EdgeRunner: a novel shape-based pipeline for tumours analysis and characterisation

Abstract

Characterisation of tumours on imaging is usually performed qualitatively by visual analysis by radiologists. However, incorporating quantitative imaging features would potentially increase diagnostic accuracy and would improve patient care and management. The goal is to eventually be able to distinguish certain quantifiable features, which along with qualitative ones could differentiate between benign and malignant tumours. This may obviate the need for invasive procedures such as a biopsy, and may also allow for earlier detection as well as better follow-up. The shape of a tumour is often qualitatively described to help differentiate between tumor types. A smooth round outline is generally thought to be indicative of a benign or slowly growing lesion. A malignant neoplasm, on the other hand, tends to have disorganised growth and has a lobulated or spiculated margin. In this manuscript, we introduce a new computed tomography-based pipeline for tumour analysis and characterisation. This method yields an easily interpretable histogram-based index of lobularity. The EdgeRunner Pipeline performs equally well in studies of individual subjects, or in population-based assessments. Importantly, the methods can be easily translated to clinical use.

Keywords:

• Tumour analysis
• tumour lobularity
• shape analysis