ABSTRACT
Artificial intelligence is a blooming branch of medical device. Its development and quality control all rely on high quality clinical data. Since there is no established standard or guidance yet, it is important to study how to build and utilize a dataset appropriately and scientifically, especially for the decrease of clinical trial expense. With reference to the current status of premarket review and related guidance in developed countries, this paper analyzes the role and requirement of datasets in the quality control of AI medical device, providing useful information for regulation agencies and the development of public datasets for AI.
Subject(s)
Artificial Intelligence , Data Analysis , Equipment and Supplies , Quality ControlABSTRACT
This paper analyses overall situation of the national quality inspection for medical devices in recent 13 years. The statistics cover the inspected varieties, sampling quantity and quality status. The achievements and suggestions are provided, which are helpful for future work.
Subject(s)
Humans , Equipment and Supplies , Reference StandardsABSTRACT
This paper introduces the implement method of DICOM medical image compression technology, The image part of DICOM files are extracted and converted to BMP format. The non-image information in DICOM file are stored into the text. When the final image of JPEG standard and non-image information are encapsulated to DICOM format images, it realizes the compression of medical image, which is beneficial to the image storage and transmission.
Subject(s)
Data Compression , Methods , Image Processing, Computer-Assisted , Methods , SoftwareABSTRACT
<p><b>OBJECTIVE</b>Establish the test platform of the intraocular lens loop, and the platform was evaluated through the experiment.</p><p><b>METHODS</b>The intraocular lens loop test platform is made up with three models. The different intraocular lens haptics support force can be completed by replacing different sample holder model.</p><p><b>RESULTS</b>The standard deviation and the coefficient of variation were calculated through the result of the fifteen samples. The standard deviation was 0.04 mN, and the coefficient of variation was 0.66%. The two values were in the acceptable range.</p><p><b>CONCLUSIONS</b>The platform was so stabilizing that it could be used to test support force of IOL loop. The different shapes of IOL could be tested on the platform through the replacement of the holder model.</p>
Subject(s)
Lenses, Intraocular , Prosthesis DesignABSTRACT
How to use clustering techniques in PACS system is introduced. Two kinds of cluster solution to configure PACS system is proposed.
Subject(s)
Computer Systems , Radiology Information SystemsABSTRACT
The regulatory history and status of in vitro diagnostic reagents (IVD) at home and abroad are introduced. Suggestions are also provided on the administration of IVD.
Subject(s)
Diagnostic Techniques and Procedures , Health Services Administration , Indicators and Reagents , Reference Standards , Product Surveillance, PostmarketingABSTRACT
Maximization of mutual information is a powerful criterion for 3D medical image registration, allowing robust and fully accurate automated rigid registration of multi-modal images in a various applications. In this paper, a method based on normalized mutual information for 3D image registration was presented on the images of CT, MR and PET. Powell's direction set method and Brent's one-dimensional optimization algorithm were used as optimization strategy. A multi-resolution approach is applied to speedup the matching process. For PET images, pre-procession of segmentation was performed to reduce the background artefacts. According to the evaluation by the Vanderbilt University, Sub-voxel accuracy in multi-modality registration had been achieved with this algorithm.