Radiomics is an emerging translational field of research aiming to extract mineable high-dimensional data from clinical images. The radiomic process can be divided into distinct steps with definable inputs and outputs, such as image acquisition and reconstruction, image segmentation, features extraction and qualification, analysis, and model building. Each step needs careful evaluation for the construction of robust and reliable models to be transferred into clinical practice for the purposes of prognosis, non-invasive disease tracking, and evaluation of disease response to treatment. After the definition of texture parameters (shape features; first-, second-, and higher-order features), we briefly discuss the origin of the term radiomics and the methods for selecting the parameters useful for a radiomic approach, including cluster analysis, principal component analysis, random forest, neural network, linear/logistic regression, and other. Reproducibility and clinical value of parameters should be firstly tested with internal cross-validation and then validated on independent external cohorts. This article summarises the major issues regarding this multi-step process, focussing in particular on challenges of the extraction of radiomic features from data sets provided by computed tomography, positron emission tomography, and magnetic resonance imaging.

Objective To estimate the cumulative radiation exposure and lifetime attributable risk of cancer incidence associated with lung cancer screening using annual low dose computed tomography (CT). Design Secondary analysis of data from a lung cancer screening trial and risk-benefit analysis. Setting 10 year, non-randomised, single centre, low dose CT, lung cancer screening trial (COSMOS study) which took place in Milan, Italy in 2004-15 (enrolment in 2004-05). Secondary analysis took place in 2015-16. Participants High risk asymptomatic smokers aged 50 and older, who were current or former smokers (≥20 pack years), and had no history of cancer in the previous five years. Main outcome measures Cumulative radiation exposure from low dose CT and positron emission tomography (PET) CT scans, calculated by dosimetry software; and lifetime attributable risk of cancer incidence, calculated from the Biological Effects of Ionizing Radiation VII (BEIR VII) report. Results Over 10 years, 5203 participants (3439 men, 1764 women) underwent 42 228 low dose CT and 635 PET CT scans. The median cumulative effective dose at the 10th year of screening was 9.3 mSv for men and 13.0 mSv for women. According to participants’ age and sex, the lifetime attributable risk of lung cancer and major cancers after 10 years of CT screening ranged from 5.5 to 1.4 per 10 000 people screened, and from 8.1 to 2.6 per 10 000 people screened, respectively. In women aged 50-54, the lifetime attributable risk of lung cancer and major cancers was about fourfold and threefold higher than for men aged 65 and older, respectively. The numbers of lung cancer and major cancer cases induced by 10 years of screening in our cohort were 1.5 and 2.4, respectively, which corresponded to an additional risk of induced major cancers of 0.05% (2.4/5203). 259 lung cancers were diagnosed in 10 years of screening; one radiation induced major cancer would be expected for every 108 (259/2.4) lung cancers detected through screening. Conclusion Radiation exposure and cancer risk from low dose CT screening for lung cancer, even if non-negligible, can be considered acceptable in light of the substantial mortality reduction associated with screening.

Recent technological advances in the field of artificial intelligence hold promise in addressing medical challenges in breast cancer care, such as early diagnosis, cancer subtype determination and molecular profiling, prediction of lymph node metastases, and prognostication of treatment response and probability of recurrence. Radiomics is a quantitative approach to medical imaging, which aims to enhance the existing data available to clinicians by means of advanced mathematical analysis using artificial intelligence. Various published studies from different fields in imaging have highlighted the potential of radiomics to enhance clinical decision making. In this review, we describe the evolution of AI in breast imaging and its frontiers, focusing on handcrafted and deep learning radiomics. We present a typical workflow of a radiomics analysis and a practical “how-to” guide. Finally, we summarize the methodology and implementation of radiomics in breast cancer, based on the most recent scientific literature to help researchers and clinicians gain fundamental knowledge of this emerging technology. Alongside this, we discuss the current limitations of radiomics and challenges of integration into clinical practice with conceptual consistency, data curation, technical reproducibility, adequate accuracy, and clinical translation. The incorporation of radiomics with clinical, histopathological, and genomic information will enable physicians to move forward to a higher level of personalized management of patients with breast cancer.