Volumetric assessment in malignant pleural mesothelioma

Convolutional Neural Networks for Segmentation of Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

The purpose of this study was to evaluate the impact of probability map threshold on pleural mesothelioma (PM) tumor delineations generated using a convolutional neural network (CNN). One hundred eighty-six CT scans from 48 PM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the reference standard provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN-derived contours consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.01 decreased the absolute percent volume difference, on average, from 42.93% to 26.60%. Median and mean DSC ranged from 0.57 to 0.59, with a peak at a threshold of 0.2; no distinct threshold was found for percent volume difference. The CNN exhibited deficiencies with specific disease presentations, such as severe pleural effusion or disease in the pleural fissure. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This study emphasized the importance of considering both figures of merit when evaluating deep learning-based tumor segmentations across probability thresholds. This work underscores the need to simultaneously assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

The International Association for the Study of Lung Cancer Mesothelioma Staging Project: Proposals for Revisions of the "T" Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Pleural Mesothelioma

INTRODUCTION

The primary tumor (T) component in the eighth edition of pleural mesothelioma (PM) staging system is based on pleural involvement and extent of invasion. Quantitative assessment of pleural tumor has been found to be prognostic. We explored quantitative and qualitative metrics to develop recommendations for T descriptors in the upcoming ninth edition of the PM staging system.

METHODS

The International Association for the Study of Lung Cancer prospectively collected data on patients with PM. Sum of maximum pleural thickness (Psum) was recorded. Optimal combinations of Psum and eighth edition cT descriptors were assessed using recursive binary splitting algorithm, with bootstrap resampling to correct for the adaptive nature of the splitting algorithm, and validated in the eighth edition data. Overall survival (OS) was calculated by the Kaplan-Meier method and differences in OS assessed by the log-rank test.

RESULTS

Of 7338 patients submitted, 3598 were eligible for cT analysis and 1790 had Psum measurements. Recursive partitioning identified optimal cutpoints of Psum at 12 and 30 mm, which, in combination with extent of invasion, yielded four prognostic groups for OS. Fmax greater than 5 mm indicated poor prognosis. cT4 category (based on invasion) revealed similar performance to eighth edition. Three eighth edition descriptors were eliminated based on low predictive accuracy. Eighth edition pT descriptors remained valid in ninth edition analyses.

CONCLUSION

Given reproducible prognostication by Psum, size criteria will be incorporated into cT1 to T3 categories in the ninth edition. Current cT4 category and all pT descriptors will be maintained, with reclassification of fissural invasion as pT2.

The prognostic value of F18 Fluorothymidine positron emission tomography for assessing the response of malignant pleural mesothelioma to chemotherapy - A prospective cohort study

INTRODUCTION

Malignant pleural mesothelioma is difficult to prognosticate. F18-Fluorodeoxyglucose positron emission tomography (FDG PET) shows promise for response assessment but is confounded by talc pleurodesis. F18-Fluorothymidine (FLT) PET is an alternative tracer specific for proliferation. We compared the prognostic value of FDG and FLT PET and determined the influence of talc pleurodesis on these parameters.

METHODS

Overall, 29 prospectively recruited patients had FLT PET, FDG PET and CT-scans performed prior to and post one chemotherapy cycle; 10 had prior talc pleurodesis. Patients were followed for overall survival. CT response was assessed using mRECIST. Radiomic features were extracted using the MiM software platform. Changes in maximum SUV (SUVmax), mean SUV (SUVmean), FDG total lesion glycolysis (TLG), FLT total lesion proliferation (TLP) and metabolic tumour volume (MTV) after one chemotherapy cycle.

RESULTS

Cox univariate analysis demonstrated FDG PET radiomics were confounded by talc pleurodesis, and that percentage change in FLT MTV was predictive of overall survival. Cox multivariate analysis showed a 10% increase in FLT tumour volume corresponded with 9.5% worsened odds for overall survival (P = 0.028, HR = 1.095, 95% CI [1.010, 1.187]). No other variables were significant on multivariate analysis.

CONCLUSION

This is the first prospective study showing the statistical significance of FLT PET tumour volumes for measuring mesothelioma treatment response. FLT may be better than FDG for monitoring mesothelioma treatment response, which could help optimise mesothelioma treatment regimes.

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

Malignant pleural mesothelioma (MPM) is the most common form of malignant mesothelioma, with exposure to asbestos being the primary cause of the disease. To assess response to treatment, tumor measurements are acquired and evaluated based on a patient's longitudinal computed tomography (CT) scans. Tumor volume, however, is the more accurate metric for assessing tumor burden and response. Automated segmentation methods using deep learning can be employed to acquire volume, which otherwise is a tedious task performed manually. The deep learning-based tumor volume and contours can then be compared with a standard reference to assess the robustness of the automated segmentations. The purpose of this study was to evaluate the impact of probability map threshold on MPM tumor delineations generated using a convolutional neural network (CNN). Eighty-eight CT scans from 21 MPM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN annotations consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.1 decreased the absolute percent volume difference, on average, from 43.96% to 24.18%. Median and mean DSC ranged from 0.58 to 0.60, with a peak at a threshold of 0.5; no distinct threshold was found for percent volume difference. The CNN exhibited deficiencies with specific disease presentations, such as severe pleural effusion or disease in the pleural fissure. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This study emphasized the importance of considering both figures of merit when evaluating deep learning-based tumor segmentations across probability thresholds. This work underscores the need to simultaneously assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

Deep learning for diagnosis of malign pleural effusion on computed tomography images

BACKGROUND

The pleura is a serous membrane that surrounds the lungs. The visceral surface secretes fluid into the serous cavity and the parietal surface ensures a regular absorption of this fluid. If this balance is disturbed, fluid accumulation occurs in the pleural space called "Pleural Effusion". Today, accurate diagnosis of pleural diseases is becoming more critical, as advances in treatment protocols have contributed positively to prognosis. Our aim is to perform computer-aided numerical analysis of Computed Tomography (CT) images from patients showing pleural effusion images on CT and to examine the prediction of malignant/benign distinction using deep learning by comparing with the cytology results.

METHODS

The authors classified 408 CT images from 64 patients whose etiology of pleural effusion was investigated using the deep learning method. 378 of the images were used for the training of the system; 15 malignant and 15 benign CT images, which were not included in the training group, were used as the test.

RESULTS

Among the 30 test images evaluated in the system; 14 of 15 malignant patients and 13 of 15 benign patients were estimated with correct diagnosis (PPD: 93.3%, NPD: 86.67%, Sensitivity: 87.5%, Specificity: 92.86%).

CONCLUSION

Advances in computer-aided diagnostic analysis of CT images and obtaining a pre-diagnosis of pleural fluid may reduce the need for interventional procedures by guiding physicians about which patients may have malignancies. Thus, it is cost and time-saving in patient management, allowing earlier diagnosis and treatment.

Considerations for Imaging of Malignant Pleural Mesothelioma: A Consensus Statement from the International Mesothelioma Interest Group

Malignant pleural mesothelioma (MPM) is an aggressive primary malignancy of the pleura that presents unique radiologic challenges with regard to accurate and reproducible assessment of disease extent at staging and follow-up imaging. By optimizing and harmonizing technical approaches to imaging MPM, the best quality imaging can be achieved for individual patient care, clinical trials, and imaging research. This consensus statement represents agreement on harmonized, standard practices for routine multimodality imaging of MPM, including radiography, computed tomography, ¹⁸F-2-deoxy-D-glucose positron emission tomography, and magnetic resonance imaging, by an international panel of experts in the field of pleural imaging assembled by the International Mesothelioma Interest Group. In addition, modality-specific technical considerations and future directions are discussed. A bulleted summary of all technical recommendations is provided.

Old Borders and New Horizons in Multimodality Imaging of Malignant Pleural Mesothelioma

BACKGROUND

The purpose of this article is to describe the various imaging techniques involved in detection, staging, and preoperative planning in malignant pleural mesothelioma (MPM) focusing on new imaging modalities.

METHODS

For this purpose, first a brief summary of the etiology of MPM is given. Second, not only the commonly known, but also novel imaging modalities used in MPM will be discussed.

RESULTS

A wide range of imaging methods, from conventional chest radiography, through computed tomography and hybrid imaging to radiomics and artificial intelligence, can be used to evaluate MPM.

CONCLUSION

Nowadays multimodality imaging is considered the cornerstone in MPM diagnosis and staging.

Sarcopenia, Precardial Adipose Tissue and High Tumor Volume as Outcome Predictors in Surgically Treated Pleural Mesothelioma

BACKGROUND

We evaluated the prognostic value of Sarcopenia, low precardial adipose-tissue (PAT), and high tumor-volume in the outcome of surgically-treated pleural mesothelioma (PM).

METHODS

From 2005 to 2020, consecutive surgically-treated PM-patients having a pre-operative computed tomography (CT) scan were retrospectively included. Sarcopenia was assessed by CT-based parameters measured at the level of the fifth thoracic vertebra (TH5) by excluding fatty-infiltration based on CT-attenuation. The findings were stratified for gender, and a threshold of the 33rd percentile was set to define sarcopenia. Additionally, tumor volume as well as PAT were measured. The findings were correlated with progression-free survival and long-term mortality.

RESULTS

Two-hundred-seventy-eight PM-patients (252 male; 70.2 ± 9 years) were included. The mean progression-free survival was 18.6 ± 12.2 months, and the mean survival time was 23.3 ± 24 months. Progression was associated with chronic obstructive pulmonary disease (COPD) (p = <0.001), tumor-stage (p = 0.001), and type of surgery (p = 0.026). Three-year mortality was associated with higher patient age (p = 0.005), presence of COPD (p < 0.001), higher tumor-stage (p = 0.015), and higher tumor-volume (p < 0.001). Kaplan-Meier statistics showed that sarcopenic patients have a higher three-year mortality (p = 0.002). While there was a negative correlation of progression-free survival and mortality with tumor volume (r = 0.281, p = 0.001 and r = -0.240, p < 0.001; respectively), a correlation with PAT could only be shown for epithelioid PM (p = 0.040).

CONCLUSIONS

Sarcopenia as well as tumor volume are associated with long-term mortality in surgically treated PM-patients. Further, while there was a negative correlation of progression-free survival and mortality with tumor volume, a correlation with PAT could only be shown for epithelioid PM.

Pilot Study to Evaluate Serum Soluble Mesothelin-Related Peptide (SMRP) as Marker for Clinical Monitoring of Pleural Mesothelioma (PM): Correlation with Modified RECIST Score

A soluble mesothelin-related peptide (SMRP) is the only FDA-approved biomarker for diagnosis of pleural mesothelioma (PM) and the most used for monitoring treatment. Radiological assessment of PM, based on modified RECIST (mRECIST) criteria, is challenging. This pilot study was designed to evaluate whether SMRP levels correlated over time with mRECIST score. Serial serum samples from PM patients were collected and SMRP levels were measured and compared with the mRECIST score obtained through centralized CT scans by blinded review. The within-patient SMRP-mRECIST relationship over time was estimated through a normal random-effects regression approach applied to the log-transformed mRECIST score. Overall, 58 PM patients were included (46 males and 12 females) with a median age at diagnosis of 67 years (min–max = 48–79), 44 (76%) with epithelioid and 14 (24%) with non-epithelioid histology. The total number of SMRP measurements and CT scans considered for analysis was 183. There was a statistically significant correlation between SMRP and mRECIST score in the 2 cohorts considered both separately and jointly. These results, although exploratory, suggest that SMRP measurement might be considered as an adjunct to monitor PM patients in order to delay CT scans time interval, thus warranting further investigation.

Clinical presentation, treatment and outcome of canine malignant mesothelioma: A retrospective study of 34 cases

Canine malignant mesothelioma (CMM) is a rare and aggressive tumour associated with a poor prognosis. Limited information is available regarding effective treatment options and prognostic factors. The purpose of this retrospective case series was to describe the clinical presentation, treatment and survival in a cohort of dogs with this disease and to investigate possible prognostic factors. Thirty-four dogs were included. Tachypnoea and dyspnoea due to pleural effusion were the most common presenting clinical signs. Twenty-two dogs had a subcutaneous access port placed and 25 dogs were treated with intracavitary and/or intravenous chemotherapy. The main protocols used were single-agent 5-FU (n = 14) and carboplatin single-agent or alternated with mitoxantrone (n = 10). The overall response rate (defined as more than 25% reduction in effusion volume) to chemotherapy treatment was 37% after 3-weeks and 24% after 15-weeks. The median survival time (MST) for all dogs was 195 days (95% CI 53-324). MST was 234 days for dogs receiving chemotherapy and 29 days for dogs not receiving chemotherapy. The 1-year survival rate was 22% for all dogs. Treatment with chemotherapy was the only significant prognostic factor associated with survival (p = .001). Further studies are needed to determine the optimal treatment approach for malignant mesothelioma in dogs. Nevertheless, effusion recurrence should be expected and the prognosis for these patients in the long-term is poor.

Malignant pleural mesothelioma: recent developments

PURPOSE OF REVIEW

Malignant pleural mesothelioma (MPM) is a rare, but aggressive tumor with still poor prognosis. In this article, we focus on recent developments in the management of MPM including diagnosis, staging, biomarkers, and treatment strategies.

RECENT FINDINGS

Molecular markers such as programmed death-ligand 1 (PDL-1), Breast Cancer gene 1-associated protein gene, and cyclin-dependent kinase inhibitor 2A (CDKN2A) have prognostic impact and should be considered for assessment in patient samples. In addition to histological subtype and tumor pattern, tumor volumetry plays an increasing important role in staging, assessment of treatment response, and prediction of survival. Several new blood-based biomarkers have been recently reported including peripheral blood DNA methylation, microRNAs, fibulin, and high-mobility group box 1, but have not been established in clinical routine use yet. Regarding treatment, targeted therapies, immunotherapy, and vaccination are considered as new promising strategies. Moreover, extended pleurectomy/decortication is favored over extrapleural pneumonectomy (EPP) and intensity-modulated radiotherapy represents a possible approach in combination with EPP and pleurectomy/decortication. Intracavitary treatment options are promising and deserve further investigations.

SUMMARY

Overall, there has not been a real breakthrough in the treatment of MPM. Further research and clinical trials are needed to evaluate outcome and to identify new potential treatment candidates.

Implementing CT tumor volume and CT pleural thickness into future staging systems for malignant pleural mesothelioma

Objectives

Tumor thickness and tumor volume measured by computed tomography (CT) were suggested as valuable prognosticator for patients’ survival diagnosed with malignant pleural mesothelioma (MPM). The purpose was to assess the accuracy of CT scan based preoperatively measured tumor volume and thickness compared to actual tumor weight of resected MPM specimen and pathologically assessed tumor thickness, as well as an analysis of their impact on overall survival (OS).

Methods

Between 09/2013–08/2018, 74 patients were treated with induction chemotherapy followed by (extended) pleurectomy/decortication ((E)PD). In 53 patients, correlations were made between CT-measured volume and -tumor thickness (cTV and cTT) and actual tumor weight (pTW) based on the available values. Further cTV and pT/IMIG stage were correlated using Pearson correlation. Overall survival (OS) was calculated with Kaplan Meier analysis and tested with log rank test. For correlation with OS Kaplan-Meier curves were made and log rank test was performed for all measurements dichotomized at the median.

Results

Median pathological tumor volume (pTV) and pTW were 530 ml [130 ml – 1000 ml] and 485 mg [95 g – 982 g] respectively. Median (IQR) cTV was 77.2 ml (35.0–238.0), median cTT was 9.0 mm (6.2–13.7). Significant association was found between cTV and pTV (R = 0.47, p < 0.001) and between cTT and IMIG stage (p = 0,001) at univariate analysis. Multivariate regression analysis revealed, that only cTV correlates with pTV. Median follow-up time was 36.3 months with 30 patients dead at the time of the analysis. Median OS was 23.7 months. 1-year and 3-year survival were 90 and 26% respectively and only the cTV remained statistically associated with OS.

Conclusion

Preoperatively assessed CT tumor volume and actual tumor volume showed a significant correlation. CT tumor volume may predict pathological tumor volume as a reflection of tumor burden, which supports the integration of CT tumor volume into future staging systems.

The role of imaging in malignant pleural mesothelioma: an update after the 2018 BTS guidelines

Malignant pleural mesothelioma (MPM) is a primary malignancy of the pleura and is associated with a poor outcome. The symptoms and signs of malignant mesothelioma present late in the natural history of the disease and are non-specific, making the diagnosis challenging and imaging key. In 2018, the British Thoracic Society (BTS) updated the guideline on diagnosis, staging, and follow-up of patients with MPM. These recommendations are discussed in this review of the current literature on imaging of MPM. It is estimated MPM will continue to cause serious morbidity and mortality in the UK late into the 21st century, and internationally, people continue to be exposed to asbestos. We aim to update the reader on current and future imaging strategies, which could aid early diagnosis of pleural malignancy and provide an update on staging and assessment of tumour response.

Loco-regional staging of malignant pleural mesothelioma by integrated 18F-FDG PET/MRI

AIM

To examine the performance of 18F-FDG PET/MRI in the loco-regional staging of malignant pleural mesothelioma (MPM).

METHODS

Consecutive subjects with MPM undergoing pre-operative staging with 18F-FDG PET/CT who underwent a same day integrated 18F-FDG PET/MRI were prospectively studied. Clinical TNM staging (AJCC 7th edition) was performed separately and in consensus by two readers on the 18F-FDG PET/MRI studies, and compared with staging by 18F-FDG PET/CT, and with final pathological stage, determined by a combination of intra-operative and histological findings.

RESULTS

10 subjects (9 male, mean age 68 years) with biopsy-proven MPM (9 epithelioid tumours, 1 biphasic) were included. One subject underwent neo-adjuvant chemotherapy between imaging and surgery and was excluded from the clinical versus pathological stage analysis. Pathological staging was concordant with staging by 18F-FDG PET/MRI in 67% (n = 6) of subjects, and with 18F-FDG PET/CT staging in 33% (n = 3). Pathological T stage was concordant with 18F-FDG PET/MRI in 78% (n = 7), and with 18F-FDG PET/CT in 33% (n = 3) of subjects. Pathological N stage was concordant with both 18F-FDG PET/MRI and 18F-FDG PET/CT in 78% (n = 7) of cases. No subject had metastatic disease. There was good inter-observer agreement for overall PET/MRI staging (weighted kappa 0.63) with moderate inter-reader agreement for T staging (weighted kappa 0.59). All 6 subjects with prior talc pleurodesis demonstrated mismatch between elevated FDG uptake and restricted diffusion in areas of visible talc deposition.

CONCLUSION

Clinical MPM staging by 18F-FDG PET/MRI is feasible, and potentially provides more accurate loco-regional staging than PET/CT, particularly in T staging.

Progress in the Management of Malignant Pleural Mesothelioma in 2017

Malignant pleural mesothelioma (MPM) is an uncommon, almost universally fatal, asbestos-induced malignancy. New and effective strategies for diagnosis, prognostication, and treatment are urgently needed. Herein we review the advances in MPM achieved in 2017. Whereas recent epidemiological data demonstrated that the incidence of MPM-related death continued to increase in United States between 2009 and 2015, new insight into the molecular pathogenesis and the immunological tumor microenvironment of MPM, for example, regarding the role of BRCA1 associated protein 1 and the expression programmed death receptor ligand 1, are highlighting new potential therapeutic strategies. Furthermore, there continues to be an ever-expanding number of clinical studies investigating systemic therapies for MPM. These trials are primarily focused on immunotherapy using immune checkpoint inhibitors alone or in combination with other immunotherapies and nonimmunotherapies. In addition, other promising targeted therapies, including pegylated adenosine deiminase (ADI-PEG20), which focuses on argininosuccinate synthase 1-deficient tumors, and tazemetostat, an enhancer of zeste 2 polycomb repressive complex 2 subunit inhibitor of BRCA1 associated protein 1 gene (BAP1)-deficient tumors, are currently being explored.