Measurement of treatment response and survival prediction in malignant pleural mesothelioma

Kidd, Andrew Craig (2023) Measurement of treatment response and survival prediction in malignant pleural mesothelioma. PhD thesis, University of Glasgow.

Full text available as:
[thumbnail of 2022KiddPhD.pdf] PDF
Download (4MB)


Malignant pleural mesothelioma (MPM) is a rare cancer of the mesothelial cells of the visceral and parietal pleurae that is heterogeneous in terms of biology, prognosis and response to systemic anti-cancer therapy (SACT). The primary tumour forms an unusual, complex shape which makes survival prediction and response measurement uniquely challenging. Computed tomography (CT) imaging is the bedrock of radiological quantification and response assessment, but it has major limitations that translate into low sensitivity and high inter-observer variation when classifying response using Response Evaluation Classification In Solid Tumours (mRECIST) criteria. Magnetic resonance imaging (MRI) tools have been developed that overcome some of these problems but cost and availability of MRI mean that optimisation of CT and better use for data acquired by this method are important priorities in the short term. In this thesis, I conducted 3 studies focused on, 1) development of a semi-automated volumetric segmentation method for CT based on recently positive studies in MRI, 2) training and external validation of a deep learning artificial intelligence (AI) tool for fully automated volumetric segmentation based on CT data, and, 3) use of non-tumour imaging features available from CT related to altered body composition for development of new prognostic models, which could assist in selection of patients for treatment and improving tolerance to treatment by targeting the systemic consequences of MPM.

The aim of Chapter 3 is to develop a semi-automated MPM tumour volume segmentation method that would serve as the ground truth for the training of a fully automated AI algorithm. A semi-automated approach to pleural tumour segmentation has been developed using MRI scans which calculated volumetric measurements from seed points - defined by differential tumour enhancement - placed within a pre-defined volume of pleural tumour. I extrapolated this MRI method using contrast-enhanced CT scans in 23 patients with MPM. Radiodensity values – defined by Hounsfield units (HU) - were calculated for the different thoracic tissues by placing regions of interest (ROI) on visible areas of pleural tumour with similar ROIs placed on other thoracic tissues. Pleural volume contours were drawn on axial CT slices and propagated throughout the volume by linear interpolation using volumetric software (Myrian Intrasense® software v2.4.3 (Paris, France)). Seed points based on the radiodensity range of pleural tumour were placed on representative areas of tumour with regions grown. There were similarities in median thoracic tissue HU values: pleural tumour, 52 [IQR 46 to 60] HU; intercostal muscle, 20.4 [IQR 11.9 to 32.3] HU; diaphragm, 40.4 [IQR 26.4 to 56.4] HU and pleural fluid, 11.8 [IQR 8.3 to 17.8] HU. There was also reduced definition between MPM tumour and neighbouring structures. The mean time taken to complete semi-automated volumetric segmentations for the 8 CT scans examined was 25 (SD 7) minutes. The semi-automated CT volumes were larger than the MRI volumes with a mean difference between MRI and CT volumes of -457.6 cm3 (95% limits of agreement -2741 to +1826 cm3). The complex shape of MPM tumour and overlapping thoracic tissue HU values precluded HU threshold-based region growing and meant that semi-automated volumetry using CT was not possible in this thesis.

Chapter 4 describes a multicentre retrospective cohort study that developed and validated an automated AI algorithm – termed a deep learning Convolutional Neural Network (CNN) - for volumetric MPM tumour segmentation. Due to the limitations of the semi-automated approach described in Chapter 3, manually annotated tumour volumes were used to train the CNN. The manual segmentation method ensured that all the parietal pleural tumour was included in the respective volumes. Although the manual CT volumes were consistently smaller than semi-automated MRI volumes (average difference between AI and human volumes 74.8 cm3), they were moderately correlated (Pearson’s r=0.524, p=0.0103). There was strong correlation (external validation set r=0.851, p<0.0001) and agreement (external validation set mean AI minus human volume difference of +31 cm3 between human and AI tumour volumes). AI segmentation errors (4/60 external validation set cases) were associated with complex anatomical features. There was agreement between human and AI volumetric responses in 20/30 (67%) cases. There was agreement between AI volumetric and mRECIST classification responses in 16/30 (55%) cases. Overall survival (OS) was shorter in patients with higher AI-defined pre-chemotherapy tumour volumes (HR=2.40, 95% CI 1.07 to 5.41, p=0.0114).

Survival prediction in MPM is difficult due to the heterogeneity of the disease. Previous survival prediction models have not included measures of body composition which are prognostic in other solid organ cancers. In Chapter 5, I explore the impact of loss of skeletal muscle and adipose tissue at the level of the third lumbar vertebra (L3) and the loss of skeletal muscle at the fourth thoracic (T4) vertebrae on survival and response to treatment in patients with MPM receiving chemotherapy. Skeletal and adipose muscle areas at L3 and T4 were quantified by manual delineation of relevant muscle and fat groups using ImageJ software (U.S. National Institutes of Health, Bethesda, MD) on pre-chemotherapy and response assessment CT scans, with normalisation for height. Sarcopenia at L3 was not associated with shorter OS at the pre-chemotherapy (HR 1.49, 95% CI 0.95 to 2.52, p=0.077) or response assessment time points (HR 1.48, 95% CI 0.97 to 2.26, p=0.0536). A higher visceral adipose tissue index (VFI) measured at L3 was associated with shorter OS (HR 1.95, 95% CI 1.05 to 3.62, p=0.0067). In multivariate analysis, obesity was associated with improved OS (HR 0.36, 95% CI 0.20 to 0.65, p<0.001) while interval VFI loss (HR 1.81, 95% CI 1.04 to 3.13, p=0.035) was associated with reduced OS. Overall loss of skeletal muscle index at the fourth thoracic vertebra (T4SMI) during treatment was associated with poorer OS (HR 2.79, 95% CI 1.22 to 6.40, p<0.0001). Skeletal muscle index on the ipsilateral side of the tumour at the fourth thoracic vertebra (Ipsilateral T4SMI) loss was also associated with shorter OS (HR 2.91, 95% CI 1.28 to 6.59, p<0.0001). In separate multivariate models, overall T4SMI muscle loss (HR 2.15, 95% CI 102 to 4.54, p=0.045) and ipsilateral T4SMI muscle loss (HR 2.85, 95% CI 1.17 to 6.94, p=0.021) were independent predictors of OS. Response to chemotherapy was not associated with decreasing skeletal muscle or adipose tissue indices.

Item Type: Thesis (PhD)
Qualification Level: Doctoral
Subjects: R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
Colleges/Schools: College of Medical Veterinary and Life Sciences > School of Infection & Immunity > Immunology & Infection
Supervisor's Name: Blyth, Professor Kevin and Chalmers, Professor Anthony
Date of Award: 2023
Depositing User: Theses Team
Unique ID: glathesis:2023-83543
Copyright: Copyright of this thesis is held by the author.
Date Deposited: 20 Apr 2023 15:10
Last Modified: 20 Apr 2023 15:10
Thesis DOI: 10.5525/gla.thesis.83543
Related URLs:

Actions (login required)

View Item View Item


Downloads per month over past year