| 1. |
- Cirillo, Marco Domenico, et al.
(författare)
-
Time-Independent Prediction of Burn Depth using Deep Convolutional Neural Networks
- 2019
-
Ingår i: Journal of Burn Care & Research. - : Oxford University Press. - 1559-047X .- 1559-0488. ; 40:6, s. 857-863
-
Tidskriftsartikel (refereegranskat)abstract
- We present in this paper the application of deep convolutional neural networks, which are a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Colour images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pre-trained deep convolutional neural networks: VGG-16, GoogleNet, ResNet-50, and ResNet-101. In the end, the best 10-fold cross-validation results obtained from ResNet- 101 with an average, minimum, and maximum accuracy are 81.66%, 72.06% and 88.06%, respectively; and the average accuracy, sensitivity and specificity for the four different types of burn depth are 90.54%, 74.35% and 94.25%, respectively. The accuracy was compared to the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and therefore can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.
|
|
| 2. |
- Lind, Emelie, et al.
(författare)
-
Assessment of MRI contrast agent concentration by quantitative susceptibility mapping (QSM) : application to estimation of cerebral blood volume during steady state
- 2017
-
Ingår i: Magnetic Resonance Materials in Physics, Biology, and Medicine. - : Springer Science and Business Media LLC. - 0968-5243 .- 1352-8661. ; 30:6, s. 555-566
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: One major issue in dynamic susceptibility contrast MRI (DSC-MRI) is to accurately determine contrast agent (CA) concentration, since T2* relaxivity in vivo is generally unknown and varies between blood and tissue. In this study, quantitative susceptibility mapping (QSM) was used for quantification of CA concentration. Materials and methods: A DSC-MRI protocol, including phase data acquisition, was applied to 20 healthy volunteers in a test–retest study. By selecting a CSF reference region of interest (ROI), the values of all QSM images were shifted to show no CA-induced change in CSF. CA concentration and cerebral blood volume (CBV) were estimated using shifted QSM data. CSF reference ROI optimization was evaluated by investigation of CBV repeatability. The CBV age dependence was analysed and tissue T2* relaxivity was estimated. Results: The best repeatability of CBV, using an optimal CSF reference ROI, showed test-versus-retest correlations of r = 0.81 and r = 0.91 for white and grey matter, respectively. A slight CBV decrease with age was observed, and the estimated in vivo T2* relaxivity was 85 mM−1s−1. Conclusion: Provided that a carefully selected CSF reference ROI is used to shift QSM image values, susceptibility information can be used to estimate concentration of contrast agent and to calculate CBV.
|
|
