Intelligent analysis system and method for abdominal plain film of acute abdomen

Abstract

The present invention provides an intelligent analysis system for abdominal plain films of acute abdomen, comprising: when a patient has taken an X-ray standing abdominal plain film examination item, an image recognition module identifies a DICOM image that matches the examination item, an image quality judgment module performs quality analysis on the DICOM image, a gas detection module judges whether there is free gas under the diaphragm in the DICOM image with qualified quality, and a gas-liquid level detection module judges whether there is a gas-liquid level that meets a first preset threshold in the DICOM image with qualified quality, and respectively feeds back the corresponding judgment results to a structured report module, and the structured report module automatically outputs a diagnostic impression for a doctor to view based on the judgment results. The present invention also discloses an intelligent analysis method for abdominal plain films of acute abdomen. The present invention can directly connect the intelligent diagnosis system to a PACS / RIS system, can directly and automatically generate diagnostic prompt information after the filming is completed, and automatically transfer the results to a structured report, thereby improving the diagnostic accuracy and the work efficiency of the doctor.

Description

Technical Field

[0001] The present invention relates to the field of medical information, and more specifically, to an intelligent analysis system and method for acute abdomen plain film. Background Art

[0002] Acute abdomen is characterized by acute abdominal pain, with an acute onset, rapid progression, and often requires surgical treatment as the main means. CT is usually the first choice for the diagnosis of surgical acute abdomen, but due to limited conditions, CT examinations are sometimes not completed in time in primary hospitals and night emergency departments, so it is necessary to rely on medical history, physical examination, laboratory tests and X-ray examinations as the main diagnostic methods. In primary medical institutions where CT is not available or during time periods when CT cannot be used, only plain abdominal X-rays can be used. In the existing technology, doctors are required to make diagnoses based on experience, medical history, laboratory test results, etc., which reduces the doctor's work efficiency and the accuracy of the diagnosis. At the same time, if the examination item is CT, it also increases the patient's medical costs. Summary of the invention

[0003] In view of this, the main purpose of the present invention is to provide an intelligent analysis system and method for acute abdomen abdominal plain film, which can solve the problem in the prior art that doctors need to make diagnoses based on experience, medical history or test results, resulting in low doctor efficiency and inaccurate diagnosis results.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0005] On the one hand, the present invention provides an intelligent analysis system for abdominal plain films of acute abdomen, including an image information management module, an image recognition module, an image quality judgment module, a gas detection module, a gas-liquid level detection module and a structured report module, wherein the image information management module is connected to the image recognition module and is used to transmit the DICOM image of the patient to the image recognition module through the DICOM protocol when the patient has completed the X-ray upright abdominal plain film examination item; the image recognition module is connected to the image information management module, the image quality judgment module and the structured report module and is used to identify the projection range and body position of the DICOM image based on the DICOM image header file information, and to judge whether the DICOM image is consistent with the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray standing abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray standing abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module; the image quality judgment module is respectively connected to the image recognition module, the gas detection module and the structured report module, and is used to analyze the quality of the DICOM image based on preset conditions, send the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and define the DICOM image that meets the preset conditions as the first image; if the quality of the DICOM image does not meet the preset conditions, the diagnosis process is terminated; and The first judgment result and the second prompt information are sent to the structured report module; wherein the first judgment result is that the image quality is unqualified or qualified; the gas detection module is respectively connected to the image quality judgment module, the gas-liquid level detection module and the structured report module, and is used to judge whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured report module respectively. If there is free gas under the diaphragm, the first key image is automatically generated based on the first preset rule, and the second judgment result and the first key image are sent to the structured report module; wherein the second judgment result is that there is free gas under the diaphragm or there is no free gas under the diaphragm; the gas-liquid level detection module is respectively connected to the gas detection module and the structured report The module is connected to the image recognition module, and is used to determine whether there is a gas-liquid surface that meets the first preset threshold in the first image. If there is no gas-liquid surface that meets the first preset threshold, the first image is sent to the structured report module. If there is a gas-liquid surface that meets the first preset threshold, a second key image is automatically generated based on the second preset rule, and the third judgment result and the second key image are sent to the structured report module; wherein the third judgment result is a visible gas-liquid surface or no gas-liquid surface is seen; the structured report module is respectively connected to the image recognition module, the image quality judgment module, the gas detection module and the gas-liquid surface detection module, and is used to automatically generate a diagnostic impression based on the built-in rules, the second judgment result and the third judgment result for the doctor to view; and stores all received data and all images.

[0006] Preferably, the system also includes: a stone segmentation module, which is respectively connected to the air-liquid surface detection module and the structured reporting module, and is used to extract the first image, and determine whether there are stones on the first image based on the second preset rule; if there are stones, stones larger than the second preset threshold are segmented on the first image, anatomical coordinates are set for all stones, diagnostic data are output, anatomical labels are set for each anatomical coordinate, the area of ​​each anatomical label, i.e., the second image, are output, and a fourth judgment result, the diagnostic data, and the second image are sent to the structured reporting module; wherein the fourth judgment result is visible stones or no stones are seen.

[0007] Preferably, the stone segmentation module also includes a calculation unit for automatically calculating the diameter and area of ​​each stone based on the diagnostic data, and automatically generating a third key image according to a third preset rule, and sending the diameter and area of ​​the stone and the third key image to the structured reporting module.

[0008] On the other hand, the present invention also provides an intelligent analysis method for abdominal plain films of acute abdomen, comprising: when the patient has completed the X-ray upright abdominal plain film examination item, the image information management module transmits the patient's DICOM image to the image recognition module through the DICOM protocol; the image recognition module identifies the projection range and body position of the DICOM image based on the DICOM image header file information, and determines whether the DICOM image matches the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray upright abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray upright abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module; the image quality judgment module analyzes the quality of the DICOM image based on preset conditions, sends the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and defines the DICOM image that meets the preset conditions as the first image; if the quality of the DICOM image does not meet the preset conditions, the diagnosis process is terminated; and the first judgment result and the second prompt information are sent to the structured report module. The first judgment result is that the image quality is unqualified or qualified; the gas detection module judges whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured report module respectively. If there is free gas under the diaphragm, based on the first preset rule, the first key image is automatically generated, and the second judgment result and the first key image are sent to the structured report module; wherein the second judgment result is that there is free gas under the diaphragm or there is no free gas under the diaphragm; the gas-liquid level detection module judges whether there is a gas-liquid level that meets the first preset threshold in the first image. If there is no gas-liquid level that meets the first preset threshold, the first image is sent to the structured report module. If there is a gas-liquid level that meets the first preset threshold, based on the second preset rule, the second key image is automatically generated, and the third judgment result and the second key image are sent to the structured report module; wherein the third judgment result is that the gas-liquid level is visible or not; the structured report module automatically generates a diagnostic impression based on the built-in rules, the second judgment result and the third judgment result for the doctor to view; and stores all received data and all images.

[0009] Preferably, the method also includes: the stone segmentation module determines whether there are stones on the first image based on the second preset rule, and if there are stones, segments the stones larger than the second preset threshold on the first image, sets anatomical coordinates for all stones, outputs diagnostic data, sets anatomical labels for each anatomical coordinate, outputs the area of ​​each anatomical label, i.e., the second image, and sends the fourth judgment result, the diagnostic data, and the second image to the structured report module; wherein the fourth judgment result is visible stones or no stones are seen.

[0010] Preferably, the method also includes: the calculation unit in the stone segmentation module automatically calculates the diameter and area of ​​each stone based on the diagnostic data, and automatically generates a third key image according to a third preset rule, and sends the diameter and area of ​​the stone and the third key image to the structured reporting module.

[0011] Technical effects of the present invention:

[0012] 1. Since the present invention is provided with an image recognition module, an image quality judgment module, a gas detection module, a gas-liquid level detection module and a structured report module, when the patient has taken an X-ray standing abdominal plain film examination item, the image recognition module will identify the DIOCOM image that matches the examination item, the image quality judgment module will analyze and judge the quality of the DICOM image, and identify the DICOM image of poor quality caused by artifacts, incomplete projection range, inappropriate projection conditions, etc., to prevent affecting the subsequent diagnosis, the gas detection module and the gas-liquid level detection module will judge whether there is free gas under the diaphragm and whether there is a gas-liquid level for the qualified DICOM image, and feed back the judgment result to the structured report module, and the structured report module will automatically output the diagnosis impression for the doctor to view according to the judgment result. The present invention directly connects the intelligent diagnosis system to the PACS / RIS system, can directly and automatically generate diagnostic prompt information after the filming is completed, automatically transfer the result to the structured report, quickly find patients with clear abnormalities, improve the diagnostic accuracy, and improve the work efficiency of doctors. At the same time, since the examination item used is an X-ray plain film, the cost is lower than that of CT, and the medical cost is reduced, which has positive general significance;

[0013] 2. Since the present invention is provided with a stone segmentation module, high-density gallstones or urinary stones can be detected when there is less interference from intestinal contents, and the stone diagnosis data can be sent to the structured reporting module, making the system more complete and more humane;

[0014] 3. Since the present invention is provided with a calculation unit, the diameter and area of ​​each stone can be automatically calculated based on the diagnostic data, and the third key image can be automatically generated according to the third preset rule. The diameter and area of ​​the stone and the third key image are sent to the structured report module, which is beneficial to the diagnosis and treatment of the stone and provides convenience for the diagnosis of clinicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0016] Figure 1 A schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to Embodiment 1 of the present invention is shown;

[0017] Figure 2 A schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to the second embodiment of the present invention is shown;

[0018] Figure 3 It shows a schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to the third embodiment of the present invention;

[0019] Figure 4 A flowchart of an intelligent analysis method for acute abdomen plain film according to Embodiment 4 of the present invention is shown;

[0020] Figure 5 The specific processing flow chart of the intelligent analysis method of acute abdomen plain film according to the fifth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0021] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0022] Embodiment 1

[0023] Figure 1 FIG. 4 shows a schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to Embodiment 1 of the present invention; Figure 1 As shown, the system includes: an image information management module 10, an image recognition module 20, an image quality judgment module 30, a gas detection module 40, a gas-liquid level detection module 50 and a structured report module 60, wherein:

[0024] The image information management module 10 is connected to the image recognition module 20 and is used to transmit the DICOM image of the patient to the image recognition module through the DICOM protocol when the patient has finished taking the X-ray upright abdominal plain film examination item;

[0025] Among them, the image information management module is the RIS (Radiology Information System) system.

[0026] The image recognition module 20 is connected to the image information management module 10, the image quality judgment module 30 and the structured report module 70, and is used to identify the projection range and body position of the DICOM image based on the DICOM image header information, and to judge whether the DICOM image matches the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray upright abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray upright abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module;

[0027] If the DICOM image does not match the X-ray upright abdominal plain film examination items, a first prompt message is sent to the structured report module, which is processed by relevant personnel and saved in the database of the structured report module for subsequent personnel to call and view.

[0028] The image quality judgment module 30 is connected to the image recognition module 20, the gas detection module 40 and the structured report module 60 respectively, and is used to analyze the quality of the DICOM image based on preset conditions, send the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and define the DICOM image that meets the preset conditions as the first image; if the quality of the DICOM image does not meet the preset conditions, the diagnosis process is terminated; and the first judgment result and the second prompt information are sent to the structured report module; wherein the first judgment result is that the image quality is unqualified or the image quality is qualified;

[0029] The situations that do not meet the preset conditions include incorrect projection position, insufficient projection range, inappropriate projection conditions (too white or too dark), etc.

[0030] The first judgment result is sent to the corresponding control of the technical evaluation (image quality) of the structured report interface. If the image quality is unqualified, the second prompt information is sent to the structured report module, which is handled by relevant personnel and saved in the database of the structured report module for subsequent personnel to call and view.

[0031] The gas detection module 40 is connected to the image quality judgment module 30, the gas-liquid level detection module 50 and the structured reporting module 60 respectively, and is used to judge whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured reporting module respectively. If there is free gas under the diaphragm, a first key image is automatically generated based on a first preset rule, and a second judgment result and the first key image are sent to the structured reporting module; wherein the second judgment result is the presence of free gas under the diaphragm or the absence of free gas under the diaphragm;

[0032] Among them, if the second judgment result is that there is free gas under the diaphragm, the qualitative judgment result "visible perforation" is sent to the corresponding control of "digestive tract perforation" on the structured report interface; if the second judgment result is that there is no free gas under the diaphragm, the qualitative judgment result "no perforation" is sent to the corresponding control of "no perforation in the digestive tract" on the structured report interface.

[0033] The gas-liquid level detection module 50 is connected to the gas detection module 40 and the structured reporting module 60, respectively, and is used to determine whether there is a gas-liquid level that meets the first preset threshold in the first image. If there is no gas-liquid level that meets the first preset threshold, the first image is sent to the structured reporting module. If there is a gas-liquid level that meets the first preset threshold, a second key image is automatically generated based on a second preset rule, and a third judgment result and the second key image are sent to the structured reporting module; wherein the third judgment result is that the gas-liquid level is visible or not.

[0034] Among them, the first preset threshold is a large number of obvious gas-liquid surfaces. If there are a large number of obvious gas-liquid surfaces, they can be detected. The first preset threshold is defined according to medicine and is not limited here.

[0035] Among them, if the third judgment result is a visible gas-liquid surface, the qualitative judgment result "visible gas-liquid surface" is sent to the corresponding control of "digestive tract obstruction" on the structured report interface; if the third judgment result is "no gas-liquid surface", the qualitative judgment result "no gas-liquid surface" is sent to the corresponding control of "no digestive tract obstruction" on the structured report interface.

[0036] The structured report module 60 is respectively connected to the image recognition module 20, the image quality judgment module 30, the gas detection module 40 and the gas-liquid level detection module 50, and is used to automatically generate a diagnostic impression for the doctor to review based on the built-in rules, the second judgment result and the third judgment result; and store all received data and all images.

[0037] X-ray upright abdominal plain film examination relies on the type of gas to assist in diagnosis, that is, by judging the presence of gas in or outside the intestinal cavity and the distribution of gas in dilated and non-dilated intestinal tubes, patients with clear abnormalities are screened out, such as obvious free gas below the diaphragm, indicating digestive tract perforation; large area, clear gas-liquid surface indicates intestinal obstruction; high-density gallstones or urinary stones can also be detected when there is less interference from intestinal contents. Therefore, although CT is the first-line examination method, X-ray upright abdominal plain film still occupies a considerable position in the examination of acute abdomen. Acute abdomen upright abdominal plain film X-ray examination requires rapid and accurate diagnosis. When there are a large number of examinees in the emergency department, patients with clear abnormalities should be screened out for emergency treatment as soon as possible.

[0038] The embodiment of the present invention is provided with an image recognition module, an image quality judgment module, a gas detection module, a gas-liquid level detection module and a structured report module. When the patient has taken an X-ray standing abdominal plain film examination item, the image recognition module will identify the DIOCOM image that matches the examination item. The image quality judgment module analyzes and judges the quality of the DICOM image, and identifies the DICOM image with poor quality caused by artifacts, incomplete projection range, inappropriate projection conditions, etc., to prevent affecting the subsequent diagnosis. The gas detection module and the gas-liquid level detection module judge whether there is free gas under the diaphragm and whether there is a gas-liquid level for the qualified DICOM image, and feed back the judgment result to the structured report module. The structured report module automatically outputs the diagnosis impression for the doctor to view according to the judgment result. The present invention directly connects the intelligent diagnosis system to the PACS / RIS system, and can directly and automatically generate diagnosis prompt information after the filming is completed, and automatically transfer the result to the structured report, so as to quickly find patients with clear abnormalities, improve the diagnostic accuracy, and improve the work efficiency of doctors. At the same time, since the examination item used is an X-ray plain film, the cost is lower than that of CT, and the medical cost is reduced, which has positive general significance.

[0039] Embodiment 2

[0040] Figure 2 FIG. 4 shows a schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to Embodiment 2 of the present invention. Figure 2 As shown, the system also includes: a stone segmentation module 70, which is respectively connected to the gas-liquid surface detection module 50 and the structured report module 60, and is used to extract the first image, and based on the second preset rule, determine whether there are stones on the first image, if there are stones, then segment the stones larger than the second preset threshold on the first image, set anatomical coordinates for all stones, output diagnostic data, set anatomical labels for each anatomical coordinate, output the area of ​​each anatomical label, i.e., the second image, and send a fourth judgment result, the diagnostic data, and the second image to the structured report module 60; wherein the fourth judgment result is visible stones or no stones are seen.

[0041] Among them, if the fourth judgment result is visible stones, the qualitative judgment result "visible stones" will be sent to the corresponding "stones" control of the structured report interface; if the fourth judgment result is no stones, the qualitative judgment result "no stones" will be sent to the corresponding "no stones" control of the structured report interface.

[0042] The embodiment of the present invention is provided with a stone segmentation module, which can detect high-density gallstones or urinary stones when there is less interference from intestinal contents, and send the stone diagnosis data to a structured reporting module, making the system more complete and more user-friendly.

[0043] Embodiment 3

[0044] Figure 3 FIG. 4 shows a schematic diagram of the structure of an intelligent analysis system for acute abdomen plain film according to Embodiment 3 of the present invention. Figure 3 As shown, the stone segmentation module 70 also includes a calculation unit 702, which is used to automatically calculate the diameter and area of ​​each stone based on the diagnostic data, and automatically generate a third key image according to a third preset rule, and send the diameter and area of ​​the stone and the third key image to the structured report module 60 for the doctor to review.

[0045] An embodiment of the present invention is provided with a calculation unit, which can automatically calculate the diameter and area of ​​each stone based on the diagnostic data, and automatically generate a third key image according to a third preset rule, and send the diameter and area of ​​the stone and the third key image to a structured reporting module, which is beneficial to the diagnosis and treatment of the stones and provides convenience for the diagnosis of clinicians.

[0046] Embodiment 4

[0047] Figure 4 FIG. 4 is a flow chart of a method for obtaining patellar anatomical parameters based on patellar axial X-ray images according to Embodiment 4 of the present invention; Figure 4 As shown, the method comprises the following steps:

[0048] Step S401, when the patient has finished taking the X-ray upright abdominal plain film examination, the image information management module transmits the DICOM image of the patient to the image recognition module through the DICOM protocol;

[0049] Among them, the image information management module is the RIS (Radiology Information System) system;

[0050] Step S402, the image recognition module identifies the projection range and body position of the DICOM image based on the DICOM image header information, and determines whether the DICOM image matches the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray upright abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray upright abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module;

[0051] If the DICOM image does not match the X-ray upright abdominal plain film examination items, a first prompt message is sent to the structured report module, which is processed by relevant personnel and saved in the database of the structured report module for subsequent personnel to call and view.

[0052] Step S403, the image quality judgment module analyzes the quality of the DICOM image based on the preset conditions, sends the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and defines the DICOM image that meets the preset conditions as the first image; if the quality of the DICOM image does not meet the preset conditions, the diagnosis process is terminated; and the first judgment result and the second prompt information are sent to the structured report module; wherein the first judgment result is that the image quality is unqualified or the image quality is qualified;

[0053] The situations that do not meet the preset conditions include incorrect projection position, insufficient projection range, inappropriate projection conditions (too white or too dark), etc.

[0054] The first judgment result is sent to the corresponding control of the technical evaluation (image quality) of the structured report interface. If the image quality is unqualified, the second prompt information is sent to the structured report module, which is handled by relevant personnel and saved in the database of the structured report module for subsequent personnel to call and view.

[0055] Step S404, the gas detection module determines whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured reporting module respectively. If there is free gas under the diaphragm, the first key image is automatically generated based on the first preset rule, and the second judgment result and the first key image are sent to the structured reporting module; wherein the second judgment result is that there is free gas under the diaphragm or there is no free gas under the diaphragm;

[0056] Among them, if the second judgment result is that there is free gas under the diaphragm, the qualitative judgment result "visible perforation" is sent to the corresponding control of "digestive tract perforation" on the structured report interface; if the second judgment result is that there is no free gas under the diaphragm, the qualitative judgment result "no perforation" is sent to the corresponding control of "no perforation in the digestive tract" on the structured report interface.

[0057] Step S405, the gas-liquid surface detection module determines whether there is a gas-liquid surface that meets the first preset threshold in the first image. If there is no gas-liquid surface that meets the first preset threshold, the first image is sent to the structured report module. If there is a gas-liquid surface that meets the first preset threshold, based on the second preset rule, a second key image is automatically generated, and a third judgment result and the second key image are sent to the structured report module; wherein the third judgment result is that the gas-liquid surface is visible or not.

[0058] Among them, the first preset threshold is a large number of obvious gas-liquid surfaces. If there are a large number of obvious gas-liquid surfaces, they can be detected. The first preset threshold is defined according to medicine and is not limited here.

[0059] Among them, if the third judgment result is a visible gas-liquid surface, the qualitative judgment result "visible gas-liquid surface" is sent to the corresponding control of "digestive tract obstruction" on the structured report interface; if the third judgment result is "no gas-liquid surface", the qualitative judgment result "no gas-liquid surface" is sent to the corresponding control of "no digestive tract obstruction" on the structured report interface.

[0060] Step S406, the structured report module automatically generates a diagnostic impression for the doctor to review based on the built-in rules, the second judgment result and the third judgment result; and stores all received data and all images.

[0061] X-ray upright abdominal plain film examination relies on the type of gas to assist in diagnosis, that is, by judging the presence of gas in or outside the intestinal cavity and the distribution of gas in dilated and non-dilated intestinal tubes, patients with clear abnormalities are screened out, such as obvious free gas below the diaphragm, indicating digestive tract perforation; large area, clear gas-liquid surface indicates intestinal obstruction; high-density gallstones or urinary stones can also be detected when there is less interference from intestinal contents. Therefore, although CT is the first-line examination method, X-ray upright abdominal plain film still occupies a considerable position in the examination of acute abdomen. Acute abdomen upright abdominal plain film X-ray examination requires rapid and accurate diagnosis. When there are a large number of examinees in the emergency department, patients with clear abnormalities should be screened out for emergency treatment as soon as possible.

[0062] The method further includes: the stone segmentation module determines whether there are stones on the first image based on the second preset rule; if there are stones, the stones larger than the second preset threshold are segmented on the first image; anatomical coordinates are set for all stones; diagnostic data are output; anatomical labels are set for each anatomical coordinate; the area of ​​each anatomical label, i.e., the second image, is output; and a fourth judgment result, the diagnostic data, and the second image are sent to the structured report module; wherein the fourth judgment result is visible stones or no stones are seen.

[0063] Among them, if the fourth judgment result is visible stones, the qualitative judgment result "visible stones" will be sent to the corresponding "stones" control of the structured report interface; if the fourth judgment result is no stones, the qualitative judgment result "no stones" will be sent to the corresponding "no stones" control of the structured report interface.

[0064] The method also includes: the calculation unit in the stone segmentation module automatically calculates the diameter and area of ​​each stone based on the diagnostic data, and automatically generates a third key image according to a third preset rule, and sends the diameter and area of ​​the stone and the third key image to the structured report module for the doctor to review.

[0065] In the embodiment of the present invention, the image recognition module, image quality judgment module, gas detection module, gas-liquid level detection module and structured report module, when the patient has taken an X-ray upright abdominal plain film examination item, the image recognition module will identify the DICOM image that matches the examination item, the image quality judgment module will analyze and judge the quality of the DICOM image, and identify the DICOM images of poor quality caused by artifacts, incomplete projection range, inappropriate projection conditions, etc., to prevent affecting subsequent diagnosis, the gas detection module and the gas-liquid level detection module will judge whether there is free gas under the diaphragm and whether there is a gas-liquid level in the qualified DICOM image, and feed back the judgment result to the structured report module, and the structured report module automatically outputs the diagnosis impression for the doctor to review based on the judgment result. The present invention directly connects the intelligent diagnosis system to the PACS / RIS system, and can automatically generate diagnostic prompt information directly after the filming is completed, and automatically transfer the results to the structured report, so as to quickly find patients with clear abnormalities, improve the diagnostic accuracy, and improve the work efficiency of doctors. At the same time, since the examination items used are X-ray plain films, the cost is lower than that of CT, which reduces the medical cost and has positive general significance; the stone segmentation module in the embodiment of the present invention can detect high-density gallstones or urinary stones when the intestinal contents have less interference, and send the stone diagnosis data to the structured report module, making the system more complete and more humane; the calculation unit in the embodiment of the present invention can automatically calculate the diameter and area of ​​each stone based on the diagnostic data, and automatically generate the third key image according to the third preset rule, and send the diameter and area of ​​the stone and the third key image to the structured report module, which is conducive to the diagnosis and treatment of stones and provides convenience for the diagnosis of clinicians.

[0066] Embodiment 5

[0067] Figure 5 FIG. 4 shows a specific processing flow chart of the intelligent analysis method for acute abdomen plain film according to Embodiment 5 of the present invention, as shown in FIG. Figure 5 As shown, the method comprises the following steps:

[0068] Step S501, the image recognition module identifies whether the DICOM image matches the X-ray upright abdominal plain film examination item? If not, the first prompt information is sent to the structured report module. If so, step S502 is executed;

[0069] Step S502: Does the image quality meet the preset conditions? If not, send the first judgment result, the first image, and the second prompt information to the structured report module; if so, execute step S503;

[0070] Step S503, the gas detection module determines whether there is free gas under the diaphragm in the first image? If yes, the second determination result and the first key image are sent to the structured reporting module; if no, the first image is sent to the gas-liquid level detection module and step S504 is executed;

[0071] Step S504, the gas-liquid surface detection module determines whether there is a gas-liquid surface that meets the first preset threshold in the first image. If yes, the third determination result and the second key image are sent to the structured reporting module. If no, the first image is sent to the stone segmentation module and step S505 is executed.

[0072] Step S505, the stone segmentation module determines whether there is a stone that meets the second preset threshold. If not, the fourth determination result (no stone found) is sent to the structured reporting module. If yes, step S506 is executed;

[0073] Step S506, the calculation unit calculates the diameter and area of ​​each stone and generates a third key image, and sends the fourth judgment result (visible stone), the diameter and area of ​​the stone, the third key image, and the second image to the structured report module;

[0074] Step S507, the structured report module automatically generates a diagnostic impression based on built-in rules and measurements for the doctor to review; and stores all received data and all images.

[0075] From the above description, it can be seen that the above-mentioned embodiments of the present invention achieve the following technical effects: since the embodiments of the present invention are provided with an image recognition module, an image quality judgment module, a gas detection module, a gas-liquid level detection module and a structured report module, when the patient completes the X-ray upright abdominal plain film examination item, the image recognition module will identify the DICOM image that matches the examination item, the image quality judgment module will analyze and judge the quality of the DICOM image, and identify the DICOM images of poor quality caused by artifacts, incomplete projection range, inappropriate projection conditions, etc., to prevent affecting subsequent diagnosis, the gas detection module and the gas-liquid level detection module will judge whether there is free gas under the diaphragm and whether there is a gas-liquid level in the qualified DICOM image, and feed back the judgment result to the structured report module, and the structured report module will automatically output the diagnostic impression for the doctor to review based on the judgment result. The present invention directly connects the intelligent diagnosis system to the PACS / RIS system, and can automatically generate diagnostic prompt information directly after the filming is completed, and automatically transfer the results to the structured report, so as to quickly find patients with clear abnormalities, improve the diagnostic accuracy, and improve the work efficiency of doctors. At the same time, since the examination items used are X-ray films, the cost is lower than that of CT, which reduces the medical cost and has positive general significance; since the embodiment of the present invention is provided with a stone segmentation module, high-density gallstones or urinary stones can be detected when the intestinal contents have less interference, and the stone diagnosis data can be sent to the structured report module, making the system more complete and more humane; since the embodiment of the present invention is provided with a calculation unit, the diameter and area of ​​each stone can be automatically calculated based on the diagnostic data, and the third key image can be automatically generated according to the third preset rule, and the diameter and area of ​​the stone and the third key image can be sent to the structured report module, which is conducive to the diagnosis and treatment of stones and provides convenience for the diagnosis of clinicians.

[0076] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0077] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent analysis system for acute abdomen plain film, characterized in that: It includes image information management module, image recognition module, image quality judgment module, gas detection module, gas-liquid level detection module and structured report module, among which: The image information management module is connected to the image recognition module and is used to transmit the DICOM image of the patient to the image recognition module through the DICOM protocol when the patient has completed the X-ray upright abdominal plain film examination; The image recognition module is connected to the image information management module, the image quality judgment module and the structured report module, and is used to identify the projection range and body position of the DICOM image based on the DICOM image header file information, and to judge whether the DICOM image matches the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray upright abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray upright abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module; The image quality judgment module is connected to the image recognition module, the gas detection module and the structured report module respectively, and is used to analyze the quality of the DICOM image based on preset conditions, send the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and define the DICOM image that meets the preset conditions as the first image; if the quality of the DICOM image does not meet the preset conditions, the diagnosis process is terminated; and the first judgment result and the second prompt information are sent to the structured report module; wherein the first judgment result is that the image quality is unqualified or the image quality is qualified; The gas detection module is connected to the image quality judgment module, the gas-liquid level detection module and the structured reporting module, respectively, and is used to judge whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured reporting module respectively. If there is free gas under the diaphragm, a first key image is automatically generated based on a first preset rule, and a second judgment result and the first key image are sent to the structured reporting module; wherein the second judgment result is the presence or absence of free gas under the diaphragm; The gas-liquid level detection module is connected to the gas detection module and the structured reporting module respectively, and is used to determine whether there is a gas-liquid level that meets a first preset threshold in the first image. If there is no gas-liquid level that meets the first preset threshold, the first image is sent to the structured reporting module. If there is a gas-liquid level that meets the first preset threshold, a second key image is automatically generated based on a second preset rule, and a third judgment result and the second key image are sent to the structured reporting module; wherein the third judgment result is that the gas-liquid level is visible or not. The structured report module is respectively connected to the image recognition module, the image quality judgment module, the gas detection module and the gas-liquid level detection module, and is used to automatically generate a diagnostic impression for the doctor to review based on the built-in rules, the second judgment result and the third judgment result; and store all received data and all images.

2. The intelligent analysis system for acute abdomen plain film according to claim 1, characterized in that: The system also includes: a stone segmentation module, which is respectively connected to the gas-liquid surface detection module and the structured reporting module, and is used to extract the first image, and determine whether there are stones on the first image based on a second preset rule. If the stones exist, stones larger than a second preset threshold are segmented on the first image, anatomical coordinates are set for all the stones, diagnostic data are output, anatomical labels are set for each of the anatomical coordinates, the area of ​​each anatomical label, i.e., the second image, and a fourth judgment result, the diagnostic data, and the second image are sent to the structured reporting module; wherein the fourth judgment result is visible stones or no stones are seen.

3. The intelligent analysis system for acute abdomen plain film according to claim 2, characterized in that: The stone segmentation module also includes a calculation unit for automatically calculating the diameter and area of ​​each stone based on the diagnostic data, and automatically generating a third key image according to a third preset rule, and sending the diameter and area of ​​the stone and the third key image to the structured reporting module.

4. An intelligent analysis method for acute abdomen plain film, characterized in that: include: When the patient has finished taking X-ray upright abdominal plain film examination items, the image information management module transmits the patient's DICOM image to the image recognition module through the DICOM protocol; The image recognition module identifies the projection range and body position of the DICOM image based on the DICOM image header information, and determines whether the DICOM image matches the X-ray upright abdominal plain film examination item. If the DICOM image matches the X-ray upright abdominal plain film examination item, the DICOM image is sent to the image quality judgment module; if the DICOM image does not match the X-ray upright abdominal plain film examination item, the diagnosis process is terminated and the first prompt information is sent to the structured report module; The image quality judgment module analyzes the quality of the DICOM image based on preset conditions, sends the DICOM image that meets the preset conditions to the gas detection module and the structured report module respectively, and defines the DICOM image that meets the preset conditions as the first image; If the quality of the DICOM image does not meet the preset condition, the diagnostic process is terminated; and the first judgment result and the second prompt information are sent to the structured report module; wherein the first judgment result is that the image quality is unqualified or the image quality is qualified; The gas detection module determines whether there is free gas under the diaphragm in the first image. If there is no free gas under the diaphragm, the first image is sent to the gas-liquid level detection module and the structured reporting module respectively. If there is free gas under the diaphragm, a first key image is automatically generated based on a first preset rule, and a second judgment result and the first key image are sent to the structured reporting module; wherein the second judgment result is the presence or absence of free gas under the diaphragm; The gas-liquid surface detection module determines whether there is a gas-liquid surface that meets a first preset threshold in the first image. If there is no gas-liquid surface that meets the first preset threshold, the first image is sent to the structured report module. If there is a gas-liquid surface that meets the first preset threshold, a second key image is automatically generated based on a second preset rule, and a third judgment result and the second key image are sent to the structured report module; wherein the third judgment result is that the gas-liquid surface is visible or not. The structured report module automatically generates a diagnostic impression based on built-in rules, the second judgment result and the third judgment result for the doctor to review; and stores all received data and all images.

5. The intelligent analysis method for acute abdomen plain film according to claim 4, characterized in that: The method also includes: a stone segmentation module extracts the first image, and based on a second preset rule, determines whether there are stones on the first image; if the stones exist, segments stones larger than a second preset threshold on the first image, sets anatomical coordinates for all the stones, outputs diagnostic data, sets an anatomical label for each of the anatomical coordinates, outputs the area of ​​each anatomical label, i.e., the second image, and sends a fourth judgment result, the diagnostic data, and the second image to the structured report module; wherein the fourth judgment result is visible stones or no stones are seen.

6. The intelligent analysis method for acute abdomen plain film according to claim 5, characterized in that: The calculation unit in the stone segmentation module automatically calculates the diameter and area of ​​each stone based on the diagnostic data, and automatically generates a third key image according to a third preset rule, and sends the diameter and area of ​​the stone and the third key image to the structured reporting module.

Images