Retrieving and viewing medical images

摘要

As medical imaging becomes more affordable, and the diversity of diagnostic modalities and therapeutic treatments increase, the amount of data being stored increases, and the problem becomes even more critical. One approach to improve retrieval efficiency of images is to employ semantics to establish a defined set of search and classification terms. However, such semantic systems still require the user to make a selection of the most appropriate term or terms to classify a report or image, and the accuracy of the results are thus dependent on the skill and knowledge of the classifier. According to a first aspect of the invention, a retriever is provided for retrieving a medical image having a searchable attribute, the retriever being configured to interface with a semantic database and an image database, and wherein the searchable attribute is determined by segmenting the medical image, using the anatomical model.

主权项

1. A hardware-implemented retriever that retrieves a medical image having a searchable attribute, the retriever being configured to interface with:
a semantic database configured to store and provide anatomical semantics, a model database configured to store anatomical models, wherein the semantic database and the model database are different databases; and an image database configured to store and provide the medical image, wherein the searchable attribute is determined by:
retrieving, from the model database, an anatomical model, wherein the anatomical model comprises a label associated with an anatomical structure;determining a presence of the anatomical structure by segmenting at least one anatomical structure from the medical image using the anatomical model;retrieving anatomical semantics from the semantic database, anddetermining a relevant semantic for the at least one anatomical structure based upon the label; the retriever comprising:
a user interface for providing a user selection, anda processor configured to:
display a medical report of a patient on a display device and the medical report includes text with distinguished semantic terms and the distinguished semantic terms are selectable;in response to an input selecting one or more distinguished semantic terms from the displayed medical report text, retrieve the medical image with searchable attributes based on the one or more distinguished semantic terms;display the retrieved medical image according to one or more viewing attributes determined by a bounding box around the segmented structure and the bounding box includes all voxels of the segmented at least one anatomical structure, and the bounding box is identified by two points of segmented at least one anatomical structure, and the viewing attributes are generated based on the bounding box.