Blind MRI Brain Lesion Inpainting Using Deep Learning

• Published in: Simulation and Synthesis in Medical Imaging Vol. 12417; pp. 41 - 49
• Main Authors: Manjón, José V., Romero, José E., Vivo-Hernando, Roberto, Rubio, Gregorio, Aparici, Fernando, de la Iglesia-Vaya, Maria, Tourdias, Thomas, Coupé, Pierrick
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2020; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Deep learning; Lesion inpainting; MRI; Robust segmentation
• ISBN: 3030595196; 9783030595197
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-59520-3_5

In brain image analysis many of the current pipelines are not robust to the presence of lesions which degrades their accuracy and robustness. For example, performance of classic medical image processing operations such as non-linear registration or segmentation rapidly decreases when dealing with lesions. To minimize their impact, some authors have proposed to inpaint these lesions so classic pipelines can be used. However, this requires to manually delineate the regions of interest which is time consuming. In this paper, we propose a deep network that is able to blindly inpaint lesions in brain images automatically allowing current pipelines to robustly operate under pathological conditions. We demonstrate the improved robustness/accuracy in the brain segmentation problem using the SPM12 pipeline with our automatically inpainted images.