基于内容的图像与视频检索技术研究

本文介绍了图像和视频检索技术的目前状况及几个有特色的CBIR系统，探讨了CBIR系统的体系结构、底层视觉特征和高层语义特征的提取与表达方法，以及基于内容视频检索的镜头边界检测、视频镜头内容表示和视频高层语义表示等技术，提出了该领域存在的问题和未来发展方向。     

基于内容的脑部MRI影像搜索的医学信息系统的研制

挖掘数字医学影像信息并为辅助检测服务是当前医学信息管理领域急需解决的问题.基于内容的医学影像检索方法(content based information retrieval,CBIR)是解决此问题有效手段.本文总结了建立基于内容图像检索的300万张脑部MRI的影像数据库和信息系统开发的应用的一些技术和方法,包括数据库的建立、搜索方法的实现等,为临床应用提供服务.     

Automatic medical image annotation and keyword-based image retrieval using relevance feedback

This paper presents novel multiple keywords annotation for medical images, keyword-based medical image retrieval, and relevance feedback method for image retrieval for enhancing image retrieval performance. For semantic keyword annotation, this study proposes a novel medical image classification method combining local wavelet-based center symmetric-local binary patterns with random forests. For keyword-based image retrieval, our retrieval system use the confidence score that is assigned to each annotated keyword by combining probabilities of random forests with predefined body relation graph. To overcome the limitation of keyword-based image retrieval, we combine our image retrieval system with relevance feedback mechanism based on visual feature and pattern classifier. Compared with other annotation and relevance feedback algorithms, the proposed method shows both improved annotation performance and accurate retrieval results.     

DWT-DCT hybrid scheme for medical image compression

With the development of communication technology the applications and services of health telemetics are growing. In view of the increasingly important role played by digital medical imaging in modern health care, it is necessary for large amount of image data to be economically stored and/or transmitted. There is a need for the development of image compression systems that combine high compression ratio with preservation of critical information. During the past decade wavelets have been a significant development in the field of image compression. In this paper, a hybrid scheme using both discrete wavelet transform (DWT) and discrete cosine transform (DCT) for medical image compression is presented. DCT is applied to the DWT details, which generally have zero mean and small variance, thereby achieving better compression than obtained from either technique alone. The results of the hybrid scheme are compared with JPEG and set partitioning in hierarchical trees (SPIHT) coder and it is found that the performance of the proposed scheme is better.     

医学影像数据库的索引及检索技术的研究

随着医学影像数据库数据量的剧增,迫切需要研究高效的索引技术以支持基于图像内容的检索。介绍了医学影像数据库索引技术的特点,比较分析了几种典型的空间数据索引方法（如R树、VA文件、A树、NB树和M树）及其作为医学图像数据库索引的性能。     

A generic concept for the implementation of medical image retrieval systems

This paper presents a technical framework to support the development and installation of system for content-based image retrieval in medical applications (IRMA). A strict separation of feature extraction, feature storage, feature comparison, and the user interfaces is suggested. This allows to reuse implemented components in different retrieval algorithms, which improves software quality, shortens the development cycle for applications, and allows to introduce standardized end-user interfaces. Based on the proposed framework, the IRMA engine has been established, which is currently used to evaluate content-based retrieval methods on a collection of 20,000 medical and 135,000 non-medical images.     

A new method of content based medical image retrieval and its applications to CT imaging sign retrieval

This paper proposes a new method of content based medical image retrieval through considering fused, context-sensitive similarity. Firstly, we fuse the semantic and visual similarities between the query image and each image in the database as their pairwise similarities. Then, we construct a weighted graph whose nodes represent the images and edges measure their pairwise similarities. By using the shortest path algorithm over the weighted graph, we obtain a new similarity measure, context-sensitive similarity measure, between the query image and each database image to complete the retrieval process. Actually, we use the fused pairwise similarity to narrow down the semantic gap for obtaining a more accurate pairwise similarity measure, and spread it on the intrinsic data manifold to achieve the context-sensitive similarity for a better retrieval performance. The proposed method has been evaluated on the retrieval of the Common CT Imaging Signs of Lung Diseases (CISLs) and achieved not only better retrieval results but also the satisfactory computation efficiency.     

Optimization of block size for DCT-based medical image compression

In view of the increasing importance of medical imaging in healthcare and the large amount of image data to be transmitted/stored, the need for development of an efficient medical image compression method, which would preserve the critical diagnostic information at higher compression, is growing. Discrete cosine transform (DCT) is a popular transform used in many practical image/video compression systems because of its high compression performance and good computational efficiency. As the computational burden of full frame DCT would be heavy, the image is usually divided into non-overlapping sub-images, or blocks, for processing. This paper aims to identify the optimum size of the block, in reference to compression of CT, ultrasound and X-ray images. Three conflicting requirements are considered, namely processing time, compression ratio and the quality of the reconstructed image. The quantitative comparison of various block sizes has been carried out on the basis of benefit-to-cost ratio (BCR) and reconstruction quality score (RQS). Experimental results are presented that verify the optimality of the 16 x 16 block size.     

基于内容的医学图像检索

本文介绍了基于内容的医学图像检索的目的、意义和实现方法以及国内外研究现状和关键技术,并对未来的发展方向做了展望。     

Optimization of block size for DCT-based medical image compression

In view of the increasing importance of medical imaging in healthcare and the large amount of image data to be transmitted/stored, the need for development of an efficient medical image compression method, which would preserve the critical diagnostic information at higher compression, is growing. Discrete cosine transform (DCT) is a popular transform used in many practical image/video compression systems because of its high compression performance and good computational efficiency. As the computational burden of full frame DCT would be heavy, the image is usually divided into non-overlapping sub-images, or blocks, for processing. This paper aims to identify the optimum size of the block, in reference to compression of CT, ultrasound and X-ray images. Three conflicting requirements are considered, namely processing time, compression ratio and the quality of the reconstructed image. The quantitative comparison of various block sizes has been carried out on the basis of benefit-to-cost ratio (BCR) and reconstruction quality score (RQS). Experimental results are presented that verify the optimality of the 16 × 16 block size.     

Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms

The purpose of this study was to evaluate image similarity measures employed in an information-theoretic computer-assisted detection (IT-CAD) scheme. The scheme was developed for content-based retrieval and detection of masses in screening mammograms. The study is aimed toward an interactive clinical paradigm where physicians query the proposed IT-CAD scheme on mammographic locations that are either visually suspicious or indicated as suspicious by other cuing CAD systems. The IT-CAD scheme provides an evidence-based, second opinion for query mammographic locations using a knowledge database of mass and normal cases. In this study, eight entropy-based similarity measures were compared with respect to retrieval precision and detection accuracy using a database of 1820 mammographic regions of interest. The IT-CAD scheme was then validated on a separate database for false positive reduction of progressively more challenging visual cues generated by an existing, in-house mass detection system. The study showed that the image similarity measures fall into one of two categories; one category is better suited to the retrieval of semantically similar cases while the second is more effective with knowledge-based decisions regarding the presence of a true mass in the query location. In addition, the IT-CAD scheme yielded a substantial reduction in false-positive detections while maintaining high detection rate for malignant masses.     

A client server model to facilitate creation of a medical image teaching library

A simple and convenient system for indexing and archiving medical images used in teaching was developed. The approach was to combine a smart client-side graphical user interface that controlled image size, file format, and keyword structure, and communicated with the hospital information system via hypertext mark-up language, to populate the interface with user selectable pull-down menus. The result is a system that is easily extensible beyond the radiology images for which it was originally designed. Only minor modifications of the client interface are required to adapt the program to accept any file format or image type.     

Creation of reference DNA barcode library and authentication of medicinal plant raw drugs used in Ayurvedic medicine

Background

Ayurveda is a system of traditional medicine that originated in ancient India, and it is still in practice. Medicinal plants are the backbone of Ayurveda, which heavily relies on the plant-derived therapeutics. While Ayurveda is becoming more popular in several countries throughout the World, lack of authenticated medicinal plant raw drugs is a growing concern. Our aim was to DNA barcode the medicinal plants that are listed in the Ayurvedic Pharmacopoeia of India (API) to create a reference DNA barcode library, and to use the same to authenticate the raw drugs that are sold in markets.

Methods

We have DNA barcoded 347 medicinal plants using rbcL marker, and curated rbcL DNA barcodes for 27 medicinal plants from public databases. These sequences were used to create Ayurvedic Pharmacopoeia of India - Reference DNA Barcode Library (API-RDBL). This library was used to authenticate 100 medicinal plant raw drugs, which were in the form of powders (82) and seeds (18).

Results

Ayurvedic Pharmacopoeia of India - Reference DNA Barcode Library (API-RDBL) was created with high quality and authentic rbcL barcodes for 374 out of the 395 medicinal plants that are included in the API. The rbcL DNA barcode differentiated 319 species (85 %) with the pairwise divergence ranging between 0.2 and 29.9 %. PCR amplification and DNA sequencing success rate of rbcL marker was 100 % even for the poorly preserved medicinal plant raw drugs that were collected from local markets. DNA barcoding revealed that only 79 % raw drugs were authentic, and the remaining 21 % samples were adulterated. Further, adulteration was found to be much higher with powders (ca. 25 %) when compared to seeds (ca. 5 %).

Conclusions

The present study demonstrated the utility of DNA barcoding in authenticating medicinal plant raw drugs, and found that approximately one fifth of the market samples were adulterated. Powdered raw drugs, which are very difficult to be identified by taxonomists as well as common people, seem to be the easy target for adulteration. Developing a quality control protocol for medicinal plant raw drugs by incorporating DNA barcoding as a component is essential to ensure safety to the consumers.

     

An integrated medical image database and retrieval system using a web application server

We developed an Integrated Medical Image Database and Retrieval System (INIS) for easy access by medical staff. The INIS mainly consisted of four parts: specific servers to save medical images from multi-vendor modalities of CT, MRI, CR, ECG and endoscopy; an integrated image database (DB) server to save various kinds of images in a DICOM format; a Web application server to connect clients to the integrated image DB and the Web browser terminals connected to an HIS system. The INIS provided a common screen design to retrieve CT, MRI, CR, endoscopic and ECG images, and radiological reports, which would allow doctors to retrieve radiological images and corresponding reports, or ECG images of a patient simultaneously on a screen. Doctors working in internal medicine on average accessed information 492 times a month. Doctors working in cardiological and gastroenterological accessed information 308 times a month. Using the INIS, medical staff could browse all or parts of a patient's medical images and reports.     

Voice-activated retrieval of mammography reference images

We undertook this project to integrate context sensitive computer-based educational and decision making aids into the film interpretation and reporting process, and to determine the clinical utility of this method as a guide for further system development. An image database of 347 digital mammography images was assembled and image features were coded. An interface was developed to a computerized speech recognition radiology reporting system which was modified to translate reported findings into database search terms. These observations were used to formulate database search strategies which not only retrieved similar cases from the image database, but also other cases that were related to the index case in different ways. The search results were organized into image sets intended to address common questions that arise during image interpretation. An evaluation of the clinical utility of this method was performed as a guide for further system development. We found that voice dictation of prototypical mammographic cases resulted in automatic retrieval of reference images. The retrieved images were organized into sets matching findings, diagnostic hypotheses, diagnosis, spectrum of findings or diagnoses, closest match to dictated case, or user specified parameters. Two mammographers graded the clinical utility of each form of system output. We concluded that case specific and problem specific image sets may be automatically generated from spoken case dictation. A potentially large number of retrieved images may be divided into subsets which anticipate common clinical problems. This automatic method of context sensitive image retrieval may provide a “continuous’; form of education integrated into routine case interpretation.     

在医院图书馆中开展医学继续教育

阐述了医院图书馆开展医学继续教育(CME)的必要性，介绍了医院图书馆进行CME的3种方式，并提出医院图书馆应关注的问题。