Ricky K. Taira

Knowledge-based image retrieval with spatial and temporal constructs

A knowledge-based approach to retrieve medical images by feature and content with spatial and temporal constructs is developed. Selected objects of interest in an image are segmented and contours are generated. Features and content are extracted and stored in a database. Knowledge about image features can be expressed as a type abstraction hierarchy (TAH), the high-level nodes of which represent the most general concepts. Traversing TAH nodes allows approximate matching by feature and content if an exact match is not available. TAHs can be generated automatically by clustering algorithms based on feature values in the databases and hence are scalable to large collections of image features. Since TAHs are generated based on user classes and applications, they are context- and user-sensitive. A knowledge-based semantic image model is proposed to represent the various aspects of an image objects characteristics. The model provides a mechanism for accessing and processing spatial, evolutionary and temporal queries. A knowledge-based spatial temporal query language (KSTL) has been developed that extends ODMGs OQL and supports approximate matching of features and content, conceptual terms and temporal logic predicates. Further, a visual query language has been developed that accepts point-click-and-drag visual iconic input on the screen that is then translated into KSTL. User models are introduced to provide default parameter values for specifying query conditions. We have implemented the KMeD (Knowledge-based Medical Database) system using these concepts.

The knowledge-based object-oriented PICQUERY/sup +/ language

PICQUERY/sup +/, a high-level domain-independent query language for pictorial and alphanumeric database management, is introduced. The PICQUERY/sup +/ language and its underlying stacked image data model are enhanced with major advances that include: convenient specification of the data domain space among a multimedia database federation, visualization of underlying data models, knowledge-based hierarchies, and domain rules, understanding of high-level abstract data types, ability to perform data object matches based on imprecise or fuzzy descriptors, imprecise relational correlators, and temporal and object evolutionary events, specification of alphanumeric and image processing algorithms on data, and specification of alphanumeric and image visualization methods for user presentation. The power of PICQUERY/sup +/ is illustrated using examples drawn from the medical imaging domain. A graphical menu-driven user interface is demonstrated for this domain as an example of the menu interface capabilities of PICQUERY/sup +/. >

A knowledge-based approach for retrieving images by content

A knowledge based approach is introduced for retrieving images by content. It supports the answering of conceptual image queries involving similar-to predicates, spatial semantic operators, and references to conceptual terms. Interested objects in the images are represented by contours segmented from images. Image content such as shapes and spatial relationships are derived from object contours according to domain specific image knowledge. A three layered model is proposed for integrating image representations, extracted image features, and image semantics. With such a model, images can be retrieved based on the features and content specified in the queries. The knowledge based query processing is based on a query relaxation technique. The image features are classified by an automatic clustering algorithm and represented by Type Abstraction Hierarchies (TAHs) for knowledge based query processing. Since the features selected for TAH generation are based on context and user profile, and the TAHs can be generated automatically by a clustering algorithm from the feature database, our proposed image retrieval approach is scalable and context sensitive. The performance of the proposed knowledge based query processing is also discussed.

KMeD: a knowledge-based multimedia medical distributed database system

Abstract The objectives of the Knowledge-Based Multimedia Medical Distributed Database System (KMeD) are to: query medical multimedia distributed databases by both image content and alphanumeric content; model the temporal, spatial, and evolutionary nature of medical objects; formulate queries using conceptual and imprecise medical terms and support cooperative processing; develop a domain-independent, high-level query language and a medical domain user interface to support KMeD functionality; and provide analysis and presentation methods for visualization of knowledge and data models. Using rules derived from application and domain knowledge, approximate and conceptual queries may be answered. These concepts are validated in a testbed linked with radiology image databases. The joint research between the UCLA Computer Science Department and the School of Medicine assures that the prototype system is of direct interest to medical research and practice. The results of this research are extensible to other multimedia database applications.

Evidence-based radiology: Requirements for electronic access

RATIONALE AND OBJECTIVES The purpose of this study was to determine the electronic requirements for supporting evidence-based radiology in todays medical environment. MATERIALS AND METHODS A software engineering technique, use case modeling, was performed for several clinical settings to determine the use of imaging and its role in evidence-based practice, with particular attention to issues relating to data access and the usage of clinical information. From this basic understanding, the analysis was extended to encompass evidence-based radiologic research and teaching. RESULTS The analysis showed that a system supporting evidence-based radiology must (a) provide a single point of access to multiple clinical data sources so that patient data can be readily used and incorporated into comprehensive radiologic consults and (b) provide quick access to external evidence in the way of similar patient cases and published medical literature, thus supporting evidence-based practice. CONCLUSION Information infrastructures that aim to support evidence-based radiology not only must address issues related to the integration of clinical data from heterogeneous databases, but must facilitate access and filtering of patient data in order to improve radiologic consultation.

A semantic modeling approach for image retrieval by content

We introduce a semantic data model to capture the hierarchical, spatial, temporal, and evolutionary semantics of images in pictorial databases. This model mimics the users conceptual view of the image content, providing the framework and guidelines for preprocessing to extract image features. Based on the model constructs, a spatial evolutionary query language (SEQL), which provides direct image object manipulation capabilities, is presented. With semantic information captured in the model, spatial evolutionary queries are answered efficiently. Using an object-oriented platform, a prototype medical-image management system was implemented at UCLA to demonstrate the feasibility of the proposed approach.

Context-Based Electronic Health Record: Toward Patient Specific Healthcare

Due to the increasingly data-intensive clinical environment, physicians now have unprecedented access to detailed clinical information from a multitude of sources. However, applying this information to guide medical decisions for a specific patient case remains challenging. One issue is related to presenting information to the practitioner: displaying a large (irrelevant) amount of information often leads to information overload. Next-generation interfaces for the electronic health record (EHR) should not only make patient data easily searchable and accessible, but also synthesize fragments of evidence documented in the entire record to understand the etiology of a disease and its clinical manifestation in individual patients. In this paper, we describe our efforts toward creating a context-based EHR, which employs biomedical ontologies and (graphical) disease models as sources of domain knowledge to identify relevant parts of the record to display. We hypothesize that knowledge (e.g., variables, relationships) from these sources can be used to standardize, annotate, and contextualize information from the patient record, improving access to relevant parts of the record and informing medical decision making. To achieve this goal, we describe a framework that aggregates and extracts findings and attributes from free-text clinical reports, maps findings to concepts in available knowledge sources, and generates a tailored presentation of the record based on the information needs of the user. We have implemented this framework in a system called Adaptive EHR, demonstrating its capabilities to present and synthesize information from neurooncology patients. This paper highlights the challenges and potential applications of leveraging disease models to improve the access, integration, and interpretation of clinical patient data.

Natural Language Processing with Dynamic Classification Improves P300 Speller Accuracy and Bit Rate

The P300 speller is an example of a brain-computer interface that can restore functionality to victims of neuromuscular disorders. Although the most common application of this system has been communicating language, the properties and constraints of the linguistic domain have not to date been exploited when decoding brain signals that pertain to language. We hypothesized that combining the standard stepwise linear discriminant analysis with a Naive Bayes classifier and a trigram language model would increase the speed and accuracy of typing with the P300 speller. With integration of natural language processing, we observed significant improvements in accuracy and 40-60% increases in bit rate for all six subjects in a pilot study. This study suggests that integrating information about the linguistic domain can significantly improve signal classification.

Implementation of a large-scale picture archiving and communication system

This paper describes the implementation of a large-scale picture archiving and communication system (PACS) in a clinical environment. The system consists of a PACS infrastructure, composed of a PACS controller, a database management system, communication networks, and optical disk archive. It connects to three MR units, four CT scanners, three computed radiography systems, and two laser film digitizers. Seven display stations are on line 24 h/day, 7 days/wk in genitourinary radiology (2K), pediatric radiology in-patient (1K and 2K) and outpatient (2K), neuroradiology (2K), pediatric ICU (1K), coronary care unit (1K), and one laser film printing station. The PACS is integrated with the hospital information system and the radiology information system. The system has been in operation since February 1992. We have integrated this PACS as a clinical component in daily radiology practice. It archives an average of 2.0-gigabyte image data per workday. A 3-mo system performance of various components are tabulated. The deployment of this large-scale PACS signifies a milestone in our PACS research and development effort. Radiologists, fellows, residents, and clinicians use it for case review, conferences, and occasionally for primary diagnosis. With this large-scale PACS in place, it will allow us to investigate the two critical issues raised when PACS research first started 10 yrs ago: system performance and cost effectiveness between a digital-based and a film-based system.

Medical Imaging Informatics

Imaging is one of the most important sources of clinically observable evidence that provides broad coverage, can provide insight on low-level scale properties, is noninvasive, has few side effects, and can be performed frequently. Thus, imaging data provides a viable observable that can facilitate the instantiation of a theoretical understanding of a disease for a particular patient context by connecting imaging findings to other biologic parameters in the model (e.g., genetic, molecular, symptoms, and patient survival). These connections can help inform their possible states and/or provide further coherent evidence. The field of radiomics is particularly dedicated to this task and seeks to extract quantifiable measures wherever possible. Example properties of investigation include genotype characterization, histopathology parameters, metabolite concentrations, vascular proliferation, necrosis, cellularity, and oxygenation. Important issues within the field include: signal calibration, spatial calibration, preprocessing methods (e.g., noise suppression, motion correction, and field bias correction), segmentation of target anatomic/pathologic entities, extraction of computed features, and inferencing methods connecting imaging features to biological states.