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
- EP ID EP373623
- DOI -
- Views 136
- Downloads 0
New pulmonary lesions in an oncologic patient
A 44-year-old woman with a history of right elbow osteosarcoma underwent her routine follow-up chest CT scan. She had been treated with chemotherapy (cisplatin, epirubicin and ifosfamide) and her WBC count at the time of...
A 3-year old child with fever and disturbance of consciousness
A 3-year old girl presented to the emergency department withhighfever, irritability and moderate disturbance of consciousness. Laboratory tests did not show abnormal serum chemistry or inflammatory markers. Analysis of c...
MRI findings related to Image Defined Risk Factors (IDRFs) in children with neuroblastic tumours: Analysis for structured reporting
Neuroblastic tumours constitute a heterogenous group of tumours with diverse presentation, variable malignant behaviour and prognosis. Image Defined Risk Factors (IDRFs) have been described in the International Neuroblas...
Undetected pancreatic carcinoma: retrospective analysis of missed findings at computed tomography
Purpose Our purpose was to retrospectively investigate whether prediagnostic CT scan may show suggestive findings of early pancreatic cancer. Material and Methods We searched our radiology and surgery database to identi...
Assessment of Breast Cancer Response to Neoadjuvant Chemotherapy: a Radiologist’s Perspective
Neoadjuvant chemotherapy (NAC) plays a central role in the management of breast cancer (BC) patients, especially (but not exclusively) in cases of locally advanced cancers, to achieve operability. A wide spectrum of imag...