Marta obtained a Bachelor of Science (2012) and a Master of Science (2014) in Physics at Università degli Studi di Milano-Bicocca.
Driven by the interest in the applications of cutting-edge technologies to Medicine, she moved to London (UK) in 2015, after being awarded a 4-year scholarship for a Master of Research and subsequent PhD in Medical Imaging at University College London. During her PhD studies, she specialized in Medical Image Computing and Machine Learning, graduating in 2020 with a thesis titled “Automating the analysis of musculoskeletal imaging in the presence of hip implants”. From November 2019 to November 2020 she also worked as a Research Assistant at King’s College London, as part of the GIFT-Surg project on innovating computer-assisted intervention for fetal therapy.
Since December 2020 she works as Computer Vision Specialist in the A.I. Center at Humanitas Research Hospital.
Marta’s research interests mainly focus on the application of computer vision, machine learning and deep learning to automate the analysis of medical images and clinical data.
Main areas of expertise are medical image registration, segmentation and image quality enhancement. Her past research in the musculoskeletal field led to the development of algorithms that combine the complementary information of CT and MRI for patients with hip implants, towards imaging biomarkers extraction and patient-specific computational anatomy. She contributed to a research project on modelling the recovery trajectories of pediatric patients undergoing neurorehabilitation. She also investigated deep learning segmentation methods for fetal brain in MRI in relation to the diagnosis of Spina Bifida.
Current research concerns the development of novel detection, classification and segmentation algorithms for medical imaging, in order to support the clinical research and to improve clinician’s and patient’s experience at Humanitas Research Hospital.
– Ranzini MBM, Ebner M, Cardoso MJ, Fotiadou A, Vercauteren T, Henckel J, Hart A, Ourselin S, Modat M. Joint multimodal segmentation of clinical CT and MR from hip arthroplasty patients. In: Glocker B, Yao J, Vrtovec T, Frangi A, Zheng G. (eds) Computational Methods and Clinical Applications in Musculoskeletal Imaging. MSKI 2017. Lecture Notes in Computer Science, vol 10734. Springer, Cham. https://doi.org/10.1007/978-3-319-74113-0_7
– Ranzini MBM, Henckel J, Ebner M, Cardoso MJ, Isaac A, Vercauteren T, Ourselin S, Hart A, Modat M. Automated postoperative muscle assessment of hip arthroplasty patients using multimodal imaging joint segmentation. Computer Methods and Programs in Biomedicine. 2020; 183:105062. https://doi.org/10.1016/j.cmpb.2019.105062.
– Ranzini MBM, Groothuis I, Kläser K, Cardoso MJ, Henckel J, Ourselin S, Hart A, Modat M. Combining multimodal information for Metal Artefact Reduction: An unsupervised deep learning framework. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI); 2020. p. 600-604. https://doi.org/10.1109/ISBI45749.2020.9098633.
