Medical diagnosis support apparatus and method of controlling the same

• US 10,282,671 B2
• Filed: 05/04/2016
• Issued: 05/07/2019
• Est. Priority Date: 02/14/2012
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kawagishi, Masami
• Primary Examiner(s): Misir, Dave
• Application Number:
  US15/146,473
• Publication Number:
  US 20160246933A1
• Time in Patent Office: 1,098 Days
• Field of Search: 705 2, 706 46, 706 52
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A medical diagnosis support apparatus is provided. In the medical diagnosis support apparatus, an acquisition unit acquires medical information associated with a diagnosis target as input information. An inference unit infers a diagnosis name of the diagnosis target based on the acquired input information. A calculation unit calculates the influence rate of each input information with respect to each inference. A creation unit creates a report sentence based on the calculated influence rate.

Claims

1. A medical diagnosis support apparatus which provides information for supporting medical diagnosis, the apparatus comprising:

at least one processor and a memory operatively coupled to function as;

an acquisition unit configured to acquire medical information associated with a diagnosis target as input information, wherein the input information is input by a user;

an inference unit configured to infer a diagnosis name of the diagnosis target as an inference result based on the acquired input information, wherein the diagnosis name exhibits a highest inference probability;

a calculation unit configured to calculate an influence rate of the acquired input information with respect to each inference;

a creation unit configured to select terms from the input information and create a report sentence based on the calculated influence rate; and

a display control unit configured to cause a monitor to display the created report sentence, wherein

the creation unit is configured to

select a first set of terms from the input information, each of the first set of terms having an influence rate equal to or more than a first threshold concerning positive influences,

determine an order of writing of the selected first set of terms based on a descending or ascending order of a positive influence rate on the inference result, and

create the report sentence based on the selected first set of terms and the determined order, the report sentence including the inferred diagnosis name.

2. The apparatus according to claim 1, wherein the creation unit selects a second set of terms from the input information according to a different threshold, and

creates the report sentence using the selected first set of terms without using the second set of terms from the input information, each of the second set of terms having an influence rate equal to or less than a second threshold concerning negative influences.

3. The apparatus according to claim 1, wherein the creation unit creates the report sentence by arranging terms in descending order of the influence rate.

4. A medical diagnosis support method which provides information for supporting medical diagnosis, the method comprising:

acquiring medical information associated with a diagnosis target as input information, wherein the input information is input by a user;

inferring a diagnosis name of the diagnosis target as an inference result based on the acquired input information, wherein the diagnosis name exhibits a highest inference probability;

calculating an influence rate of the acquired input information with respect to each inference; and

creating a report sentence based on the calculated influence rate and display the created report sentence on a monitor, wherein the creating includes selecting terms from the input information, and includes

selecting a first set of terms from the input information, each of the first set of terms having an influence rate equal to or more than a first threshold concerning positive influences,

determining an order of writing of the selected first set of terms based on a descending or ascending order of a positive influence rate on the inference result, and

creating the report sentence based on the selected first set of terms and the determined order, the report sentence including the inferred diagnosis name.

5. The method according to claim 4, wherein the creating of the report sentence includes selecting a second set of terms from the input information according to a different threshold, and

using the selected first set of terms without using the second set of terms from the input information, each of the second set of terms having an influence rate equal to or less than a second threshold concerning negative influences.

6. The method according to claim 4, wherein the creating of the report sentence includes arranging terms in descending order of the influence rate.

7. A non-transitory computer-readable storage medium storing, in executable form, instructions for causing a computer to perform a medical diagnosis support method which provides information for supporting medical diagnosis, the method comprising:

acquiring medical information associated with a diagnosis target as input information, wherein the input information is input by a user;

inferring a diagnosis name of the diagnosis target as an inference result based on the acquired input information, wherein the diagnosis name exhibits a highest inference probability;

calculating an influence rate of the acquired input information with respect to each inference; and

creating a report sentence based on the calculated influence rate and display the created report sentence on a monitor, wherein the creating includes selecting terms from the input information, and includes

selecting a first set of terms from the input information, each of the first set of terms having an influence rate equal to or more than a first threshold concerning positive influences,

determining an order of writing of the selected first set of terms based on a descending or ascending order of a positive influence rate on the inference result, and

creating the report sentence based on the selected first set of terms and the determined order, the report sentence including the inferred diagnosis name.

8. The non-transitory computer-readable storage medium according to claim 7, wherein the creating of the report sentence includes selecting a second set of terms from the input information according to a different threshold, and

using the selected first set of terms without using the second set of terms from the input information, each of the second set of terms having an influence rate equal to or less than a second threshold concerning negative influences.

9. The non-transitory computer-readable storage medium according to claim 7, wherein the creating of the report sentence includes arranging terms in descending order of the influence rate.