Skeletal maturity is assessed visually by comparing hand radiographs to a standardized reference image atlas. Most
common are the methods by Greulich & Pyle and Tanner & Whitehouse. For computer-aided diagnosis (CAD), local
image regions of interest (ROI) such as the epiphysis or the carpal areas are extracted and evaluated. Heuristic
approaches trying to automatically extract, measure and classify bones and distances between bones suffer from the high
variability of biological material and the differences in bone development resulting from age, gender and ethnic origin.
Content-based image retrieval (CBIR) provides a robust solution without delineating and measuring bones. In this work,
epiphyseal ROIs (eROIS) of a hand radiograph are compared to previous cases with known age, mimicking a human
observer. Leaving-one-out experiments are conducted on 1,102 left hand radiographs and 15,428 metacarpal and
phalangeal eROIs from the publicly available USC hand atlas. The similarity of the eROIs is assessed by a combination
of cross-correlation, image distortion model, and Tamura texture features, yielding a mean error rate of 0.97 years and a
variance of below 0.63 years. Furthermore, we introduce a publicly available online-demonstration system, where
queries on the USC dataset as well as on uploaded radiographs are performed for instant CAD. In future, we plan to
evaluate physician with CBIR-CAD against physician without CBIR-CAD rather than physician vs. CBIR-CAD.
Proc. SPIE. 7628, Medical Imaging 2010: Advanced PACS-based Imaging Informatics and Therapeutic Applications
KEYWORDS: Medicine, Computer aided diagnosis and therapy, Databases, Image processing, Diagnostics, Medical imaging, Mammography, Computer aided design, Radiology, Picture Archiving and Communication System
The large and continuously growing amount of medical image data demands access methods with regards to content
rather than simple text-based queries. The potential benefits of content-based image retrieval (CBIR) systems for
computer-aided diagnosis (CAD) are evident and have been approved. Still, CBIR is not a well-established part of daily
routine of radiologists. We have already presented a concept of CBIR integration for the radiology workflow in
accordance with the Integrating the Healthcare Enterprise (IHE) framework. The retrieval result is composed as a Digital
Imaging and Communication in Medicine (DICOM) Structured Reporting (SR) document. The use of DICOM SR
provides interchange with PACS archive and image viewer. It offers the possibility of further data mining and automatic
interpretation of CBIR results. However, existing standard templates do not address the domain of CBIR. We present a
design of a SR template customized for CBIR. Our approach is based on the DICOM standard templates and makes use
of the mammography and chest CAD SR templates. Reuse of approved SR sub-trees promises a reliable design which is
further adopted to the CBIR domain. We analyze the special CBIR requirements and integrate the new concept of similar
images into our template. Our approach also includes the new concept of a set of selected images for defining the
processed images for CBIR. A commonly accepted pre-defined template for the presentation and exchange of results in a standardized format promotes the widespread application of CBIR in radiological routine.
Radiological bone age assessment is based on local image regions of interest (ROI), such as the epiphysis or the area of
carpal bones. These are compared to a standardized reference and scores determining the skeletal maturity are calculated.
For computer-aided diagnosis, automatic ROI extraction and analysis is done so far mainly by heuristic approaches. Due
to high variations in the imaged biological material and differences in age, gender and ethnic origin, automatic analysis is
difficult and frequently requires manual interactions. On the contrary, epiphyseal regions (eROIs) can be compared to
previous cases with known age by content-based image retrieval (CBIR). This requires a sufficient number of cases with
reliable positioning of the eROI centers. In this first approach to bone age assessment by CBIR, we conduct leaving-oneout
experiments on 1,102 left hand radiographs and 15,428 metacarpal and phalangeal eROIs from the USC hand atlas.
The similarity of the eROIs is assessed by cross-correlation of 16x16 scaled eROIs. The effects of the number of eROIs,
two age computation methods as well as the number of considered CBIR references are analyzed. The best results yield
an error rate of 1.16 years and a standard deviation of 0.85 years. As the appearance of the hand varies naturally by up to
two years, these results clearly demonstrate the applicability of the CBIR approach for bone age estimation.
Increasing use of digital imaging processing leads to an enormous amount of imaging data. The access to picture
archiving and communication systems (PACS), however, is solely textually, leading to sparse retrieval results because
of ambiguous or missing image descriptions. Content-based image retrieval (CBIR) systems can improve the clinical
diagnostic outcome significantly. However, current CBIR systems are not able to integrate their results with clinical
workflow and PACS. Existing communication standards like DICOM and HL7 leave many options for implementation
and do not ensure full interoperability. We present a concept of the standardized integration of a CBIR system for the
radiology workflow in accordance with the Integrating the Healthcare Enterprise (IHE) framework. This is based on the
IHE integration profile 'Post-Processing Workflow' (PPW) defining responsibilities as well as standardized
communication and utilizing the DICOM Structured Report (DICOM SR). Because nowadays most of PACS and RIS
systems are not yet fully IHE compliant to PPW, we also suggest an intermediate approach with the concepts of the
CAD-PACS Toolkit. The integration is independent of the particular PACS and RIS system. Therefore, it supports the
widespread application of CBIR in radiological routine. As a result, the approach is exemplarily applied to the Image
Retrieval in Medical Applications (IRMA) framework.