Character information identification method for medical image and device thereof

A technology of medical imaging and text information, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as errors, increased workload of medical staff, and delay of time for patients to take films, so as to improve recognition efficiency and improve The effect of accuracy

Active Publication Date: 2015-09-16
上海新红医医疗科技有限公司
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current practice is to manually check and match the films and reports to assign the corres

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Character information identification method for medical image and device thereof
  • Character information identification method for medical image and device thereof
  • Character information identification method for medical image and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0021] Example one

[0022] Such as figure 1 As shown, this embodiment is a schematic flow chart of the method for recognizing text information in medical images. The method includes the following steps 110 to 140.

[0023] Positioning step 110: receiving an input of an operator selecting a text area on a medical image, and determining a text area to be recognized for text information according to the input.

[0024] In step 110, it is possible to detect the area selected by the operator on the medical image, and then use the detected area as the text area to be recognized for text information. For example, provide the operator with a frame selection tool such as a mouse or touch Carry out the frame selection of the area. Or, by providing example input text for the operator to input the information of the medical image that he observes, combining the information to determine the text area to be recognized by the text information, for example, the information corresponding to the upp...

Example Embodiment

[0032] Example two

[0033] This embodiment is an improvement made on the basis of the first embodiment, such as figure 2 As shown, in addition to the same steps 110 to 150 as in the first embodiment, it also includes a learning step 170 and / or a receiving step 160.

[0034] As described in the first embodiment, in addition to the recognized text that has passed the verification, the verification result can also be an output that prompts the operator that the recognition is wrong. Regarding the former (that is, the recognized text that has passed the verification), this embodiment receives the operator’s feedback on the output. The feedback includes the operator’s positive feedback and representation recognition based on the recognized text and the actual text on the image. Wrong negative feedback, according to the positive feedback and negative feedback, determine the positive sample and negative sample of the recognized text that passed the verification, and then use the known c...

Example Embodiment

[0036] Example three

[0037] This embodiment is an improvement made on the basis of the first embodiment or the second embodiment. Here, the improvement on the first embodiment is taken as an example for description, and the improvement can also be implemented in a similar position of the second embodiment. Such as image 3 As shown, in addition to the same steps 110 to 150 as in the first embodiment, this embodiment also includes a re-identification step 180 (this re-identification step 180 can also be placed between the identification step 130 and the correction step 140 in the second embodiment) . In the re-recognition step, the operator’s feedback on the recognition of the initially recognized characters output from the recognition step is received. If the feedback is lower than the preset minimum recognition threshold condition, the operator is prompted to re-execute the positioning step. The actual text on the image gives feedback that characterizes the recognition accur...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a character information identification method for a medical image and a device thereof. The method comprises the steps that input of selecting a character area of an operator on the medical image is received, and the character area under character information identification is confirmed according to the input; image preprocessing operation is performed on the character area so that non-character information is removed and a clean character image is obtained; the character image is cut so that characters are split out and single character images are obtained, and the obtained single character images are identified so that preliminarily identified characters are obtained; the preliminarily identified characters are corrected; and the corrected identified characters are verified according to the preset verification conditions so that unreasonable and illegal identified characters are removed, a verification result is outputted, and the verification result includes the verified identified characters. The identification range is reduced according to the received input of the operator, identification efficiency is enhanced, and the preprocessed and preliminarily identified characters are corrected and verified so that identification accuracy is further enhanced.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a text information recognition method and device in medical images. Background technique [0002] At present, hospitals generally use the Picture Archiving and Communication System (PACS) to store and manage the medical image data obtained by medical staff after performing imaging examinations on patients. Doctors need to review images of patients, write imaging inspection reports, etc. Since the images and reports are distributed independently, the digital film corresponding to the medical image does not store relevant information of the patient in text format, but the information is embedded in the digital film corresponding to the medical image in the form of an image. Therefore, before the film and the report are handed over to the patient, it is necessary to associate the patient information obtained in the film with the report. The current practice is to ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/34G06K9/72
CPCG06V10/267G06V10/768G06V30/287
Inventor 宗旭东
Owner 上海新红医医疗科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap