Lung pathological information processing method and device, electronic equipment and computer medium
Through the lung pathological information processing method, the lung images are automatically analyzed using image acquisition, feature extraction and intelligent voice robot Q&A, which solves the problem of low diagnosis efficiency, and achieves rapid and accurate pathological information transmission to assist doctors in diagnosis.
Patent Information
- Application Number
- CN202411006999.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-25
AI Technical Summary
The diagnosis of pulmonary complications is inefficient, and professionals require operation of CT imaging machines and no pathological analysis is performed, resulting in delays in diagnosis.
The lung pathological information processing method is adopted to automatically collect and analyze lung images through lung image collection, feature extraction, pre-training model recognition and intelligent voice robot Q&A, and generate pathological information and send it to the doctor.
It improves the efficiency of lung imaging detection, assists doctors in diagnosis, speeds up the patient diagnosis process, and saves doctors’ consultation time.
Smart Images

Figure CN119028566A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of lung pathology information processing, and in particular to a lung pathology information processing method, device, electronic device, and computer medium. Background Art
[0002] At present, the number of patients with pulmonary complications is gradually increasing, and the diagnosis of pulmonary complications usually requires taking CT images first, and then the doctor determines the patient's condition based on the images. However, the above-mentioned diagnosis methods for pulmonary complications usually have the following technical problems: professional managers are required to operate the CT imaging machine, which affects the efficiency of patient diagnosis when there are many patients; in addition, the CT images are not pathologically analyzed, resulting in low doctor diagnostic efficiency and easy delays in patient treatment.
[0003] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention
[0004] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0005] Some embodiments of the present disclosure propose a lung pathology information processing method, device, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.
[0006] In a first aspect, some embodiments of the present disclosure provide a lung pathology information processing method, which is applied to a lung nodule all-in-one machine, wherein the lung nodule all-in-one machine includes: a lung image acquisition terminal, an intelligent voice robot and a doctor terminal, and the method includes: in response to a lung image acquisition instruction detected, controlling the associated lung image acquisition terminal to acquire lung image information of a user at a target position, wherein the lung image information includes: lung images; extracting features of the lung images included in the lung image information to obtain lung image features; inputting the lung image features into a pre-trained lung image pathology recognition model to obtain lung image pathology. recognition result; in response to determining that the above-mentioned lung image pathology recognition result meets the abnormality detection condition, controlling the associated intelligent voice robot to conduct intelligent question and answer with the above-mentioned user according to the above-mentioned lung image pathology recognition result, and collecting the above-mentioned user's voice in real time; performing voice recognition on the above-mentioned user's voice to obtain a voice recognition result, and filling the above-mentioned voice recognition result into a pre-set pathology question and answer information filling template to obtain pathology question and answer information; combining the user number of the above-mentioned user, the above-mentioned lung image pathology recognition result and the above-mentioned pathology question and answer information into lung pathology information, and sending the above-mentioned lung pathology information to the associated doctor end.
[0007] In a second aspect, some embodiments of the present disclosure provide a lung pathology information processing device, which is applied to a lung nodule all-in-one machine. The lung nodule all-in-one machine includes: a lung image acquisition terminal, an intelligent voice robot and a doctor terminal. The device includes: a first control unit, which is configured to control the associated lung image acquisition terminal to acquire lung image information of a user at a target position in response to a lung image acquisition instruction detected, wherein the lung image information includes: lung images; an extraction unit, which is configured to perform feature extraction on the lung images included in the lung image information to obtain lung image features; an input unit, which is configured to input the lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition model. The second control unit is configured to, in response to determining that the above-mentioned lung image pathology recognition result meets the abnormality detection condition, control the associated intelligent voice robot to conduct intelligent question and answer with the above-mentioned user according to the above-mentioned lung image pathology recognition result, and collect the above-mentioned user's voice in real time; the recognition unit is configured to perform voice recognition on the above-mentioned user's voice to obtain a voice recognition result, and fill the above-mentioned voice recognition result into a pre-set pathology question and answer information filling template to obtain pathology question and answer information; the sending unit is configured to combine the user number of the above-mentioned user, the above-mentioned lung image pathology recognition result and the above-mentioned pathology question and answer information into lung pathology information, and send the above-mentioned lung pathology information to the associated doctor end.
[0008] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0009] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0010] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the lung pathology information processing method of some embodiments of the present disclosure, the detection efficiency of lung images is improved, so as to assist doctors in diagnosis and speed up the diagnosis efficiency of patients. Specifically, the reasons that affect the patient's diagnostic efficiency and are likely to delay the patient's treatment time are: professional management personnel are required to operate the CT imaging machine, which affects the patient's diagnostic efficiency when there are many patients; in addition, the CT image is not pathologically analyzed, resulting in low doctor's diagnostic efficiency and easy delay of the patient's treatment time. Based on this, the lung pathology information processing method of some embodiments of the present disclosure, first, in response to the inspection of the lung image acquisition instruction, controls the associated lung image acquisition end to collect the lung image information of the user at the target position. Among them, the above-mentioned lung image information includes: lung image. The lung image included in the above-mentioned lung image information is feature extracted to obtain the lung image feature. Thus, it is convenient to perform pathological identification on the lung image. Secondly, the above-mentioned lung image feature is input into the pre-trained lung image pathology recognition model to obtain the lung image pathology recognition result. Thus, the lung image can be preliminarily detected by the pre-trained lung image pathology recognition model. In response to determining that the above-mentioned lung image pathology recognition result meets the abnormal detection condition, the associated intelligent voice robot is controlled to conduct intelligent questions and answers with the above-mentioned user according to the above-mentioned lung image pathology recognition result, and the voice of the above-mentioned user is collected in real time. Thus, through the lung image pathology recognition model and the intelligent voice robot, the consultation on the patient's condition can be preliminarily completed. Thus, the doctor's consultation time is saved. Then, the voice of the above-mentioned user is voice recognized to obtain the voice recognition result, and the above-mentioned voice recognition result is filled into the pre-set pathology question and answer information filling template to obtain pathology question and answer information; finally, the user number of the above-mentioned user, the above-mentioned lung image pathology recognition result and the above-mentioned pathology question and answer information are combined into lung pathology information, and the above-mentioned lung pathology information is sent to the associated doctor end. Thus, the detection efficiency of lung images is improved, so that doctors can be assisted in diagnosis and the diagnosis efficiency of patients can be accelerated. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0012] Figure 1 is a flow chart of some embodiments of the lung pathology information processing method according to the present disclosure;
[0013] Figure 2 is a schematic diagram of the structure of some embodiments of the lung pathology information processing device according to the present disclosure;
[0014] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0016] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0017] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0018] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0019] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0020] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0021] Figure 1The flowchart of some embodiments of the lung pathology information processing method according to the present disclosure is shown. The process 100 of some embodiments of the lung pathology information processing method according to the present disclosure is shown. The lung pathology information processing method is applied to a lung nodule all-in-one machine, which includes: a lung image acquisition terminal, an intelligent voice robot and a doctor terminal, and includes the following steps:
[0022] Step 101, in response to detecting a lung image acquisition instruction, controlling an associated lung image acquisition terminal to acquire lung image information of a user at a target position.
[0023] In some embodiments, the execution subject (e.g., a computing device) of the lung pathology information processing method may control the associated lung image acquisition terminal to acquire lung image information of a user at a target position in response to detecting a lung image acquisition instruction. The above-mentioned lung image information includes: lung images. The lung image acquisition instruction may refer to an instruction to acquire lung images of a user at a target position. For example, the lung image acquisition terminal may be a lung image acquisition CT. The target position may refer to a pre-set position of a user for acquiring lung images. The lung image information may refer to the acquired lung nodule image information (CT image) of the user.
[0024] Step 102: extract features of the lung image included in the lung image information to obtain lung image features.
[0025] In some embodiments, the execution subject may perform feature extraction on the lung image included in the lung image information to obtain lung image features. For example, the lung image included in the lung image information may be subjected to feature extraction by a feature extraction model to obtain lung image features. For example, the feature extraction model may refer to a convolutional neural network model.
[0026] In practice, the execution subject may extract features of the lung image included in the lung image information through the following steps:
[0027] The first step is to perform chromatic aberration correction on the above lung image to obtain a chromatic aberration corrected lung image.
[0028] The first step may include the following sub-steps:
[0029] The first sub-step is to determine the image erasing area corresponding to the above-mentioned lung image. For example, the erasing area selected by the doctor for the above-mentioned lung image is determined as the image erasing area. The doctor may select the erasing area by moving a preset erasing tool. The preset erasing tool may be a planar object with a pre-set shape and size. For example, the preset erasing tool may be a circle with a preset number of points in diameter. The image erasing area may be an area where the content within the area needs to be erased and the color is supplemented according to the image background.
[0030] The second sub-step is to generate a mask image and an initial erased image based on the image erased area. A mask image may be generated whose image size is the same as that of the lung image, and the pixel values of the pixels in the area corresponding to the image erased area are 255, and the pixel values of the pixels outside the area are 0. Then, the execution subject may use an image erasing algorithm to fill in the color of the lung image in the image erased area to obtain an initial erased image. For example, the image erasing algorithm may be a Stable Diffusion Inpainting algorithm.
[0031] The third sub-step is to generate a lung image integration map based on the lung image and the mask map. For example, for each pixel point in the lung image in the mask area corresponding to the mask map, the execution subject can replace the pixel value of the pixel point with [0, 0, 0]. Then, the lung image after the pixel values of each pixel point in the mask area are replaced can be determined as the lung image integration map.
[0032] The fourth sub-step is to generate a lung image splicing tensor based on the initial erased image, the lung image integration map and the mask map. For example, the execution subject can perform tensor conversion on the initial erased image, the lung image integration map and the mask map respectively to obtain an initial color difference corrected lung image tensor, a lung image integration map tensor and a mask map tensor. Then, the obtained initial color difference corrected lung image tensor, lung image integration map tensor and mask map tensor can be spliced into a lung image splicing tensor.
[0033] The fifth sub-step is to input the lung image splicing tensor into the pre-trained lung image chromatic aberration correction model to obtain the chromatic aberration corrected lung image tensor. The lung image chromatic aberration correction model includes residually connected encoding and decoding networks, in each of the encoding and decoding networks, the lung image splicing tensor of the input tensor and the output tensor of the previous encoding and decoding network is used as the input tensor of the next encoding and decoding network, and the encoding and decoding network in each of the encoding and decoding networks includes a downsampling module and an upsampling module, the downsampling module includes a downsampling layer sequence, the upsampling module includes an upsampling layer sequence corresponding to the reverse order of the downsampling layer sequence, the downsampling layers in the downsampling layer sequence are connected in sequence, the upsampling layers in the upsampling layer sequence are connected in sequence, and each downsampling layer in the downsampling layer sequence is connected to the upsampling layer corresponding to the downsampling layer in the upsampling layer sequence. The output tensor of the previous downsampling layer in the above-mentioned downsampling layer sequence is used as the input tensor of the next downsampling layer, and the width and height of the input tensor of each downsampling layer are preset multiples of the width and height of the output tensor; the lung image tensor corresponding to the output tensor of the previous upsampling layer in the above-mentioned upsampling layer sequence is used as the input tensor of the next upsampling layer, and the width and height of the output tensor of each upsampling layer are preset multiples of the width and height of the input tensor, and the above-mentioned lung image tensor is a lung image splicing tensor of the output tensor of the above-mentioned previous upsampling layer and the output tensor of the downsampling layer corresponding to the above-mentioned previous upsampling layer.
[0034] Therefore, the fitting accuracy of the model can be improved through the residual connection of each encoding and decoding network. Also, because the sample lung image integration map can be used as the added feature dimension of the model, and the model is composed of the residual connection of each encoding and decoding network, it can improve the effect of solving the color difference and boundary problems and the fitting accuracy of the model, and thus reduce the color difference between the erased area and the non-erased area in the erased lung image.
[0035] The sixth sub-step is to convert the chromatic aberration-corrected lung image tensor into a chromatic aberration-corrected lung image corresponding to the initial erased image.
[0036] In the second step, feature extraction is performed on the color-corrected lung image to obtain lung image features. For example, feature extraction can be performed on the color-corrected lung image through a feature extraction model to obtain lung image features. For example, the feature extraction model can refer to a BERT model.
[0037] Optionally, the lung image chromatic aberration correction model can be trained by the following steps:
[0038] The first step is to obtain a lung image sample set. The lung image samples in the above lung image sample set include sample color difference lung images, sample lung image mask images, and sample color difference-free lung images. The sample color difference lung image can be a lung image with color difference between the mask area and other areas. The sample lung image mask image can be a mask image containing the mask area. The mask image can be a grayscale image. The pixel value of the pixel point in the mask area in the mask image can be 255. The pixel value of the pixel point outside the mask area in the mask image can be 0. The sample color difference-free lung image can be a lung image with no color difference between the mask area and other areas.
[0039] In the second step, for each lung image sample in the above lung image sample set, the following processing steps are performed:
[0040] First, a sample lung image integration map is generated based on the sample color difference lung image, the sample lung image mask map and the sample non-color difference lung image included in the lung image sample. For each pixel point in the sample color difference lung image in the mask area corresponding to the sample lung image mask map, the execution subject can replace the pixel value of the pixel point with [0, 0, 0]. Then, the sample color difference lung image after replacing the pixel value of each pixel point in the mask area can be determined as the sample lung image integration map.
[0041] Next, based on the sample color difference lung image, the sample lung image mask map and the sample lung image integration map, a spliced lung image tensor is generated. First, the execution subject can perform tensor conversion on the sample color difference lung image, the sample lung image mask map and the sample lung image integration map respectively to obtain a sample color difference lung image tensor, a sample lung image mask map tensor and a sample lung image integration map tensor. Then, the sample color difference lung image tensor, the sample lung image mask map tensor and the sample lung image integration map tensor can be spliced into a spliced lung image tensor.
[0042] Afterwards, the sample color difference-free lung image is converted into a sample color difference-free lung image tensor. The sample color difference-free lung image can be tensor-converted to obtain a sample color difference-free lung image tensor.
[0043] Then, the spliced lung image tensor and the sample color-difference-free lung image tensor are combined into a lung image training sample.
[0044] The third step is to train the initial lung image chromatic aberration correction model according to each lung image training sample to obtain a trained lung image chromatic aberration correction model. The lung image chromatic aberration correction model can be trained in a distributed training manner.
[0045] The third step may include the following sub-steps:
[0046] The first sub-step is to select a target lung image training sample from the above-mentioned lung image training samples. A lung image training sample can be randomly selected from the lung image training samples as the target lung image training sample.
[0047] In the second sub-step, the spliced lung image tensor included in the target lung image training sample is input into the initial lung image chromatic aberration correction model to obtain a chromatic aberration-free lung image tensor.
[0048] The third sub-step is to determine the loss value between the color difference-free lung image tensor and the sample color difference-free lung image tensor corresponding to the target lung image training sample. For example, the loss value between the color difference-free lung image tensor and the sample color difference-free lung image tensor corresponding to the target lung image training sample can be determined by a cross entropy loss function or a hinge loss function.
[0049] The fourth sub-step is to determine whether the above loss value is less than or equal to a preset loss value.
[0050] In a fifth sub-step, in response to determining that the loss value is less than or equal to a preset loss value, the initial lung image chromatic aberration correction model is determined as a trained lung image chromatic aberration correction model.
[0051] Step 103: input the above-mentioned lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result.
[0052] In some embodiments, the above-mentioned execution entity may input the above-mentioned lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result. The lung image pathology recognition model may refer to a pre-trained neural network model that takes lung image features as input and outputs lung image pathology recognition results. For example, the lung image pathology recognition model may be a multi-scale capsule-weighted fusion classification network (MCFCN). The lung image pathology recognition result may indicate whether there are lung nodule features in the lung image.
[0053] The lung image pathology recognition model can be trained through the following steps:
[0054] The first step is to obtain a lung image feature sample set. The lung image feature samples in the lung image feature sample set include sample lung features and sample labels. The sample label can indicate whether the sample lung feature is a lung nodule feature.
[0055] The second step is to select target lung image feature samples from the above lung image feature sample set.
[0056] The third step is to input the sample lung image features included in the above target lung image feature samples into the initial lung image pathology recognition model to obtain the initial lung image pathology recognition results.
[0057] The fourth step is to determine the model loss value between the initial lung image pathology recognition result and the corresponding sample label. The model loss value between the initial lung image pathology recognition result and the corresponding sample label can be determined by a preset loss function.
[0058] In a fifth step, in response to determining that the above model loss value is less than or equal to the preset model loss value, the initial lung image pathology recognition model is determined as the trained lung image pathology recognition model.
[0059] Therefore, the pre-trained lung image pathology recognition model can be used to perform pathology detection and recognition on lung images, thereby speeding up the doctor's diagnostic efficiency.
[0060] Step 104, in response to determining that the above-mentioned lung image pathology recognition result meets the abnormality detection condition, control the associated intelligent voice robot to conduct intelligent question and answer with the above-mentioned user according to the above-mentioned lung image pathology recognition result, and collect the above-mentioned user's voice in real time.
[0061] In some embodiments, the execution subject may, in response to determining that the lung image pathology recognition result satisfies an abnormality detection condition, control the associated intelligent voice robot to conduct intelligent question and answer with the user according to the lung image pathology recognition result, and collect the user's voice in real time. The abnormality detection condition may be: the lung image pathology recognition result indicates the presence of lung nodules in the lungs. The intelligent voice robot may be an intelligent robot with an intelligent question and answer function, which may conduct intelligent question and answer with the user to inquire about the user's physical condition. Real-time collection of the user's voice may refer to the user's reply voice to the questions asked by the intelligent voice robot.
[0062] Step 105, performing speech recognition on the user's speech to obtain a speech recognition result, and filling the speech recognition result into a preset pathology question and answer information filling template to obtain pathology question and answer information.
[0063] In some embodiments, the above-mentioned execution subject can perform voice recognition on the voice of the above-mentioned user to obtain a voice recognition result, and fill the above-mentioned voice recognition result into a pre-set pathology question and answer information filling template to obtain pathology question and answer information. For example, the voice of the above-mentioned user can be voice recognized by voice-to-text software to obtain a voice recognition result. The pathology question and answer information filling template can be a pre-built filling template for filling in reply information about lung patients. For example, the pathology question and answer information filling template can include various field types. The text of the corresponding field type in the voice recognition result can be filled in the blank filling place of the corresponding field type. For example, the pathology question and answer information filling template can be "Name: [ ]; Age: [ ]; Symptom description: [ ]". That is, "[ ]" can represent a blank filling place.
[0064] Step 106: Combine the user number of the user, the lung image pathology recognition result and the pathology question and answer information into lung pathology information, and send the lung pathology information to the associated doctor terminal.
[0065] In some embodiments, the execution entity may combine the user ID of the user, the lung image pathology recognition result and the pathology question and answer information into lung pathology information, and send the lung pathology information to an associated doctor terminal. The doctor terminal may be an operation terminal of a lung doctor who analyzes the lung pathology information.
[0066] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a lung pathology information processing device. These lung pathology information processing device embodiments are Figure 1 Corresponding to the method embodiments shown, the lung pathology information processing device can be specifically applied to various electronic devices.
[0067] like Figure 2As shown, the lung pathology information processing device 200 of some embodiments includes: a first control unit 201, an extraction unit 202, an input unit 203, a second control unit 204, an identification unit 205 and a sending unit 206. The first control unit 201 is configured to control the associated lung image acquisition terminal to collect lung image information of the user at the target position in response to detecting a lung image acquisition instruction, wherein the lung image information includes: lung images; the extraction unit 202 is configured to extract features of the lung images included in the lung image information to obtain lung image features; the input unit 203 is configured to input the lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result; the second control unit 204 is configured to respond to determining that the lung image pathology recognition result meets the requirements; The abnormal detection conditions are met, and the associated intelligent voice robot is controlled to conduct intelligent question and answer with the user according to the lung image pathology recognition result, and to collect the user's voice in real time; the recognition unit 205 is configured to perform voice recognition on the user's voice to obtain a voice recognition result, and fill the voice recognition result into a preset pathology question and answer information filling template to obtain pathology question and answer information; the sending unit 206 is configured to combine the user number of the user, the lung image pathology recognition result and the pathology question and answer information into lung pathology information, and send the lung pathology information to the associated doctor end.
[0068] It is understandable that the units described in the pulmonary pathology information processing device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the pulmonary pathology information processing device 200 and the units contained therein, and will not be described in detail here.
[0069] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0070] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0071] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0072] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.
[0073] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0074] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0075] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to detecting a lung image acquisition instruction, controls the associated lung image acquisition terminal to acquire lung image information of a user at a target position, wherein the lung image information includes: lung images; performs feature extraction on the lung images included in the lung image information to obtain lung image features; inputs the lung image features into a pre-trained lung image pathology recognition model to obtain lung image pathology recognition results; in response to determining that the lung image pathology recognition results meet the abnormality detection conditions, controls the associated intelligent voice robot to conduct intelligent question and answer with the user according to the lung image pathology recognition results, and acquires the user's voice in real time; performs voice recognition on the user's voice to obtain a voice recognition result, and fills the voice recognition result into a pre-set pathology question and answer information filling template to obtain pathology question and answer information; combines the user number of the user, the lung image pathology recognition result and the pathology question and answer information into lung pathology information, and sends the lung pathology information to the associated doctor terminal.
[0076] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0077] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0078] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor comprising: a first control unit, an extraction unit, an input unit, a second control unit, a recognition unit and a sending unit. Among them, the names of these units do not constitute a limitation on the unit itself in certain cases. For example, the recognition unit may also be described as "a unit for performing speech recognition on the above-mentioned user's speech to obtain a speech recognition result, and filling the above-mentioned speech recognition result into a pre-set pathology question and answer information filling template to obtain pathology question and answer information".
[0079] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0080] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. A lung pathology information processing method, applied to a lung nodule all-in-one machine, the lung nodule all-in-one machine comprising: Lung image acquisition end, intelligent voice robot and doctor end, including: In response to detecting a lung image acquisition instruction, controlling the associated lung image acquisition terminal to acquire lung image information of the user at the target position, wherein the lung image information includes: lung images; Extracting features of the lung image included in the lung image information to obtain lung image features; Inputting the lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result; In response to determining that the lung image pathology recognition result meets the abnormality detection condition, controlling the associated intelligent voice robot to conduct intelligent question and answer with the user according to the lung image pathology recognition result, and collecting the user's voice in real time; Performing speech recognition on the user's speech to obtain a speech recognition result, and filling the speech recognition result into a preset pathology question and answer information filling template to obtain pathology question and answer information; The user number of the user, the lung image pathology recognition result and the pathology question and answer information are combined into lung pathology information, and the lung pathology information is sent to an associated doctor terminal.
2. The method according to claim 1, wherein: The extracting features of the lung image included in the lung image information to obtain lung image features includes: Performing chromatic aberration correction processing on the lung image to obtain a chromatic aberration corrected lung image; Feature extraction is performed on the chromatic aberration-corrected lung image to obtain lung image features.
3. The method according to claim 2, wherein: The step of performing chromatic aberration correction processing on the lung image to obtain a chromatic aberration corrected lung image includes: Determine an image erasing area corresponding to the lung image; Based on the image erasing area, generating a mask map and an initial erasing image; Generate a lung image integration map based on the lung image and the mask map; generating a lung image splicing tensor based on the initial erased image, the lung image integration map and the mask map; Inputting the lung image stitching tensor into a pre-trained lung image chromatic aberration correction model to obtain a chromatic aberration corrected lung image tensor; The chromatic aberration-corrected lung image tensor is converted into a chromatic aberration-corrected lung image corresponding to the initial erased image.
4. The method according to claim 1, wherein: Before inputting the lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result, the method further includes: Acquire a lung image feature sample set, wherein the lung image feature samples in the lung image feature sample set include sample lung features and sample labels; Selecting a target lung image feature sample from the lung image feature sample set; Inputting the sample lung image features included in the target lung image feature sample into the initial lung image pathology recognition model to obtain an initial lung image pathology recognition result; Determining a model loss value between the initial lung image pathology recognition result and the corresponding sample label; In response to determining that the model loss value is less than or equal to the preset model loss value, the initial lung image pathology recognition model is determined as the trained lung image pathology recognition model.
5. A pulmonary pathology information processing device, applied to a pulmonary nodule integrated machine, the pulmonary nodule integrated machine comprising: Lung image acquisition end, intelligent voice robot and doctor end, including: The first control unit is configured to control the associated lung image acquisition terminal to acquire lung image information of the user at the target position in response to detecting the lung image acquisition instruction, wherein the lung image information includes: lung image; an extraction unit, configured to perform feature extraction on the lung image included in the lung image information to obtain lung image features; An input unit is configured to input the lung image features into a pre-trained lung image pathology recognition model to obtain a lung image pathology recognition result; A second control unit is configured to, in response to determining that the lung image pathology recognition result meets the abnormality detection condition, control the associated intelligent voice robot to conduct intelligent question and answer with the user according to the lung image pathology recognition result, and collect the user's voice in real time; A recognition unit configured to perform speech recognition on the user's speech to obtain a speech recognition result, and fill the speech recognition result into a preset pathology question and answer information filling template to obtain pathology question and answer information; The sending unit is configured to combine the user number of the user, the lung image pathology recognition result and the pathology question and answer information into lung pathology information, and send the lung pathology information to the associated doctor end.
6. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.
7. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Weak supervision semantic segmentation method and device based on image restoration technology
CN111369572A
Medical image hospital guide and examination guide system, method and equipment based on artificial intelligence
CN112786194A
Medical image conversion method and system
CN117522673A
Image-based severe disease comparison evaluation method and system
CN117995341A
Forming method for patterned FRP molded product
JP1980133926A
