Image processing apparatus, image processing method, image processing system, and program
US-2019035094-A1 · Jan 31, 2019 · US
US12016722B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12016722-B2 |
| Application number | US-202017078301-A |
| Country | US |
| Kind code | B2 |
| Filing date | Oct 23, 2020 |
| Priority date | Apr 27, 2018 |
| Publication date | Jun 25, 2024 |
| Grant date | Jun 25, 2024 |
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.
According to one embodiment, a medical information processing system includes processing circuitry. The processing circuitry acquires an ultrasound image of a subject. The processing circuitry acquires a first modality image of the subject, the first modality image differing from the ultrasound image. The processing circuitry acquires an imaging position for the ultrasound image. The processing circuitry generates diagnosis support information for the subject based on the ultrasound image, the imaging position for the ultrasound image, and the first modality image.
Opening claim text (preview).
The invention claimed is: 1. A medical information processing system, comprising: processing circuitry configured to acquire an ultrasound image of a subject, acquire a first modality image of the subject, the first modality image differing from the ultrasound image, and acquire an imaging position for the ultrasound image; and a memory storing a trained model, wherein the processing circuitry is further configured to perform computer-aided detection with the ultrasound image, perform computer-aided detection with the first modality image, generate diagnosis support information for the subject by inputting, in an inference stage, inference inputs including a result of the computer-aided detection with the ultrasound image, a result of the computer-aided detection with the first modality image, and the imaging position for the ultrasound image to the trained model, and when determining that the result of the computer-aided detection with the ultrasound image indicates a diseased state, plot a mark indicative of the imaging position for the ultrasound image on a schematic diagram of a breast of the subject, and specify, on the first modality image, a band-shaped region of interest having a center coincide with a straight line corresponding to a position of the plotted mark and corresponding to an imaging angle of the first modality image, the first modality image being a mammogram, and wherein the trained model was previously trained, in a training stage, based on training inputs, different from the inference inputs, including a result of a computer-aided detection with a training ultrasound image, a result of a computer-aided detection with a first training modality image, and a training imaging position for the training ultrasound image, the training ultrasound image, the first training modality image, and the training imaging position being acquired before the training stage. 2. The medical information processing system according to claim 1 , wherein the processing circuitry is further configured to generate the diagnosis support information for the subject by inputting the inference inputs to the trained model, the inference inputs further including the ultrasound image and the first modality image, and wherein the trained model was previously trained, in the training stage, based on the training inputs, which further include the training ultrasound image and the first training modality image. 3. A medical information processing system, comprising: processing circuitry configured to acquire an ultrasound image of a subject, acquire a first modality image of the subject, the first modality image differing from the ultrasound image, and acquire an imaging position for the ultrasound image; and a memory storing a trained model, wherein the processing circuitry is further configured to generate a second modality image by processing the first modality image based on the imaging position for the ultrasound image, perform computer-aided detection with the ultrasound image, perform computer-aided detection with the second modality image, generate diagnosis support information for the subject by inputting, in an inference stage, inference inputs including a result of the computer-aided detection with the ultrasound image and a result of the computer-aided detection with the second modality image to the trained model, and when determining that the result of the computer-aided detection with the ultrasound image indicates a diseased state, plot a mark indicative of the imaging position for the ultrasound image on a schematic diagram of a breast of the subject, and specify, on the first modality image, a band-shaped region of interest having a center coincide with a straight line corresponding to a position of the plotted mark and corresponding to an imaging angle of the first modality image, the first modality image being a mammogram, and wherein the trained model was previously trained, in a training stage, based on training inputs, different from the inference inputs, including a result of a computer-aided detection with a training ultrasound image and a result of a computer-aided detection with a second training modality image, the training ultrasound image and the second training modality image being acquired before the training stage. 4. The medical information processing system according to claim 3 , wherein the processing circuitry is further configured to generate the diagnosis support information for the subject by inputting the inference inputs to the trained model, the inference inputs further including the ultrasound image and the second modality image, and wherein the trained model was previously trained, in the training stage, based on the training inputs, which further include the training ultrasound image and the second training modality image.
for diagnosis of breast, i.e. mammography · CPC title
Emission tomography · CPC title
Transmission computed tomography [CT] · CPC title
adapted for image acquisition of a particular organ or body part (A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062) · CPC title
combining images from different diagnostic modalities, e.g. ultrasound and X-ray · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.