Studies in health technology and informatics
-
Stud Health Technol Inform · Jan 2002
Performance evaluation of artificial intelligence classifiers for the medical domain.
The application of artificial intelligence systems is still not widespread in the medical field, however there is an increasing necessity for these to handle the surfeit of information available. One drawback to their implementation is the lack of criteria or guidelines for the evaluation of these systems. ⋯ This paper shows evidence that the most prevalent form of intelligent system, neural networks, is generally not being evaluated rigorously regarding classification precision. A taxonomy of the types of evaluation tests that can be carried out, to gauge inherent performance of the outputs of intelligent systems has been assembled, and the results of this presented in a clear and concise form, which should be applicable to all intelligent classifiers for medicine.
-
Emergency healthcare delivery involves a variety of activities performed from the time of a call to the ambulance service till the time of patient's disposal from the emergency department of a hospital. Workflow systems have recently received considerable attention in the healthcare field since they overcome organizational structures and support collaboration and coordination requirements by automatically routing relevant information where and when needed. In particular, healthcare workflow systems implemented over the Web can form the basis for a collaborative environment by bringing together healthcare professionals who are geographically dispersed and, hence, creating virtual healthcare workgroups organized around patient care. In this paper, a web-based workflow system is presented that was developed to support emergency healthcare processes and to provide an infrastructure for the integration of pre-hospital and in-hospital emergency healthcare.
-
Stud Health Technol Inform · Jan 2001
Experimental and theoretical analysis of wavelet-based denoising filter for echocardiographic images.
One of the most significant features of diagnostic echocardiographic images is to reduce speckle noise and make better image quality. In this paper we proposed a simple and effective filter design for image denoising and contrast enhancement based on multiscale wavelet denoising method. Wavelet threshold algorithms replace wavelet coefficients with small magnitude by zero and keep or shrink the other coefficients. ⋯ High spectral content tends to over-estimate the noise standard deviation estimation performed at the finest level of the DWT. As a result, a lower threshold parameter is required to get the optimal S/MSE. The standard WCS theory predicts a threshold that depends on the number of signal samples only.
-
Stud Health Technol Inform · Jan 2001
Measurement of in-vivo local shear modulus by combining multiple phase offsets mr elastography.
To provide realistic surgical simulation, haptic feedback is important. In the existing surgical simulators, the fidelity of the deformation and haptic feedback is limited because they are based on the subjective evaluation of the expert-user and not on an objective model-based evaluation. To obtain elastic modulus of in-vivo human tissues, magnetic resonance elastography (MRE) was developed. ⋯ To confirm the reliability of this method, a computer simulation and phantom study were performed. The shear modulus measured with various elastic objects was well consistent with the value obtained by MRE and the mechanical method. The shear moduli of excised porcine liver and in-vivo human calf muscle were also analyzed by this method. on the subjective evaluation of an expert-user and not on objective model-based methods.