Artificial Intelligence System for Determining Drug Use through Medical Imaging
US-2024197287-A1 · Jun 20, 2024 · US
US10376236B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10376236-B2 |
| Application number | US-201514717646-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 20, 2015 |
| Priority date | Nov 21, 2012 |
| Publication date | Aug 13, 2019 |
| Grant date | Aug 13, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An ultrasound diagnostic apparatus according to an embodiment includes processing circuitry. The processing circuitry sets a ROI in ultrasound image data that corresponds to at least one temporal phase and is among moving image data of two-/three-dimensional ultrasound image data acquired while using a region containing a tissue in motion as an image taking target. The processing circuitry obtains first position information of an estimated ROI based on movement information and second position information of an estimated ROI based on information other than the movement information, in ultrasound image data corresponding to the other remaining temporal phases within an acquisition period of the moving image data. The processing circuitry tracks the ROI, by obtaining position information combining the first and second position information based on an index related to reliability of the movement information, as position information of the ROI.
Opening claim text (preview).
What is claimed is: 1. An ultrasound diagnostic apparatus comprising: an ultrasound probe configured to emit ultrasound waves and detect reflected waves that are used to generate ultrasound image data, the ultrasound image data representing two- or three-dimensional ultrasound images of a target-including region containing a tissue in motion, the ultrasound images corresponding to a plurality of temporal phases; and processing circuitry configured to set, for at least one temporal phase of the plurality of temporal phases, a two- or three-dimensional region of interest in the ultrasound image data, the region of interest representing a portion of the tissue, obtain movement information by a tracking process using the ultrasound images, wherein the movement information represents motion vectors of first points in the region of interest, and corresponds to a likelihood that when a first point is translated according to the motion vectors relative to positions within the respective ultrasound images, the positions within the respective ultrasound images refer to a same location on the target, obtain a reliability index based on indicia of reliability of the movement information including at least one variable obtained from the tracking process, determine, using the movement information, movement-based positions, which are first estimates of positions of the region of interest in ultrasound images corresponding to remaining temporal phases, which are temporal phases of the plurality of temporal phases other than the at least one temporal phase, determine, using shape information of a shape of the tissue, shape-based positions, which are second estimates of the positions of the region of interest in the ultrasound images corresponding to the remaining temporal phases, the shape-based positions being determined by estimating the shape of the tissue in the remaining temporal phases and then determining the second estimates of the positions of the region of interest from the estimated shape of the tissue in the remaining temporal phases, combine the movement-based positions with the shape-based positions by weighting the movement-based positions relative to the shape-based positions based on the reliability index, to generate position information of the region of interest, the weighting being performed such that, for a value of the reliability index indicating a greater reliability of the movement information, a contribution to the generated position information by the movement-based positions is increased relative to a contribution by the shape-based positions, and track the region of interest using the position information of the region of interest by updating the region of interest with respect to time in accordance with changes of the region of interest represented by the position information. 2. The ultrasound diagnostic apparatus according to claim 1 , wherein the plurality of temporal phases correspond to a time period of at least one cyclic period and the ultrasound images were acquired when the tissue was in periodic motion. 3. The ultrasound diagnostic apparatus according to claim 1 , wherein the processing circuitry is configured to estimate the movement information between a first image of the ultrasound image data corresponding to a first temporal phase of the plurality of temporal phases and a second image of the ultrasound image data corresponding to a second temporal phase of the plurality of temporal phases, which is temporally adjacent to the first temporal phase, estimate the movement-based positions in the second image by moving the region of interest in the first image based on the estimated movement information, and estimate the shape-based positions in the second image. 4. The ultrasound diagnostic apparatus according to claim 3 , wherein the processing circuitry is configured to estimate the movement-based positions by calculating motion vectors at second points in a region that contains the region of interest, selecting the first points to be tracking points structuring the region of interest, eliminating statistically-abnormal motion vectors from the calculated motion vectors to generate remaining motion vectors, and estimating the motion vectors at the first points using the group of remaining motion vectors, and define the reliability index based on said at least one variable, wherein said at least one variable is one or more of a density of the remaining motion vectors in vicinal regions of the first points and a variance of motion vectors at the first points in vicinal regions of the first points. 5. The ultrasound diagnostic apparatus according to claim 3 , wherein the processing circuitry is configured to estimate, for each of the first points, which are tracking points structuring the region of interest, and for a time interval between the first image and the second image, forward-direction motion vectors representing motions forward in time from the first temporal phase to the second temporal phase, as well as backward-direction motion vectors representing motions backward in time from the second temporal phase to the first temporal phase, and define the reliability index based on said at least one variable, wherein said at least one variable includes a degree of matching between the forward-direction motion vector and the backward-direction motion vector at respective first points. 6. The ultrasound diagnostic apparatus according to claim 3 , wherein the processing circuitry is configured to calculate motion vectors at second points in a region that contains the region of interest by performing a template matching process, and define the reliability index based on said at least one variable, wherein said at least one variable includes one or more of a level of similarity between templates used in the template matching process, a signal variance value of a standard template used in the template matching process, and an average signal value of the standard template. 7. The ultrasound diagnostic apparatus according to claim 3 , wherein the processing circuitry is configured to estimate the shape-based positions by using one or more of comparing a shape of the shape-based positions of the second image with shape dictionary information corresponding to a same temporal phase as the second image; minimizing a shape energy of the shape of the shape-based positions of the second image; and fitting the shape of the shape-based positions of the second image using a least square method. 8. The ultrasound diagnostic apparatus according to claim 3 , wherein the processing circuitry is configured to perform the combining of the movement-based positions with the shape-based positions using a weighted addition of the movement-based positions and the shape-based positions in such a manner that a larger weight is applied to estimates of the positions of the region of interest of the movement-based positions corresponding to first points for which the reliability index indicates greater reliability. 9. The ultrasound diagnostic apparatus according to claim 1 , further comprising: controlling circuitry configured to, for a temporal phase of the plurality of temporal phases, cause the processing circuitry to output the movement-based positions as the position information of the region of interest when an average of values of the reliability index corresponding to the region of interest and the temporal phase is equal to or larger than a predetermined threshold value, and cause the processing circuitry to output the position information resulting from combining the movement-based positions with the shape-based positions as the position information of the region of interest when the average is smaller than the predetermin
for diagnosis of the heart · CPC title
involving processing of raw data to produce diagnostic data, e.g. for generating an image · CPC title
using feature-based methods, e.g. the tracking of corners or segments · CPC title
Heart; Cardiac · CPC title
Ultrasound image · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.