|
|
On Validation of Algorithms for Dynamic Medical Data Separation
Tichý, Ondřej
The problem of dynamic medical image sequence separation is studied. We introduced the state of the art algorithms for medical sequence decomposition together with those that are proposed by us. The validation and the comparison of the algorithms are nontrivial and challenging task. We propose to use a synthetic data where a ground truth is available so it is possible to compute a significant statistics for comparison reason. Moreover, we proposed a comparison on 99 real data from renal scintigraphy where relative renal functions are automatically computed and compared with those obtained by physician.
|
|
|
Convolution Model of Time-activity Curves in Blind Source Separation
Tichý, Ondřej ; Šmídl, Václav
Availability of input and organ functions is a prerequisite for analysis of dynamic image sequences in scintigraphy and positron emission tomography (PET) via kinetic models. In PET, the input function can be directly measured by sampling the arterial blood. This invasive procedure can be substituted by extraction of the input function from the observed images. Standard procedure for the extraction is based on manual selection of a region of interest (ROI) which is user-dependent and inaccurate. The aim of our contribution is to demonstrate a new procedure for simultaneous estimation of the input and organ functions from the observed image sequence. We design a mathematical model that integrates all common assumption of the domain, including convolution of the input function and tissue-specific kernels. The input function as well as the kernel parameters are considered to be unknown. They are estimated from the observed images using the Variational Bayes method.
|
|
|
Model Consideration for Blind Source Separation of Medical Image Sequences
Tichý, Ondřej
The problem of functional analysis of medical image sequences is studied. The obtained images are assumed to be a superposition of images of underlying biological organs. This is commonly modeled as a Factor Analysis (FA) model. However, this model alone allows for biologically impossible solutions. Therefore, we seek additional biologically motivated assumptions that can be incorporated into the model to yield better solutions. In this paper, we review additional assumptions such as convolution of time activity, regions of interest selection, and noise analysis. All these assumptions can be incorporated into the FA model and their parameters estimated by the Variation Bayes estimation procedure. We compare these assumptions and discuss their influence on the resulting decomposition from diagnostic point of view. The algorithms are tested and demonstrated on real data from renal scintigraphy; however, the methodology can be used in any other imaging modality.
|
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
guest ::
