About KIME

KIME in Japanese means 'texture', an element of the surface or volume distinguished by its perceived visual properties.

KIME is a DICOM processing software focussed on quantitative oncologic imaging designed around the concept of textrure. The underlying framework combines elements of computer-vision and statistical models to provide advanced image processing power. It includes tools for semi-automated segmentation and calculation of a wide range of textural (radiomic) features from CT, PET and MR images.

Developed using Microsoft .NET Framework, KIME is a flexible, paralell research platform for development and testing of new radiomic features and machine-learning concepts.

Core Features

Reads DICOM files and images

Image pre-processing and normalization

Semi-automated segmentation

Multiple ROI's

Radiomic analysis

Advanced intra-tumor heterogeneity analysis

Save results in Microsoft Excel format (.xls)

Complies with the Image Biomarker Standardisation Initiative

Radiomic Features

Intensity-based Statistics

Intensity histogram

Gray Level Co-occurrence Matrix (GLCM)

Gray Level Run Length Matrix (GLRLM)

Neighborhood Grey-Level Different Matrix (NGLDM)

Gray Level Zone Size Matrix (GLZSM)

Experimental Features and Models

Gray Level Affinity Matrix (GLAM)

Image perturbation and ROI randomisation