An Introduction to Radiomics: Capturing Tumour Biology in Space and Time

Journal Title: Hellenic Journal of Radiology - Year 2018, Vol 3, Issue 1

Abstract

Currently, there is a shift from visual interpretation of medical images, which is highly variable, to the extraction of high-dimensional meaningful data the so called Radiomic signatures that can be used in conjunction with machine learning algorithms to predict clinical outcomes. Quantification of imaging biomarkers can be used to make predictions on whether a specific treatment will work for a specific patient, and can aid in differential diagnosis problems or may offer prognostic capabilities related to disease recurrence or relapse. Modern algorithms based on machine learning techniques can be used to provide automatic or semi-automatic segmentation with minimal human interaction. Feature extraction is the calculation of texture and shape imaging features that can be used along with clinical biomarkers. Feature selection is important to avoid overfitting and exclude redundant features improving the quality of data, by reducing their dimensionality. Following to that, multiple machine learning algorithms can be recruited in order to find the optimal that can provide with the best performance. Algorithms like Bays, linear regression, Support Vector Machines, Random Forests and others are currently used.

Authors and Affiliations

Nickolas Papanikolaou, Joao Santinha

Keywords

Related Articles

Covered stents for symptomatic iliac artery in-stent restenosis treatment: Midterm Results

Purpose: To evaluate the safety and efficacy of balloon-expandable covered stent (CS) for treatment of symptomatic iliac artery in-stent restenosis (ISR). Material and methods: This was a retrospective, single-arm, sing...

Normal and abnormal MRI findings after abdominal radical trachelectomy (ART) for cervical cancer

Purpose: To report MRI findings after abdominal radical trachelectomy (ART) for early-stage cervical cancer. Material and Methods: During an 8-year period, 25 women (mean age: 32 years) with biopsy-proven cervical cance...

Prevalence and quantification of left ventricular trabeculation detected by cardiac MR imaging in non-ischaemic primary or secondary cardiomyopathies

Purpose: To assess the prevalence and the qualitative and quantitative characteristics of left ventricular (LV) trabeculation in patients with non-ischaemic primary or secondary cardiomyopathies using detailed cardiac ma...

Terminal veins and neonatal intraventricular haemorrhage of prematurity: a sonographic approach

Purpose: To evaluate the sonographic appearance and velocities of terminal veins (TVs) in premature neonates without/with germinal matrix (GMH) or intraventricular haemorrhage (IVH), and to investigate for an early sonog...

Contrast enhanced sonographic study of the spleen

The spleen shows a variety of pathological entities. Ultrasound (US) is the first imaging modality performed for its assessment. When it is not conclusive, the addition of intravenous contrast agents improves performance...

Download PDF file
  • EP ID EP373623
  • DOI -
  • Views 145
  • Downloads 0

How To Cite

Nickolas Papanikolaou, Joao Santinha (2018). An Introduction to Radiomics: Capturing Tumour Biology in Space and Time. Hellenic Journal of Radiology, 3(1), -. https://europub.co.uk./articles/-A-373623