accuracy of visual analysis and the retention index (RI) with dual-time point ¹⁸F-FDG PET/CT for the characterization of indeterminate pulmonary nodules (IPN) with low FDG uptake.

MATERIALS AND METHODS

A retrospective analysis was performed on 43 patients (28 men, 64 ± 11 years old, range 36-83 years) referred for IPN characterization with ¹⁸F-FDG-PET/CT and maximum standard uptake value ≤ 2.5 at 60 minutes post-injection (SUV_max1). Nodules were analyzed by size, visual score for FDG uptake on standard (OSEM 2,8) and high definition (HD) reconstructions, SUV_max1, SUV_max at 180 minutes post-injection (SUV_max2), and RI was calculated. The definitive diagnosis was based on histopathological confirmation (n = 28) or ≥ 2 years of follow-up.

RESULTS

Twenty-four (56%) nodules were malignant. RI ≥ 10% on standard reconstruction detected 18 nodules that would have been considered negative using the standard SUV_max ≥ 2.5 criterion for malignancy. RI ≥ 10% had a sensitivity, specificity, PPV, NPV and accuracy of 75, 73.7, 78.3, 70, and 74.4%, respectively, while for FDG uptake > liver on HD these were 79.1, 63.2, 73.1, 70.6, and 72.1%, respectively. SUV_max1 ≥ 2, SUV_max2 > 2.5 and FDG uptake > liver on standard reconstruction had a PPV of 100%. FDG uptake > mediastinum on HD had a NPV of 100%.

CONCLUSIONS

RI ≥ 10% was the most accurate criterion for malignancy, followed by FDG uptake > liver on HD reconstruction. On standard reconstruction, SUV_max1 ≥2 was highly predictive of malignancy, as well as SUV_max2 > 2.5 and FDG uptake > liver. FDG uptake < mediastinum on HD was highly predictive of benign nodules.

Comparison of the diagnostic accuracy of diffusion-weighted and dynamic contrast-enhanced MRI with 18F-FDG PET/CT to differentiate osteomyelitis from Charcot neuro-osteoarthropathy in diabetic foot

PURPOSE

To compare the diagnostic accuracy of diffusion-weighted imaging (DWI) and dynamic contrast-enhanced-magnetic resonance imaging (DCE-MRI) involving two region of interest (ROI) sizes with 18-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) to differentiate diabetic foot osteomyelitis (DFO) from Charcot neuro-osteoarthropathy (CN).

METHOD

Thirty-one diabetic patients were included in this prospective study. Two readers independently evaluated DWI (apparent diffusion coefficient [ADC] and high-b-value signal pathological-to-normal bone ratio [DWIr]) and DCE-MRI parameters (K^trans, K_ep, V_e, internal area under the gadolinium curve at 60 s [iAUC₆₀] and time intensity curve [TIC]) using two different ROI sizes, and ¹⁸F-FDG PET/CT parameters (visual assessment, SUV_max, delayed SUV_max, and percentage changes between SUV_max and delayed SUV_max). Techniques were compared by univariate analysis using the area under the receiver operating characteristic curve [AUC]. Reliability was analyzed with Kappa and Intraclass correlation [ICC].

RESULTS

DWIr, K^trans and iAUC₆₀ showed better diagnostic accuracy (AUC = 0.814-0.830) and reliability (ICC > 0.9) for large than for small ROIs (AUC = 0.736-0.750; ICC = 0.6 in K^trans, 0.8 in DWIr and iAUC₆₀). TIC showed moderate diagnostic performance (AUC = 0.739-0.761) and reliability (κ 0.7). Visual assessment of ¹⁸F-FDG PET/CT demonstrated a significantly higher accuracy (AUC = 0.924) than MRI parameters. Semi-quantitative ¹⁸F-FDG PET/CT parameters did not provide significant improvement over visual analysis (AUC = 0.848-0.903).

CONCLUSION

DWIr, K^trans and iAUC₆₀ allowed reliable differentiation of DFO and CN, particularly for large ROIs. Visual assessment of ¹⁸F-FDG PET/CT was the most accurate technique for differentiation.

Evaluation of the diagnostic efficacy of 18 F-Fluorine-2-Deoxy-D-Glucose PET/CT for lung cancer and pulmonary tuberculosis in a Tuberculosis-endemic Country

OBJECTIVE

To determine the diagnostic efficacy of ¹⁸ F-FDG PET/CT in distinguishing between pulmonary tuberculosis (PTB) and lung cancer in solitary pulmonary nodule (SPN) in a country with a high prevalence of PTB.

METHODS

Patients with SPN who underwent ¹⁸ F-FDG PET/CT imaging were retrospectively included in the study. The final diagnosis was established by histopathology. A linear regression equation was fitted to a scatter plot of size and SUVmax of lung cancer and PTB. ROC was used to determine the optimal cutoff values and diagnostic accuracy of ¹⁸ F-FDG PET/CT in PTB and lung cancer.

RESULTS

About 514 patients were included with the mean age of 57.5 ± 10.6 years. Four hundred and seventy-five cases were diagnosed as lung cancer, and 39 cases were PTB by histopathology. ¹⁸ F-FDG PET/CT had sensitivity, specificity, and diagnostic accuracy of 96.0%, 48.7%, and 92.0%, respectively. Utilization of SUVmax ≥2.5 in SPN resulted in 2 and 11 false positives cases of lung cancer and PTB, respectively, whereas SUVmax <2.5 resulted in 18 and 10 false-positive cases of lung cancer and PTB, respectively. The SUVmax and the size of short-axis in the lung cancer group were statistically higher than those in the PTB group. The linear regression equation parameters indicated the slope of the regression line of lung cancer was greater than that of PTB. The ROC curve demonstrated the SUVmax cutoff values of 4.85 and 2.25 for lung cancer and PTB, respectively for predicting the diagnostic accuracy of ¹⁸ F-FDG PET/CT.

CONCLUSION

¹⁸ F-FDG PET/CT has a higher sensitivity and diagnostic accuracy for malignant SPN. However, it has high false-positive rate and low specificity in tuberculosis endemic areas. Neither SUVmax nor the sizes of the nodules are valuable parameters for distinguishing between lung cancer and PTB. However, the SPN with larger short-axis and higher SUVmax would be inclined to malignant tumor.

Using neighborhood gray tone difference matrix texture features on dual time point PET/CT images to differentiate malignant from benign FDG-avid solitary pulmonary nodules

OBJECTIVE

Lung cancer usually presents as a solitary pulmonary nodule (SPN) on diagnostic imaging during the early stages of the disease. Since the early diagnosis of lung cancer is very important for treatment, the accurate diagnosis of SPNs has much importance. The aim of this study was to evaluate the discriminant power of dual time point imaging (DTPI) PET/CT in the differentiation of malignant and benign FDG-avid solitary pulmonary nodules by using neighborhood gray-tone difference matrix (NGTDM) texture features.

METHODS

Retrospective analysis was carried out on 116 patients with SPNs (35 benign and 81 malignant) who had DTPI ¹⁸F-FDG PET/CT between January 2005 and May 2015. Both PET and CT images were acquired at 1 h and 3 h after injection. The SUV_max and NGTDM texture features (coarseness, contrast, and busyness) of each nodule were calculated on dual time point images. Patients were randomly divided into training and validation datasets. Receiver operating characteristic (ROC) curve analysis was performed on all texture features in the training dataset to calculate the optimal threshold for differentiating malignant SPNs from benign SPNs. For all the lesions in the testing dataset, two visual interpretation scores were determined by two nuclear medicine physicians based on the PET/CT images with and without reference to the texture features.

RESULTS

In the training dataset, the AUCs of delayed busyness, delayed coarseness, early busyness, and early SUV_max were 0.87, 0.85, 0.75 and 0.75, respectively. In the validation dataset, the AUCs of visual interpretations with and without texture features were 0.89 and 0.80, respectively.

CONCLUSION

Compared to SUV_max or visual interpretation, NGTDM texture features derived from DTPI PET/CT images can be used as good predictors of SPN malignancy. Improvement in discriminating benign from malignant nodules using SUVmax and visual interpretation can be achieved by adding busyness extracted from delayed PET/CT images.

Improved discrimination between benign and malignant LDCT screening-detected lung nodules with dynamic over static 18F-FDG PET as a function of injected dose

Lung cancer mortality rate can be significantly reduced by up to 20% through routine low-dose computed tomography (LDCT) screening, which, however, has high sensitivity but low specificity, resulting in a high rate of false-positive nodules. Combining PET with CT may provide more accurate diagnosis for indeterminate screening-detected nodules. In this work, we investigated low-dose dynamic 18F-FDG PET in discrimination between benign and malignant nodules using a virtual clinical trial based on patient study with ground truth. Six patients with initial LDCT screening-detected lung nodules received 90 min single-bed PET scans following a 10 mCi FDG injection. Low-dose static and dynamic images were generated from under-sampled list-mode data at various count levels (100%, 50%, 10%, 5%, and 1%). A virtual clinical trial was performed by adding nodule population variability, measurement noise, and static PET acquisition start time variability to the time activity curves (TACs) of the patient data. We used receiver operating characteristic (ROC) analysis to estimate the classification capability of standardized uptake value (SUV) and net uptake constant K i from their simulated benign and malignant distributions. Various scan durations and start times (t *) were investigated in dynamic Patlak analysis to optimize simplified acquisition protocols with a population-based input function (PBIF). The area under curve (AUC) of ROC analysis was higher with increased scan duration and earlier t *. Highly similar results were obtained using PBIF to those using image-derived input function (IDIF). The AUC value for K i using optimized t * and scan duration with 10% dose was higher than that for SUV with 100% dose. Our results suggest that dynamic PET with as little as 1 mCi FDG could provide discrimination between benign and malignant lung nodules with higher than 90% sensitivity and specificity for patients similar to the pilot and simulated population in this study, with LDCT screening-detected indeterminate lung nodules.

Diagnostic performance of fluorine-18 fluorodeoxyglucose positron emission tomography in the management of solitary pulmonary nodule: a meta-analysis

Background

In the setting of solitary pulmonary nodules (SPNs), fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG-PET/CT) is considered a useful non-invasive diagnostic tool though false positive (FP) and false negative (FN) results affects accuracy due to different conditions, such as inflammatory diseases or low-uptake neoplasms. Aim of this study is to evaluate overall diagnostic performance of ¹⁸F-FDG-PET/CT for malignant pulmonary nodules.

Methods

A computerized research, including published articles from 2012 and 2017, was carried out. ¹⁸F-FDG-PET/CT overall sensitivity (Se), specificity (Spe), positive likelihood ratio (PLR), negative likelihood ratio (NLR), positive predictive value (PPV), negative predictive value (NPV), diagnostic index and odds ratio were pooled. No selection-bias were found according to asymmetry test.

Results

A total of twelve studies were included in the meta-analysis. The pooled Se, Spe, PLR, NLR, PPV, NPV and accuracy index (AI) with relative 95% confidence intervals (CI) were 0.819 (95% CI: 0.794-0.843), 0.624 (95% CI: 0.582-0.665), 2.190 (95% CI: 1.950-2.440), 0.290 (95% CI: 0.250-0.330), 0.802 (95% CI: 0.783-0.819), 0.652 (95% CI: 0.618-0.684) and 0.649 (95% CI: 0.625-0.673), respectively. The diagnostic odds ratio (DOR) was 7.049 with a relative 95% CI between 5.550 and 8.944.

Conclusions

The results suggest ¹⁸F-FDG-PET/CT has good diagnostic accuracy in SPNs evaluation; but, it should not be considered as a discriminatory test rather than a method to be included in a clinical and diagnostic pathway.

18F-Fluoro-2-Deoxy-d-Glucose PET/Computed Tomography Evaluation of Lung Cancer in Populations with High Prevalence of Tuberculosis and Other Granulomatous Disease

Pulmonary tuberculosis infects one-third of world's population and is responsible for the high mortality and morbidity in developing countries. The presence of a high number of macrophages and lymphocytes in active tuberculosis granulomas is associated with high uptake of ¹⁸F-fluoro-2-deoxy-d-glucose on PET imaging mimicking lung cancer. In many cases, radiological features of pulmonary tuberculosis are undistinguishable from lung cancer, which makes the diagnosis difficult. Clinical history and computed tomographic (CT) findings on a hybrid PET/CT are as important as findings on a PET in the diagnosis of lung cancer.

Diagnostic classification of solitary pulmonary nodules using dual time 18F-FDG PET/CT image texture features in granuloma-endemic regions

Lung cancer, the most commonly diagnosed cancer worldwide, usually presents as solid pulmonary nodules (SPNs) on early diagnostic images. Classification of malignant disease at this early timepoint is critical for improving the success of surgical resection and increasing 5-year survival rates. ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET/CT has demonstrated value for SPNs diagnosis with high sensitivity to detect malignant SPNs, but lower specificity in diagnosing malignant SPNs in populations with endemic infectious lung disease. This study aimed to determine whether quantitative heterogeneity derived from various texture features on dual time FDG PET/CT images (DTPI) can differentiate between malignant and benign SPNs in patients from granuloma-endemic regions. Machine learning methods were employed to find optimal discrimination between malignant and benign nodules. Machine learning models trained by texture features on DTPI images achieved significant improvements over standard clinical metrics and visual interpretation for discriminating benign from malignant SPNs, especially by texture features on delayed FDG PET/CT images.