St. Jude Medical, Cardiology Division, Inc.

Oracle International Corporation

Erhan Erdemir

Carlo Pappone

Wenwen Li

Valtino X Afonso

Eric Jon Voth

Dennis J Morgan

Kenneth James Peterka

The embodiments disclosed herein relate to identifying phrases in an electronic document, where each token is one or more characters. Phrases are formed from the tokens, based on a position of each token relative to other tokens in the document. If the horizontal space between two tokens is less than a threshold, the two tokens are identified as a phrase. Information identifying phrases and tokens can be stored in a marked-up document. Value phrases can be identified by the content of the phrase. Thereafter, a label phrase can be identified based on proximity to the value phrase and/or the presence of an association symbol in the phrase. The label phrase and value phrase can be identified as a label-value pair, where the label identifies the type of content in the value phrase. A reading order of the document can be determined through the use of a binary tree.

Data extraction and ordering based on document layout analysis

The embodiments disclosed herein relate to extracting table data from an electronic document. Tables are detected based on identification of the column headers, of the table, that correspond to known fields. Once a table is detected, values corresponding to the column headers are extracted and stored in association with the known fields.

Extracting data from tables detected in electronic documents

An electrophysiology map, for example a map of arrhythmic substrate, can be generated by acquiring both geometry information and electrophysiology information pertaining to an anatomical region, and associating the acquired geometry and electrophysiology information as a plurality of electrophysiology data points. A user can select two (or more) electrophysiological characteristics for display, and can further elect to apply various filters to the selected electrophysiological characteristics. The user can also define various relationships (e.g., Boolean ANDS, ORs, and the like) between the selected and/or filtered characteristics. The user-selected filtering criteria can be applied to the electrophysiology data points to output various subsets thereof. These subsets can then be graphically rendered using various combinations of colorscale, monochrome scale, and iconography, for example as a three-dimensional cardiac electrophysiology model.

Methods and systems for generating integrated substrate maps for cardiac arrhythmias

The local conduction velocity of a cardiac activation wavefront can be computed by collecting a plurality of electrophysiology ('EP') data points using a multi-electrode catheter, with each EP data point including both position data and local activation time ('LAT') data. For any EP data point, a neighborhood of EP data points, including the selected EP data point and at least two additional EP data points, can be defined. Planes of position and LATs can then be defined using the positions and LATs, respectively, of the EP data points within the neighborhood. A conduction velocity can be computed from an intersection of the planes of positions and LATs. The resultant plurality of conduction velocities can be output as a graphical representation (e.g., an electrophysiology map), for example by displaying vector icons arranged in a uniform grid over a three-dimensional cardiac model.

Methods and systems for mapping local conduction velocity

A method of generating a real-time electrophysiology map, such as a cardiac electrophysiology map, includes displaying a cardiac surface model and receiving a plurality of electrophysiology data points (e.g., using a plurality of intracardiac electrodes). The electrophysiology data from the received electrophysiology data points can be displayed and updated on the cardiac surface model in real-time when it satisfies a preset inclusion criteria, such as a projection distance criterion (e.g., the electrophysiology data point is within a preset distance of the cardiac surface model), a contact force criterion (e.g., the intracardiac catheter is exerting at least a preset contact force on the tissue surface), and/or an electrical coupling criterion (e.g., the electrode-tissue electrical coupling exceeds a preset threshold). New electrophysiology data points can be received when a triggering event, such as a point in the cardiac cycle, occurs, or according to a preset timer interval.

System and method for real-time electrophysiological mapping

Systems for mapping local conduction velocity

A computer-implemented method can include receiving an input image of a physical document, performing down-sampling on the input image, applying median filtering to the input image, applying Canny edge detection to the input image, performing a Hough transform on the input image, computing a quadrilateral having sides that represent borders of the physical document, and providing the computed quadrilateral as an output.

Algorithmic method for detection of documents in images

An electrophysiology map, for example a map of arrhythmic substrate, can be generated by acquiring both geometry information and electrophysiology information pertaining to an anatomical region, and associating the acquired geometry and electrophysiology information as a plurality of electrophysiology data points. A user can select two (or more) electrophysiological characteristics for display, and can further elect to apply various filters to the selected electrophysiological characteristics. The user can also define various relationships (e.g., Boolean ANDs, ORs, and the like) between the selected and/or filtered characteristics. The user-selected filtering criteria can be applied to the electrophysiology data points to output various subsets thereof. These subsets can then be graphically rendered using various combinations of colorscale, monochrome scale, and iconography, for example as a three-dimensional cardiac electrophysiology model.

Growing community of inventors

Maplewood, MN, United States of America

Erhan Erdemir