Advantages and disadvantages of endocrown restorations of endodontically treated teeth with large coronal destruction / 中华口腔医学杂志

The strength of endodontically treated teeth were reduced apparently because of structural damage, therefore further reduction of healthy tissue should be avoided as much as possible in restoration. Endocrown made by chair-side CAD/CAM is some kind of minimal invasive restoration, and the retention of restoration is achieved by reliable bonding and macromechanial retention forces. Without post preparation, the root structure could be resevered. Following the indications and use of biomechanical dentin-like CAD/CAM materials could reduce the adverse effect of tensile stress on cervical part.

Research of automatic peripheral white blood cell classification system / 医疗卫生装备

Identification and classification of white blood cells are important for clinical diagnosis.Many researchers have been seeking the effective methods for white blood cells' automatic classification based on morphological characters.After cell segmentation,leukocytes' feature acquirement and selection,this paper accomplishes white blood cells' automatic classification using Sugeno-model fuzzy neural network and compares the result with that from classifier of BP network.

Parsing and encoding of DICOM Nesting Data Set and its application to PACS / 医疗卫生装备

DICOM is a standard for data format and transmission of digital medical image. DICOM Data Set is a binary data stream using DICOM encoding rule. DICOM Nesting Data Set is a kind of complex Data Set with a tree structure, and is widely used in DICOM services and encoding of DICOM files for its special structure. In this article, the functions and encoding rule of Data Set and Nesting Data Set in DICOM format are presented, and the way of parsing and organizing of them is put forward. The realization method and practical application are also discussed.

Rapid method of object detection based on color feature / 医疗卫生装备

Object detection systems are widely used in many fields. To speed up object detection, a rapid method based on color feature is presented in this paper. Artificial neural network is used for color classification. A series of original objects are gained through searching the most outstanding feature of the marker based on multi-resolution. A set of features obtained from these original objects in the original image, and artificial neural network are used for object classification. Experimental results prove the effectiveness of this method.