Computer-assisted planning of liver surgery

Computer-assisted surgical planning systems, despite their enormous support in the decision-making process, have faced challenges in clinical practice mainly due to the difficulty of obtaining 3D patient-specific models. This requires the segmentation of anatomical structures, a process traditionally considered tedious, complex, and imprecise. However, recent advances in artificial intelligence, particularly in convolutional neural networks, have enabled automatic segmentation, which presents a new clinical reality where 3D patient-specific models can be generated systematically for surgical planning and guidance. Additionally liver resection planning also requires precise definition of virtual resection lines, which help clinicians to visualize the surgical cutting path, affected vessels and resection margins. In addition, virtual resections allow the computation of the estimated resected volume. This new reality makes the perfect scenario to introduce AI and advanced geometrical modeling to liver surgical planning, ultimately toward improving clinical practice.

Faculty Supervisor:

Gabor Fichtinger

Student:

Partner:

Oslo University Hospital

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology; Artificial Intelligence

University:

Queen's University

Program: