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.
• No residual tumour (RT) at surgery is the most important prognostic factor in OC. • Radiomic features related to mass size, randomness and homogeneity were associated with RT. • Progression of disease within 12 months (PD12) indicates worse prognosis in OC. • A model including clinical and radiomic features performed better than only-clinical model to predict PD12.
Society of Radiology. This e-offprint isAbstract Objectives To evaluate the radiation dose in routine multidetector computed tomography (MDCT) examinations in Italian population. Methods This was a retrospective multicentre study included 5,668 patients from 65 radiology departments who had undergone common CT protocols: head, chest, abdomen, chest-abdomen-pelvis (CAP), spine and cardiac. Data included patient characteristics, CT parameters, volumetric CT dose index (CTDI vol ) and dose length product (DLP) for each CT acquisition phase. Descriptive statistics were calculated, and a multi-regression analysis was used to outline the main factors affecting exposure. Results The 75th percentiles of CTDI vol (mGy) and DLP (mGy cm) for whole head were 69 mGy and 1,312 mGy cm, respectively; for chest, 15 mGy and 569 mGy cm; spine, 42 mGy and 888 mGy cm; cardiac, 7 mGy and 131 mGy cm for calcium score, and 61 mGy and 1,208 mGy cm for angiographic CT studies. High variability was present in the DLP of abdomen and CAP protocols, where multiphase examinations dominated (71 % and 73 % respectively): for abdomen, 18 mGy, with 555 and 920 mGy cm in abdomen and abdomen-pelvis acquisitions respectively; for CAP, 17 mGy, with 508, 850 and 1,200 mGy cm in abdomen, abdomen-pelvis and CAP acquisitions respectively. Conclusion The results of this survey could help in the definition of updated diagnostic reference levels (DRL). Key Points • Radiation dose associated with multidetector CT (MDCT) is an important health issue.• This national survey assessed dose exposures of 5,668 patients undergoing MDCT.• Dose indices correlate with BMI, voltage, rotation time, pitch and tube current.• These results may contribute to an update of national diagnostic reference levels.
Background: To evaluate whether a model based on radiomic and clinical features may be associated with lymph node (LN) status and overall survival (OS) in lung cancer (LC) patients; to evaluate whether CT reconstruction algorithms may influence the model performance. Methods: patients operated on for LC with a pathological stage up to T3N1 were retrospectively selected and divided into training and validation sets. For the prediction of positive LNs and OS, the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression model was used; univariable and multivariable logistic regression analysis assessed the association of clinical-radiomic variables and endpoints. All tests were repeated after dividing the groups according to the CT reconstruction algorithm. p-values < 0.05 were considered significant. Results: 270 patients were included and divided into training (n = 180) and validation sets (n = 90). Transfissural extension was significantly associated with positive LNs. For OS prediction, high- and low-risk groups were different according to the radiomics score, also after dividing the two groups according to reconstruction algorithms. Conclusions: a combined clinical–radiomics model was not superior to a single clinical or single radiomics model to predict positive LNs. A radiomics model was able to separate high-risk and low-risk patients for OS; CTs reconstructed with Iterative Reconstructions (IR) algorithm showed the best model performance.
In this study we evaluated the correlation between neuropsychological impairment (measured with the Brief Repeatable Battery Neuropsychological Tests) and (juxta)cortical lesions detected with FLAIR and the relative sensitivity of the FLAIR sequence compared to spin-echo MRI sequences in detecting (juxta)cortical MS lesions. A total of 39 patients with definite MS were evaluated by MRI with a conventional and fast spin echo sequence and fast FLAIR sequence, and neuropsychological tests of the Brief Repeatable Battery Neuropsychological tests were performed. The Z-score of all subtests were used to calculate a Cognitive Impairment Index. The results show that a high number of (juxta)cortical lesions is detected with thin slice FLAIR (30% of all lesions seen). This percentage was not superior to spin-echo, reflecting the thin slice thickness (3 mm) we used. The lesions detected with FLAIR were to a certain degree different ones than the lesions detected with the other techniques. While the number of non-cortical lesions correlated with the expanded disability status scale (r=0.32, P=0.045), the number of (juxta)cortical lesions detected with the FLAIR showed a correlation (r=0.34, P=0.035) with the Cognitive Impairment Index. Our study underlines the high number of (juxta)cortical lesions in MS and the value of thin slice FLAIR sequence to detect such lesions with MRI. It also stresses the importance of (juxta)cortical lesions on determining neuropsychological impairment. Multiple Sclerosis (2000) 6 280 - 285
In this study we evaluated the correlation between neuropsychological impairment (measured with the Brief Repeatable Battery Neuropsychological Tests) and (juxta)cortical lesions detected with FLAIR and the relative sensitivity of the FLAIR sequence compared to spin-echo MRI sequences in detecting (juxta)cortical MS lesions. A total of 39 patients with definite MS were evaluated by MRI with a conventional and fast spin echo sequence and fast FLAIR sequence, and neuropsychological tests of the Brief Repeatable Battery Neuropsychological tests were performed. The Z-score of all subtests were used to calculate a Cognitive Impairment Index. The results show that a high number of (juxta)cortical lesions is detected with thin slice FLAIR (30% of all lesions seen). This percentage was not superior to spin-echo, reflecting the thin slice thickness (3 mm) we used. The lesions detected with FLAIR were to a certain degree different ones than the lesions detected with the other techniques. While the number of non-cortical lesions correlated with the expanded disability status scale (r=0.32, P=0.045), the number of (juxta)cortical lesions detected with the FLAIR showed a correlation (r=0.34, P=0.035) with the Cognitive Impairment Index. Our study underlines the high number of (juxta)cortical lesions in MS and the value of thin slice FLAIR sequence to detect such lesions with MRI. It also stresses the importance of (juxta)cortical lesions on determining neuropsychological impairment. Multiple Sclerosis (2000) 6 280 - 285
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.