Derivation and validation of a 18F-FDG PET/CT scoring model to predict malignant pleural effusion.

OBJECTIVE: To develop an 18F-fluorodeoxyglucose PET/computed tomography (CT) scoring model based on metabolic and radiologic findings of the pleura and fluid to identify malignant pleural effusion. METHODS: The PET and CT findings from patients with pleural effusion in the derivation dataset were used to develop a scoring model. Then, the diagnostic accuracy of the predictive score was verified by the validation dataset. RESULTS: Eight parameters independently predicting malignancy were retained in the scoring model, including pleural nodules or masses (4 points), focal pleural thickening (2 points), absence of pleural loculation (2 points), thickness of mediastinal pleura involvement ≥0.5 cm (2 points), maximum standardized uptake value (SUVmax) of mediastinal pleura involvement ≥2.3 (2 points), thickness of nonmediastinal pleura involvement ≥0.5 cm (1 point), SUVmax of nonmediastinal pleura involvement ≥3.0 (1 point) and fluid SUVmax ≥1.6 (1 point). The operating characteristics of the PET/CT score were 0.958 area under the curve (AUC), 88.6% sensitivity, 91.2% specificity, 10.09 positive likelihood ratio and 0.13 negative likelihood ratio, with 6 points as the threshold. These values in the validation dataset were 0.947, 91.7%, 88.4%, 7.91 and 0.094, respectively. No difference was found in AUCs between the derivation and validation datasets (z = 0.517, P = 0.697). The negative predictive value was 99.4% in the score from 0 to 2, and the positive predictive value was 98.3% for patients with score between 9 and 15. CONCLUSIONS: The PET/CT scoring model is a valuable strategy to help physicians to distinguish malignant-benign pleural effusion and stratify patients who will benefit from invasive procedures.

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

BACKGROUND: This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. RESULTS: For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. CONCLUSIONS: The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.

Predictive Role of the Number of 18F-FDG-Positive Lymph Nodes Detected by PET/CT for Pre-Treatment Evaluation of Locally Advanced Gastric Cancer.

OBJECTIVES: The aim of this study was to investigate the predictive value of the numbers of metabolically positive lymph nodes (MPLN) detected by 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) in patients with locally advanced gastric cancer (LAGC). METHODS: We retrospectively analyzed the records of 50 patients with LAGC (stage T2-T4) who had undergone pre-operative PET/CT examination and laparotomy (total gastrectomy, n = 11; subtotal gastrectomy, n = 13; distal gastrectomy, n = 22; and bypass with gastrojejunstomy, n = 4). The numbers of MPLN were determined by combining visual observations with semi-quantitative measurements of the maximized standardized uptake value (SUVmax). Performance was investigated in terms of predicting post-surgical overall survival (OS). RESULTS: The median post-surgical OS was 32.57 months (range 3.0-94 months). The numbers of MPLN were moderately correlated with the numbers of histological positive LN (r = 0.694, p = 0.001). In univariate analyses, the numbers of MPLN (≤ 2 vs. ≥3), PET/CT LN (positivity vs. negativity), SUVmax of LN (< 2.8 vs. ≥ 2.8), TNM stage (I, II vs. III, IV), and surgery type (R0 vs. non-R0) were significantly associated with OS. In multivariate analysis, surgery type (R0 vs. non-R0) and numbers of MPLN (≤ 2 vs. ≥ 3) were both independent factors for poor OS. CONCLUSIONS: This explored study indicates that the number of MPLN could provide additional information for LAGC prognosis. Patients with MPLNs ≥ 3 may be at the risk of the more bad outcomes, and the further clinical trials are needed.

The Role of 18F-FDG PET/CT Integrated Imaging in Distinguishing Malignant from Benign Pleural Effusion.

OBJECTIVE: The aim of our study was to evaluate the role of 18F-FDG PET/CT integrated imaging in differentiating malignant from benign pleural effusion. METHODS: A total of 176 patients with pleural effusion who underwent 18F-FDG PET/CT examination to differentiate malignancy from benignancy were retrospectively researched. The images of CT imaging, 18F-FDG PET imaging and 18F-FDG PET/CT integrated imaging were visually analyzed. The suspected malignant effusion was characterized by the presence of nodular or irregular pleural thickening on CT imaging. Whereas on PET imaging, pleural 18F-FDG uptake higher than mediastinal activity was interpreted as malignant effusion. Images of 18F-FDG PET/CT integrated imaging were interpreted by combining the morphologic feature of pleura on CT imaging with the degree and form of pleural 18F-FDG uptake on PET imaging. RESULTS: One hundred and eight patients had malignant effusion, including 86 with pleural metastasis and 22 with pleural mesothelioma, whereas 68 patients had benign effusion. The sensitivities of CT imaging, 18F-FDG PET imaging and 18F-FDG PET/CT integrated imaging in detecting malignant effusion were 75.0%, 91.7% and 93.5%, respectively, which were 69.8%, 91.9% and 93.0% in distinguishing metastatic effusion. The sensitivity of 18F-FDG PET/CT integrated imaging in detecting malignant effusion was higher than that of CT imaging (p = 0.000). For metastatic effusion, 18F-FDG PET imaging had higher sensitivity (p = 0.000) and better diagnostic consistency with 18F-FDG PET/CT integrated imaging compared with CT imaging (Kappa = 0.917 and Kappa = 0.295, respectively). The specificities of CT imaging, 18F-FDG PET imaging and 18F-FDG PET/CT integrated imaging were 94.1%, 63.2% and 92.6% in detecting benign effusion. The specificities of CT imaging and 18F-FDG PET/CT integrated imaging were higher than that of 18F-FDG PET imaging (p = 0.000 and p = 0.000, respectively), and CT imaging had better diagnostic consistency with 18F-FDG PET/CT integrated imaging compared with 18F-FDG PET imaging (Kappa = 0.881 and Kappa = 0.240, respectively). CONCLUSION: 18F-FDG PET/CT integrated imaging is a more reliable modality in distinguishing malignant from benign pleural effusion than 18F-FDG PET imaging and CT imaging alone. For image interpretation of 18F-FDG PET/CT integrated imaging, the PET and CT portions play a major diagnostic role in identifying metastatic effusion and benign effusion, respectively.

The Volume-metabolic Combined Parameters from (18)F-FDG PET/CT May Help Predict the Outcomes of Cervical Carcinoma.

RATIONALE AND OBJECTIVES: The aim of this study was to evaluate the prognostic value of 18-fluoro-2-deoxyglucose positron emission tomography/computed tomography ((18)F-FDG PET/CT) volume-metabolic combined parameters in patients with cervical carcinoma. MATERIALS AND METHODS: We retrospectively reviewed 91 consecutive patients' whole-body FDG-PET/CT images, and further measured and calculated FDG PET/CT volume-metabolic parameters, including cervical metabolic tumor volume (CMTV), cervical total lesion glycolysis (CTLG), whole-body metabolic tumor volume (WB-MTV), whole-body total lesions glycolysis (WB-TLG). The prognostic value of these tumor volume-metabolic measures was assessed by Cox Proportional Hazard Regression Analysis. RESULTS: The overall survival (OS) was 88.8% for patients with low CMTV (≤53.75 mL) and 45.5% for those with high CMTV (>53.75 mL), respectively (P < 0.01, 95% confidence interval). Univariate analysis showed that CMTV and CTLG were significant prognostic factors for OS, in addition to International Federation of Gynecology and Obstetrics (FIGO) stage, age, lymphadenopathy, and maximum standardized uptake value (SUVmax) (P < 0.05 for all). On multivariate analysis, CMTV remained significant for OS, in addition to FIGO stage (P < 0.05 for all). CMTV remains as prognostic factor for OS regardless of patients' FIGO stages (P < 0.05). In patients in the metastatic diseases group, univariate and multivariate analyses demonstrated that CMTV, WB-MTV, and WB-TLG were independent prognostic factors for OS (P < 0.05 for all). CONCLUSION: CMTV, WB-MTV, and WB-TLG are reliable prognostic factors for patients with cervical carcinoma and should be included in FDG-PET/CT reports to guide referral clinicians for risk-adapted therapies.

The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from (18)F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer.

OBJECTIVES: In clinical practice, image analysis is dependent on simply visual perception and the diagnostic efficacy of this analysis pattern is limited for mediastinal lymph nodes in patients with lung cancer. In order to improve diagnostic efficacy, we developed a new computer-based algorithm and tested its diagnostic efficacy. METHODS: 132 consecutive patients with lung cancer underwent (18)F-FDG PET/CT examination before treatment. After all data were imported into the database of an on-line medical image analysis platform, the diagnostic efficacy of visual analysis was first evaluated without knowing pathological results, and the maximum short diameter and maximum standardized uptake value (SUVmax) were measured. Then lymph nodes were segmented manually. Three classifiers based on support vector machine (SVM) were constructed from CT, PET, and combined PET-CT images, respectively. The diagnostic efficacy of SVM classifiers was obtained and evaluated. RESULTS: According to ROC curves, the areas under curves for maximum short diameter and SUVmax were 0.684 and 0.652, respectively. The areas under the ROC curve for SVM1, SVM2, and SVM3 were 0.689, 0.579, and 0.685, respectively. CONCLUSION: The algorithm based on SVM was potential in the diagnosis of mediastinal lymph nodes.

Evaluation of the diagnostic performance of magnetic resonance spectroscopy in brain tumors: a systematic review and meta-analysis.

OBJECT: The aim of this study was to determine the suitability of magnetic resonance spectroscopy (MRS) for screening brain tumors, based on a systematic review and meta-analysis of published data on the diagnostic performance of MRS. METHODS: The PubMed and PHMC databases were systematically searched for relevant studies up to December 2013. The sensitivities and specificities of MRS in individual studies were calculated and the pooled diagnostic accuracies, with 95% confidence intervals (CI), were assessed under a fixed-effects model. RESULTS: Twenty-four studies were included, comprising a total of 1013 participants. Overall, no heterogeneity of diagnostic effects was observed between studies. The pooled sensitivity and specificity of MRS were 80.05% (95% CI = 75.97%-83.59%) and 78.46% (95% CI: 73.40%-82.78%), respectively. The area under the summary receiver operating characteristic curve was 0.78. Stratified meta analysis showed higher sensitivity and specificity in child than adult. CSI had higher sensitivity and SV had higher specificity. Higher sensitivity and specificity were obtained in short TE value. CONCLUSION: Although the qualities of the studies included in the meta-analysis were moderate, current evidence suggests that MRS may be a valuable adjunct to magnetic resonance imaging for diagnosing brain tumors, but requires selection of suitable technique and TE value.

The role of (18)F-FDG PET/CT for evaluation of metastatic mediastinal lymph nodes in patients with lung squamous-cell carcinoma or adenocarcinoma.

OBJECTIVES: To evaluate the efficacy of (18)F-FDG PET/CT in depicting metastatic mediastinal lymph nodes in patients with lung squamous-cell carcinoma (LSCC) or lung adenocarcinoma (LAC) in a tuberculosis-endemic country. METHODS: This study retrospectively reviewed patients with LSCC or LAC, who underwent preoperative (18)F-FDG PET/CT to assess mediastinal lymph node metastasis. Patients with the short-axis of mediastinal lymph node≤15mm were included. PET/CT interpretation was analyzed in two ways. Firstly, with CT for anatomical localization, lymph nodes showing greater (18)F-FDG uptake than vessel pool on PET were regarded malignant. Secondly, lymph nodes with positive uptake on PET were considered malignant, only when nodes had neither calcification nor higher attenuation than vessel pool on CT. RESULTS: One hundred and sixteen LSCCs and 234 LACs were evaluated. With CT for anatomical localization, the sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of PET were 78.6%, 45.5%, 53.4%, 31.4% and 87.0% in LSCC group, and 61.8%, 66.3%, 65.0%, 42.9% and 80.9% in LAC group. PET showed higher specificity and accuracy in LAC group compared with LSCC group (p=0.001 and p=0.038, respectively). Considering calcification or high attenuation on CT, the sensitivity, specificity, accuracy, PPV and NPV of PET/CT were 71.4%, 67.0%, 68.1%, 40.8% and 88.1% in LSCC group, and 54.4%, 86.1%, 76.9%, 61.7% and 82.2% in LAC group. Compared with PET, PET/CT possessed higher specificity and accuracy in LSCC group (p=0.000 and p=0.000, respectively), and higher specificity, accuracy and PPV in LAC group (p=0.000, p=0.000 and p=0.022, respectively). CONCLUSIONS: (18)F-FDG PET displays limited efficacy in assessing mediastinal lymph node metastasis with the short-axis diameter <15mm in LSCC and LAC groups and higher false-positivity in LSCC group. The specificity and accuracy in LSCC and LAC groups are enhanced by interpreting attenuation characteristic on CT.

Evaluation of ¹8F-FDG PET/CT in early-stage cervical carcinoma.

INTRODUCTION: The purpose is to evaluate ¹8F-fluorodeoxy glucose-positron emission tomography (PET)/computed tomography (CT) for the detection of cervical carcinoma of the International Federation of Gynecology and Obstetrics stages Ib and IIa. METHODS: Twenty-two patients with cervical carcinoma were included in this study. Eleven of them were at the International Federation of Gynecology and Obstetrics stage Ib, and the remaining patients were at stage IIa. All the patients underwent ¹8F-fluorodeoxy glucose-PET/CT scan, and in 15 patients, additional delayed imaging of pelvis was performed. The PET/CT findings were compared with histopathologic and follow-up results. RESULTS: Of the 22 patients, 20 had cervical cancer with abnormal uptake that were detected directly using PET/CT without additional information from delayed imaging of pelvis; the other 2 patients showed lesions with no abnormal uptake. The use of delayed imaging of the pelvis with PET/CT corrected 1 false-negative case. Thus, the accuracy of PET/CT for early-stage cervical carcinoma was 95.45% (21/22). The uptake of early-stage cervical carcinoma showed no statistical significance between the group of stage Ib and the group of stage IIa (P > 0.05). The false-negative rate and negative predictive value of PET/CT imaging in predicting pelvic nodal involvement were 6.25% (1/16) and 93.75%, respectively. CONCLUSIONS: PET/CT showed a high accuracy for the diagnosis of early-stage cervical cancer and a high-negative predictive value for predicting the pelvic nodal status in early-stage cervical cancer.

A correlation study between maximum standardized uptake values and pathology and clinical staging in nonsmall cell lung cancer.

OBJECTIVE: To investigate the relationship between maximum standardized uptake value and pathological type, degree of differentiation, tumor size, and clinical staging of nonsmall cell lung cancer (NSCLC). METHODS: This study included 135 cases with pathologically proven NSCLC. Correlations between maximum standardized uptake value (SUVmax) and pathological type, degree of differentiation, tumor size, and clinical staging were analyzed. RESULTS: There was a significant correlation between the SUVmax of NSCLC and the pathological type (r= 0.391, P= 0.000); the SUVmax of squamous cell carcinoma (SCC) was higher than that of adenocarcinoma (AC) (P =0.000), and the SUVmax of AC was higher than that of bronchioloalveolar carcinoma (P = 0.004). There was a positive correlation between the SUVmax of AC and the degree of differentiation (r= 0.222, P = 0.044); SUVmax was lower in well-differentiated ACs than in moderately or poorly differentiated ACs (P=0.034 and 0.022 respectively); however, there was no statistical difference between the moderately differentiated and poorly differentiated groups (P= 1.000). There was no correlation between the SUVmax of SCC and the degree of differentiation (r= - 0.304, P= 0.054). A positive correlation was found between the SUVmax of NSCLC and tumor size (r= 0.569, P =0.000). The SUVmax of AC had a positive correlation with clinical staging (r= 0.298, P = 0.006); SUVmax was lower in stage I than in stages II, III, and IV (P = 0.047, 0.038 and 0.015, respectively); however, the SUVmax in stages II, III, and IV were not different (P= 0.708, 0.570 and 0.528, respectively). There was no correlation between the SUVmax of SCC and clinical staging (r =0.066, P = 0.680). CONCLUSION: There was a correlation between the SUVmax of NSCLC and the pathological type and tumor size. A positive correlation was found between the SUVmax of AC and the degree of differentiation and clinical staging. There were no correlations between the SUVmax of SCC and the degree of differentiation or clinical staging.

[Correlation between SUV of (18)F-FDG PET-CT and the expression of GLUT1, MVD and Ki67 in non-small cell lung cancer].

OBJECTIVE: To investigate the correlation between 18F-FDG standard uptake value (SUV) and expression of GLUT1, MVD and Ki67 in non-small cell lung cancer (NSCLC). METHODS: Thirty-three patients with non-small cell lung cancer received preoperative 18F-FDG PET-CT examination and underwent surgery. The expression of GLUT1, MVD and Ki67 were detected by immunohistochemstry. The correlation between the SUV of 18F-FDG PET-CT and the immunohistochemical results of the three above mentioned parameters was analyzed. RESULTS: Of the 33 NSCLC patients, 21 were in stage I, 4 in stage II and 8 in stage IIIa. Positive expression of GLUT1 was found in 22 cases (66.7%, 12 adenocarcinomas and 10 squamous cell carcinomas), and negative expression in 11 cases (10 adenocarcinomas and 1 squamous cell carcinoma). Twenty-four patients (72.7%) showed positive expression of Ki67 (13 adenocarcinomas and 11 squamous cell carcinomas), and other 9 (adenocarcinomas) had negative expression. The positive expression rate of CD34 in this series was 100.0% with a mean MVD of 12.6 +/- 2.9. CONCLUSION: SUV of 18F-FDG PET-CT is linearly correlated with the expression of GLUT1, but not with the expression of Ki67 or MVD. The expression of GLUT1, Ki67 and CD34 is not correlated with tumor size and lymph node metastasis.