Recent advances in large scale whole body MRI image analysis: Imiomics

Abstract

Due to the massive amount of medical image data being made available, in research and clinical work, computer-aided tools are valuable and have a great potential for a sustainable work situation for physicians and for generating disease understanding. High-end methods in the present era of big data and artifical intelligence are designed to efficiently find patterns in large scale image data. The amount of data is today often too big to be parsed by human experts, and computer-assisted methods often perform at least as well as human experts on well-defined problems where it is possible to quantify performance by a loss function. This paper gives an overview of a computer-assisted method, Imiomics. Imiomics enables statistical analyses of relations between whole body image image data in large cohorts and other non-imaging data, at an unprecedented spatial resolution. Its usefulness in medicine is illustrated by a number of medical applications, and some aspects of technical development that enable the analysis is also presented. We conclude that computer-assisted methods, such as Imiomics, are essential for efficient processing of the huge amount of data in today's medical research and, to some extent, clinical practice.