Grades computacionais na recuperação de imagens médicas baseada em conteúdo

Abstract

OBJECTIVE: To utilize the grid computing technology to enable the utilization of a similarity measurement algorithm for content-based medical image retrieval. MATERIALS AND METHODS: The content-based images retrieval technique is comprised of two sequential steps: texture analysis and similarity measurement algorithm. These steps have been adopted for head and knee images for evaluation of accuracy in the retrieval of images of a single plane and acquisition sequence in a databank with 2,400 medical images. Initially, texture analysis was utilized as a pre-selection resource to obtain a set of the 1,000 most similar images as compared with a reference image selected by a clinician. Then, these 1,000 images were processed utilizing a similarity measurement algorithm on a computational grid. RESULTS: The texture analysis has demonstrated low accuracy for sagittal knee images (0.54) and axial head images (0.40). Nevertheless, this technique has shown effectiveness as a filter, pre-selecting images to be evaluated by the similarity measurement algorithm. Content-based images retrieval with similarity measurement algorithm applied on these pre-selected images has demonstrated satisfactory accuracy -0.95 for sagittal knee images, and 0.92 for axial head images. The high computational cost of the similarity measurement algorithm was balanced by the utilization of grid computing. CONCLUSION: The approach combining texture analysis and similarity measurement algorithm for content-based images retrieval resulted in an accuracy of > 90%. Grid computing has shown to be essential for the utilization of similarity measurement algorithm in the content-based images retrieval that otherwise would be limited to supercomputers.

Implementação e avaliação de um sistema de gerenciamento de imagens médicas com suporte à recuperação baseada em conteúdo

“…The results regarding the performance of the system for images retrieval by similarity utilizing texture attributes, with an overall mean rate of hits reaching 72% are compatible with results found by other studies in the literature (1,18,19) . Pereira Jr et al (18) have developed a study demonstrating that texture attributes can be useful in the automatic differentiation between normal regions and regions with nodules or microcalcifications on digitized mammographic images, with more than 90% of hits.…”

“…However, these attributes sensitivity for differentiating malignant from benign lesions decreases to as low as 50%. In a study involving the analysis of texture for images retrieval by similarity, Oliveira et al (19) have found results for accuracy of about 54% for sagittal images of knee, and 40% for axial images of head. Kinoshita et al (1) have presented results ranging between 78% and 83% of hits in a CBIR system based on texture and artificial neural networks developed to retrieve mammographic images by tissue density similarity.…”

Construction of an index of information from clinical practice in Radiology and Imaging Diagnosis based on text mining and thesaurus

“…Most of such lexical systems and vocabularies designed for communication are available only in English. Studies (10)(11)(12)(13) demonstrate that the application of such systems directly into the medical practice results in positive changes in the medical assistance quality, but, in certain circumstances, the application of a closed model of knowledge may bring difficulties to the use by specialists and even problems for the developer in the programming of technological solutions. The difficulty in the transposition of a closed terminology into the practice results fundamentally from the distancing between the theoretical perspective of using the developed terminology (how to use it, with which purpose, and who should/can use it), and the actual conditions of local use where such terminology will be utilized (which involves the institutional culture and the proper formalisms of each individual physician) (14) .…”