Advancements in Whole-Body Multi-Modal MRI:
Towards computer-aided diagnosis of metastatic bone disease 

Cancer that begins in an organ, such as the lungs, breast, or prostate, and then spreads to the bone or other organs marks the beginning of metastatic disease. The confident detection of metastatic bone disease and the reliable assessment of the tumour load and treatment response is essential to improve patients’ comfort and increase life expectancy.

Magnetic resonance imaging (MRI) has been successfully used for monitoring of bone metastatic disease. Anatomical whole-body sequences offer excellent resolution and sensitivity for the detection of neoplastic cells within the bone marrow. The combination with spatially pre-aligned functional diffusion-weighted whole-body MRI and apparent diffusion coefficient maps allows for focused, efficient, multi-parametric and holistic evaluation of the total tumour volume, diffusion volume and treatment response assessment.

One of the major challenges for integrating whole-body MRI in clinical routine comes from the large amount of data to be reviewed, making lesion detection and quantification demanding for a radiologist, but also prone to error. Additionally, whole-body MR images are often corrupted with multiple spatial and intensity artifacts, which degrade the performance of medical image processing algorithms.

The PhD research presents a design of a fully automated computer-aided diagnosis system for the detection and segmentation of the metastatic bone disease using whole-body multi-modal MRI. The system focuses on advanced prostate cancer patients introducing multiple novel medical image processing contributions improving whole-body MR image quality, such as the spatial groupwise image registration (to align multiple MRI modalities), multi-atlas segmentation (to define the skeleton region of interest), image standardization (to map MRI intensities into comparable ranges). Finally, a deep learning framework for detection and segmentation of bone metastases is proposed.

"One of the major challenges for integrating whole-body MRI in clinical routine comes from the large amount of data to be reviewed"

Jakub received the degree in Biomedical Engineering from the Lodz University of Technology, Lodz, Poland in 2012 and the M.Sc. degree in Biomedical Engineering from the University of Groningen, Groningen, The Netherlands in 2014. Since 2014 he has been affiliated with the ETRO-MIT research group of the Vrije Universiteit Brussel where he started his PhD in the field of medical image processing. Research interests: medical image registration, medical image segmentation using deep learning, automatic diagnosis of cancer from whole-body MRI.