18F-fluoro-2-deoxy-d-glucose positron emission tomography/computed tomography fused imaging in malignant mesothelioma patients: looking from outside is not enough

Deep learning with deep convolutional neural network using FDG-PET/CT for malignant pleural mesothelioma diagnosis

OBJECTIVES

This study analyzed an artificial intelligence (AI) deep learning method with a three-dimensional deep convolutional neural network (3D DCNN) in regard to diagnostic accuracy to differentiate malignant pleural mesothelioma (MPM) from benign pleural disease using FDG-PET/CT results.

RESULTS

For protocol A, the area under the ROC curve (AUC)/sensitivity/specificity/accuracy values were 0.825/77.9% (81/104)/76.4% (55/72)/77.3% (136/176), while those for protocol B were 0.854/80.8% (84/104)/77.8% (56/72)/79.5% (140/176), for protocol C were 0.881/85.6% (89/104)/75.0% (54/72)/81.3% (143/176), and for protocol D were 0.896/88.5% (92/104)/73.6% (53/72)/82.4% (145/176). Protocol D showed significantly better diagnostic performance as compared to A, B, and C in ROC analysis (p = 0.031, p = 0.0020, p = 0.041, respectively).

MATERIALS AND METHODS

Eight hundred seventy-five consecutive patients with histologically proven or suspected MPM, shown by history, physical examination findings, and chest CT results, who underwent FDG-PET/CT examinations between 2007 and 2017 were investigated in a retrospective manner. There were 525 patients (314 MPM, 211 benign pleural disease) in the deep learning training set, 174 (102 MPM, 72 benign pleural disease) in the validation set, and 176 (104 MPM, 72 benign pleural disease) in the test set. Using AI with PET/CT alone (protocol A), human visual reading (protocol B), a quantitative method that incorporated maximum standardized uptake value (SUVmax) (protocol C), and a combination of PET/CT, SUVmax, gender, and age (protocol D), obtained data were subjected to ROC curve analyses.

CONCLUSIONS

Deep learning with 3D DCNN in combination with FDG-PET/CT imaging results as well as clinical features comprise a novel potential tool shows flexibility for differential diagnosis of MPM.

18F-fluorodeoxyglucose positron emission tomography in malignant pleural mesothelioma: diagnostic and prognostic performance and its correlation to pathological results

Although 18F-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) scan has been generally validated in the staging of malignant pleural mesothelioma (MPM), its diagnostic and prognostic performances are not clearly established. Aiming to identify possible factors causing 18F-fluorodeoxyglucose PET/CT false-negative results and influencing prognosis in MPM patients, we analysed clinical, radiometabolic and pathological features in 141 MPM patients who underwent diagnostic 18F-fluorodeoxyglucose PET/CT scan (January 2009-July 2018) at 2 high-volume institutions. The Fisher's exact test and the Cox model were used in statistical analysis. Overall detection rate was 88.3% with 16 patients (11.6%) presenting with a standardized uptake value (SUV) max <2.5 (PET-negative). PET-negative cases were more frequently detected in older patients (P = 0.027) and early-stage tumours (33.3% false-negative in stage I and 40.0% false-negative in T1-tumours, with P = 0.014 both). Mean SUVmax value was higher in sarcomatoid (11.8 ± 4.6) and biphasic MPM (9.3 ± 7.0), rather than in epithelioid MPM (6.9 ± 3.8, P < 0.001). Concerning overall survival, SUVmax (both as continuous and as categorical variable) was found to be a prognostic factor, in addition to stage (P = 0.032) and histology (P = 0.014) as confirmed by multivariable analysis (hazard ratio 2.65, confidence interval 1.23-5.70; P < 0.001). In the light of such results, we highlight that a low fluorodeoxyglucose uptake might be observed in more than 10% MPMs, especially in early-stage tumours affecting elderly patients. Furthermore, high SUVmax values significantly correlated with a worse prognosis.

ACR Appropriateness Criteria® Occupational Lung Diseases

Ordering the appropriate diagnostic imaging for occupational lung disease requires a firm understanding of the relationship between occupational exposure and expected lower respiratory track manifestation. Where particular inorganic dust exposures typically lead to nodular and interstitial lung disease, other occupational exposures may lead to isolated small airway obstruction. Certain workplace exposures, like asbestos, increase the risk of malignancy, but also produce pulmonary findings that mimic malignancy. This publication aims to delineate the common and special considerations associated with occupational lung disease to assist the ordering physician in selecting the most appropriate imaging study, while still stressing the importance of a multidisciplinary approach. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Diagnostic Value of Computed Tomography Imaging Features in Malignant Pleural Mesothelioma

BACKGROUND

Medical history, thoracentesis, and imaging features are usually the first steps in the investigation of a possible malignant pleural effusion (MPE). Unfortunately, the diagnostic yield of thoracentesis in this situation is suboptimal even if the procedure is repeated, especially in the context of malignant pleural mesothelioma (MPM). The next step for confirming the diagnosis, if clinically appropriate, is thoracoscopy, but not all patients are fit to undergo this procedure, so the diagnosis is then based on the medical history and imaging features only.

OBJECTIVES

Our objective was to evaluate the diagnostic value of the medical history and imaging features in MPM.

METHODS

We reviewed the imaging and medical charts of 92 patients with a final diagnosis of MPE included in our prospective medical thoracoscopy database. The clinical characteristics and imaging features of patients with primary MPE were compared with those of patients with secondary MPE.

RESULTS

Male sex (82 vs. 59%, p = 0.02), asbestos exposure (58 vs. 10%, p < 0.001), and mediastinal (68 vs. 33%, p = 0.04), diaphragmatic (75 vs. 31%, p = 0.001) and circumferential pleural thickening (55 vs. 19% p = 0.001) were significantly more frequent in MPM patients. In a multivariate linear regression model, only asbestos exposure (OR 11.2; 95% CI 3.4-36.9) and circumferential pleural thickening (OR 4.7; 95% CI 1.6-13.9) were significantly associated with a diagnosis of MPM.

CONCLUSION

In situations where it is impossible to obtain adequate pleural samples to differentiate MPM from a secondary pleural malignancy, the combination of circumferential pleural thickening and a history of asbestos exposure may be sufficient to make a clinical diagnosis.

[Medical thoracoscopy in respiratory medicine: The Liège University Hospital experience]

INTRODUCTION

The incidence of pleural disease continues to increase worldwide. Medical thoracoscopy remains the standard method for exploration of the pleural cavity.

METHOD

We report the retrospective evaluation, the efficacy and the observed complications in 1024 medical thoracoscopies undertaken in the University Hospital of Liège between 2000 and 2017.

RESULTS

In total, 100 pneumothoraces and 400 benign and 501 malignant pleural diseases were identified. The main indication for thoracoscopy remains the diagnosis of an exudative, lymphocytic pleural effusion of unknown aetiology after thoracocentesis. The diagnostic sensibility of thoracoscopy was 99.2% in distinguishing benign from malignant pleural disease. Talc pleurodesis was performed in 69.5% of the total population and in 66.1% of pleural effusions or thickening. Failure of pleurodesis was observed in 11% of the patients with recurrent pneumothorax and in 7.8% of neoplastic pleural effusion. We report a mortality of 0.6% in the 30 days post procedure, long duration of drainage in 8.3% and serious complications in 4.7%. In 22/1024 (2.1%) thoracoscopic evaluation was not feasible because of dense pleural fibrosis.

CONCLUSION

Medical thoracoscopy is a safe, well-tolerated procedure with high accuracy in the diagnostic and therapeutic management of pleural disease.

Comparison of cytology, chest computed and positron emission tomography findings in malignant pleural effusion from lung cancer

Background

Malignant pleural effusion (MPE) is a common medical problem in lung cancer (LC). Pleural fluid cytology (PFC), chest computed tomography (CCT) and positron emission tomography (PET) findings are helpful as first line approach. The objectives of this study were to evaluate whether there is a correlation between PFC, CCT and PET in patients with MPE due to LC.

Methods

We selected patients from our electronic files. Data of PFC, pleural biopsy (PB), CCT and PET have been recorded and analyzed.

Results

A total of 101 consecutive patients (66 males, 65.3%) with a mean age of 66.2±31 years were selected. Types of LC were adenocarcinoma in 71 patients (70.2%), squamous in 13 (12.8%), small-cell in 12 (11.8%) and large cell in 5 (4.9%). CCT showed nodules in 6 (5.9%), pleural thickening in 8 (7.9%) and both in 17 (16.8%) patients. PFC was positive in 55/91 thoracentesis (60.4%) and 32/52 thoracoscopy (61.5%), while PB in 38/40 performed (95%). PET fixation was found in 32/47 (68%) patients who had MPE at diagnosis. When we associate PFC to CCT and PET findings, the yield in our study becomes 90%. No correlation was observed between CCT findings and PFC (P=0.62) between PFC and PET fixation (P=0.63) or between CCT and PET (P=0.06).

Conclusions

In our cohort of LC patients with MPE, we observed a high sensitivity for PFC, while in most of the cases no findings were observed in CCT. PET had a relative low sensitivity. However, when all 3 methods were combined the yield was 90%.

Clinical staging of malignant pleural mesothelioma: current perspectives

Malignant pleural mesothelioma (MPM) is a disease with limited therapeutic options, the management of which is still controversial. Diagnosis is usually made by thoracoscopy, which allows multiple biopsies with histological subtyping and is indicated for staging purposes in surgical candidates. The recommended and recently updated classification for clinical use is the TNM staging system established by the International Mesothelioma Interest Group and the International Association for the Study of Lung Cancer, which is based mainly on surgical and pathological variables, as well as on cross-sectional imaging. Contrast-enhanced computed tomography is the primary imaging procedure. Currently, the most used measurement system for MPM is the modified Response Evaluation Criteria in Solid Tumors (RECIST) method, which is based on unidimensional measurements of tumor thickness perpendicular to the chest wall or mediastinum. Magnetic resonance imaging and functional imaging with ¹⁸F-fluoro-2-deoxy-D-glucose positron-emission tomography can provide additional staging information in selected cases, although the usefulness of this method is limited in patients undergoing pleurodesis. Molecular reclassification of MPM and gene expression or miRNA prognostic models have the potential to improve prognostication and patient selection for a proper treatment algorithm; however, they await prospective validation to be introduced in clinical practice.

The potential value of volume-based quantitative PET parameters and increased bone marrow uptake for the prediction of survival in patients with malignant pleural mesothelioma

PURPOSE

The aim of this study was to investigate the relationship between volume-based quantitative PET parameters and survival in patients with malignant pleural mesothelioma (MPM) and to evaluate the potential value of bone marrow (BM) uptake in predicting prognosis.

MATERIALS AND METHODS

We retrospectively reviewed the data of 51 patients with MPM who underwent initial staging by fluorine-18-fluorodeoxyglucose (F-FDG) PET/computerized tomography (PET/CT). F-FDG-PET images were visually and quantitatively re-evaluated and maximum standardized uptake values (SUVmax), mean standardized uptake values (SUVmean), metabolic tumor volume (MTV), total lesion glycolysis of primary tumors, and pleural thickening were calculated. In addition, BM and liver uptakes were measured; also, the degree of BM uptake was scored visually. BM/liver ratio and visual BM uptake score were noted. The correlations between quantitative PET parameters, BM uptake, and overall survival were analyzed.

RESULTS

F-FDG-PET scans upstaged 6 (11.8%) of 51 patients because of detection of previously unknown distant metastasis. On univariate analysis, advanced disease stage, high leukocyte count (≥10×10/ml), pleural thickening greater than 13 mm, SUVmax, SUVmean, MTV, total lesion glycolysis, BM/liver greater than 1.01, and visual score 1 and 2 were negative prognostic factors (P<0.05). In multivariate analysis, SUVmax greater than 8.6 [P=0.027, hazard ratio (HR): 2.961], MTV greater than 112 (P=0.001, HR: 4.861), and visual score 2 (P=0.035, HR: 3.827) were associated independently with a poor prognosis.

CONCLUSION

The presence of distant metastasis is more predictive of survival than PET nodal status in MPM patients. PET/CT has the potential to provide prognostic information in MPM patients and there was a good correlation between overall survival and volume-based PET parameters. Determination of BM uptake may contribute toward the prediction of patient outcome with other quantitative PET parameters.

Present and future roles of FDG-PET/CT imaging in the management of malignant pleural mesothelioma

Positron emission tomography/computed tomography (PET/CT) integrated with 2-[(18)F]fluoro-2-deoxy-D-glucose ((18)F-FDG) has emerged as a powerful tool for combined metabolic and anatomic evaluations in clinical oncologic imaging. This review discusses the utility of (18)F-FDG PET/CT as a tool to manage patients with malignant pleural mesothelioma. We discuss different stages of patient management in malignant pleural mesothelioma, including diagnosis, initial staging, therapy planning, early treatment response assessment, re-staging, and prognosis.