| 1. |
|
|
| 2. |
- Damangir, Soheil, et al.
(författare)
-
Multispectral MRI segmentation of age related white matter changes using a cascade of support vector machines
- 2012
-
Ingår i: Journal of the Neurological Sciences. - : Elsevier BV. - 0022-510X .- 1878-5883. ; 322:1-2, s. 211-216
-
Tidskriftsartikel (refereegranskat)abstract
- White matter changes (WMC) are the focus of intensive research and have been linked to cognitive impairment and depression in the elderly. Cumbersome manual outlining procedures make research on WMC labor intensive and prone to subjective bias. We present a fast, fully automated method for WMC segmentation using a cascade of reduced support vector machines (SVMs) with active learning. Data of 102 subjects was used in this study. Two MRI sequences (T1-weighted and FLAIR) and masks of manually outlined WMC from each subject were used for the image analysis. The segmentation framework comprises pre-processing, classification (training and core segmentation) and post-processing. After pre-processing, the model was trained on two subjects and tested on the remaining 100 subjects. The effectiveness and robustness of the classification was assessed using the receiver operating curve technique. The cascade of SVMs segmentation framework outputted accurate results with high sensitivity (90%) and specificity (99.5%) values, with the manually outlined WMC as reference. An algorithm for the segmentation of WMC is proposed. This is a completely competitive and fast automatic segmentation framework, capable of using different input sequences, without changes or restrictions of the image analysis algorithm.
|
|
| 3. |
- Graham, Ian, et al.
(författare)
-
New strategies for the development of lipid-lowering therapies to reduce cardiovascular risk.
- 2018
-
Ingår i: European heart journal. Cardiovascular pharmacotherapy. - : Oxford University Press (OUP). - 2055-6845 .- 2055-6837. ; 4:2, s. 119-127
-
Tidskriftsartikel (refereegranskat)abstract
- The very high occurrence of cardiovascular events presents a major public health issue, because treatment remains suboptimal. Lowering LDL cholesterol (LDL-C) with statins or ezetimibe in combination with a statin reduces major adverse cardiovascular events. The cardiovascular risk reduction in relation to the absolute LDL-C reduction is linear for most interventions without evidence of attenuation or increase in risk at low LDL-C levels. Opportunities for innovation in dyslipidaemia treatment should address the substantial risk of lipid-associated cardiovascular events among patients optimally treated per guidelines but who cannot achieve LDL-C goals and who could benefit from additional LDL-C-lowering therapy or experience side effects of statins. Fresh approaches are needed to identify promising drug targets early and develop them efficiently. The Cardiovascular Round Table of the European Society of Cardiology (ESC) convened a workshop to discuss new lipid-lowering strategies for cardiovascular risk reduction. Opportunities to improve treatment approaches and the efficient study of new therapies were explored. Circulating biomarkers may not be fully reliable proxy indicators of the relationship between treatment effect and clinical outcome. Mendelian randomization studies may better inform development strategies and refine treatment targets before Phase 3. Trials should match the drug to appropriate lipid and patient profile, and guidelines may move towards a precision-based approach to individual patient management. Stakeholder collaboration is needed to ensure continued innovation and better international coordination of both regulatory aspects and guidelines. It should be noted that risk may also be addressed through increased attention to other risk factors such as smoking, hypertension, overweight, and inactivity.
|
|
