Towards detection of malignant mesothelioma from 4D magnetic resonance images of the thorax

• Grant number: 22/03754-5
• Support Opportunities: Scholarships in Brazil - Master
• Start date: September 01, 2022
• End date: January 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Alexandre Xavier Falcão
• Grantee: Taylla Milena Theodoro
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?, AP.TEM
• Associated scholarship(s): 22/14507-9 - Detection of malignant mesothelioma from 4D magnetic resonance images of the thorax: an evaluation and improvement study, BE.EP.MS

Abstract

Mesothelioma is an abnormal mass (a tumor) in the layers of tissues surrounding organs of the chest. Malignant Pleural Mesothelioma (MPM) is the most common primary malignancy of the parietal and visceral layers covering the lungs (the pleura). In a healthy individual, such layers of tissues are thinner than a strand of hair. The mesothelioma increases the thickness of the pleura, and it can be a benign or a malignant tumor. The patient prognosis is poor, with a median survival of 9-17 months after diagnosis. Current diagnostic pathways include clinical assessment, radiographic imaging, ultrasound-guided pleural aspiration, and additional imaging and pleural biopsy. A biomarker from images would be a significant advance to detect the MPM at its early stages in a non-invasive way. Recent findings from MR image sequences (a four-dimensional image) suggest the mean intensity profile of voxels over time, in some areas of the pleura, as a potential biomarker to distinguish between benign and malignant mesothelioma. This MSc project aims at developing a semi-automatic image analysis technique to identify those areas of the pleura from four-dimensional MR images and verify the effectiveness of the suggested biomarker in distinguishing malignant mesothelioma from other pleural diseases. The study will be developed in cooperation with medical researchers of the Cancer Research UK, Glasgow Centre, in Scotland. They will provide the MR images and evaluate our software tool with the semi-automatic image analysis technique. The MSc project includes a period at the Cancer Research UK (a BEPE project), in which the student will interact with our collaborators. (AU)