In this paper a new technique, Empirical Mode Decomposition(EMD), for use in non-stationary and non-linear data processing, was introduced. Some simulated signal, real ECG and RRI signals combined with Hilbert Transform method were analyzed. The authors also put emphasis on the differences between EMD and Wavelet Transform.
Algorithms ; Computer Simulation ; Diagnosis, Computer-Assisted ; methods ; Electrocardiography ; Heart Rate

In the paper, iridology and computer-aided iridiagnosis technologies are briefly introduced and the extraction method of the collarette contour is then investigated. The iris map can be overlapped on the original iris image based on collarette contour extraction. The research on collarette contour extraction and iris map overlap is of great importance to computer-aided iridiagnosis technologies.
Diagnosis, Computer-Assisted ; methods ; Humans ; Image Processing, Computer-Assisted ; methods ; Iris Diseases ; diagnosis ; Software

The biochemical analysis of urine is an important inspection and diagnosis method in hospitals. The conventional method of urine analysis covers mainly colorimetric visual appraisement and automation detection, in which the colorimetric visual appraisement technique has been superseded basically, and the automation detection method is adopted in hospital; moreover, the price of urine biochemical analyzer on market is around twenty thousand RMB yuan (Y), which is hard to enter into ordinary families. It is known that computer vision system is not subject to the physiological and psychological influence of person, its appraisement standard is objective and steady. Therefore, according to the color theory, we have established a computer vision system, which can carry through collection, management, display, and appraisement of color difference between the color of standard threshold value and the color of urine test paper after reaction with urine liquid, and then the level of an illness can be judged accurately. In this paper, we introduce the Urine Test Biochemical Analysis method, which is new and can be popularized in families. Experimental result shows that this test method is easy-to-use and cost-effective. It can realize the monitoring of a whole course and can find extensive applications.
Automation ; Colorimetry ; methods ; Diagnosis, Computer-Assisted ; Humans ; Signal Processing, Computer-Assisted ; Urinalysis ; methods

In this paper, a new method of contour analysis is presented to find path in endoscopy navigation. At first, edge detection is used to endoscope image. Then we do skeleton extraction and connect the edge skeleton to contours by grouping criteria. At last we can get navigation information by analyzing the contours. Experiments show that this algorithm has good precision and stability.
Algorithms ; Diagnosis, Computer-Assisted ; Endoscopy ; methods ; Gastroscopy ; Humans ; Image Enhancement ; methods ; Image Processing, Computer-Assisted

Coronary angiography (CAG) as a typical imaging modality for the diagnosis of coronary diseases hasbeen widely employed in clinical practices. For CAG-based computer-aided diagnosis systems, accurate vessel segmentation plays a fundamental role. However, patients with bradycardia usually have a pacemaker which frequently interferes the vessel segmentation. In this case, the segmentation of vessels will be hard. To mitigate interferences of pacemakers and then extract main vessels more effectively in CAG images, we propose an approach. At first, a pseudo CAG (pCAG) image is generated through a part of a CAG sequence, in which the pacemaker exists. Then, a local feature descriptor is employed to register the relative location of pacemaker between the pCAG image and the target CAG image. Finally, combining the registration result and segmentation results of main vessels and pacemaker, interferences of pacemaker are removed and the segmentation of main vessels is improved. The proposed method is evaluated based on 11 CAG images with pacemakers acquired in clinical practices. An optimization ratio of the Dice coefficient is 12.04%, which demonstrates that our method can remove overlapping pacemakers and achieve the improvement of main vessel segmentation in CAG images.Our method can further become a helpful component in a CAG-based computer-aided diagnosis system, improving its diagnosis accuracy and efficiency.
Humans ; Coronary Angiography/methods* ; Diagnosis, Computer-Assisted ; Pacemaker, Artificial ; Image Processing, Computer-Assisted/methods* ; Algorithms

Based on theoretic analysis, a new method for measuring linearity of physiological instrument and its inner unit circuits is provided. In this method, the sawtooth wave signal, which includes a base wave and its odd-even times harmonic waves, is used to act as input signal, then the linearity of physiological instrument and its inner unit circuits can be measured by analyzing the shape and frequency property of the output signal. The results of experiment show this method is quick and convenient for measuring the linearity of physiological instrument and its inner unit circuits.
Diagnosis, Computer-Assisted ; methods ; Humans ; Monitoring, Physiologic ; instrumentation ; Signal Processing, Computer-Assisted

This paper, analyzes the defects and its limitations of computer-aided diagnosis system (CADS) in clinical practice in the past, proposes a new pattern CADS of designing method. We used the theory of multidetection, stored the accumulated experience in computer, established the knowledge base, and made the medical diagnosis through maximizing a posteriori (MAP) judgement rule. Statistical data revealed that the CADS had a high accuracy rate. The medical diagnosis can meet the demand for clinical treatments, and realize the clinical diagnostic application of information technology.
Bayes Theorem ; Decision Making, Computer-Assisted ; Diagnosis, Computer-Assisted ; methods ; Humans

Accurate area assessment of a burn injury and its treatment according to its depth of injury are the foundation of burn treatment due to its complexity, and various techniques and methods have been employed to solve these problems for many years. As the demand of modern medicine calls for individualized and precise therapeutic measures, it is clear that the traditional diagnostic and treatment measures are insufficient. The flourishing development of three-dimensional (3D) technology seems to provide new research approaches and technical opporturities for burn surgery. A series of techniques such as 3D model, 3D scanning, and 3D printing may be promising in advancing burn surgery through basic research to achieve rational clinical applications in the future. In this paper, the applications and achievements of 3D technology in burn surgery in recent years are summarized.
Body Surface Area ; Burns ; diagnosis ; pathology ; therapy ; Humans ; Image Processing, Computer-Assisted ; methods ; Therapy, Computer-Assisted

The differences of body surface temperature reflect the changes of the status of body tissues. In this regard, detecting and forecasting the changes of the surface temperature is the objective of the technique of medical thermal diagnosis, and how to diagnose the disease earlier with the use of thermal images is a common problem in the field of medical diagnostics and biological engineering. The authors put forward that utilizing the soft-sensing techniques in the field of engineering will be a good solution.
Body Temperature ; Diagnosis, Computer-Assisted ; Humans ; Image Interpretation, Computer-Assisted ; methods ; Infrared Rays ; Neural Networks (Computer) ; Skin Temperature ; Thermography ; methods

It is estimated that epilepsy, a chronic disorder of the nervous system, affects about 0.5%-2% of the population and about 10%-50% do not respond well to current antiepileptic medications and may not be candidates for surgery. For these patients, the unpredictability of seizure onset is a major cause of disability and mortality. Therefore, anticipation of an imminent seizure would be beneficial to patients because it could provide time for the application of preventive measures to keep the risk of seizure to a minimum. This paper reviews the feasibilities, the progress, existing problems and possible applications in the field of epileptic seizure prediction.
Algorithms ; Diagnosis, Computer-Assisted ; methods ; Electroencephalography ; methods ; Epilepsy ; diagnosis ; physiopathology ; Humans ; Seizures ; diagnosis ; physiopathology ; Signal Processing, Computer-Assisted