Fluorescence in-situ hybridization signal processing system, method and equipment and storage medium

Abstract

The invention relates to the technical field of fluorescence scanning, and discloses a fluorescence in-situ hybridization signal processing system, method and equipment and a storage medium. The system comprises an image acquisition subsystem and a signal processing subsystem, wherein the signal processing subsystem comprises a preprocessing module, a signal processing module and a signal statistics module; the image acquisition subsystem is used for scanning the fluorescence in-situ hybridization sample and acquiring a sample image; the preprocessing module is used for preprocessing the sample image to obtain a preprocessed sample image; the signal processing module is used for performing signal processing on the preprocessed sample image by using the optimized target detection model, the optimized segmentation model and the optimized classification model to obtain signal processing data; and the signal statistics module is used for evaluating the signal processing data according to a preset threshold value to obtain a fluorescence in-situ hybridization evaluation result. According to the invention, efficient automation of the whole project of fluorescence in situ hybridization is effectively realized, large-scale data analysis is supported, and the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of fluorescence scanning technology, and in particular to a fluorescence in situ hybridization signal processing system, method, device and storage medium. Background Art

[0002] Currently, fluorescence in situ hybridization (FISH) assays are primarily interpreted manually in laboratories, requiring technicians to visually observe the fluorescence signal and manually record the results. This method is not only time-consuming and inefficient, but also susceptible to human factors (such as fatigue and lack of experience), resulting in low consistency and accuracy in FISH results. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and to provide a fluorescence in situ hybridization signal processing system, method, device and storage medium.

[0004] The present invention provides the following technical solutions:

[0005] In a first aspect, an embodiment of the present disclosure provides a fluorescence in situ hybridization signal processing system, the system comprising an image acquisition subsystem and a signal processing subsystem, the image acquisition subsystem and the signal processing subsystem being communicatively connected, the signal processing subsystem comprising a preprocessing module, a signal processing module, and a signal statistics module;

[0006] The image acquisition subsystem is used to scan the fluorescence in situ hybridization sample and acquire the sample image;

[0007] The preprocessing module is used to preprocess the sample image to obtain a preprocessed sample image, wherein the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching;

[0008] The signal processing module is used to perform signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model to obtain signal processing data;

[0009] The signal statistics module is used to set a preset threshold and evaluate the signal processing data according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result.

[0010] In an optional embodiment, the image acquisition subsystem includes an automatic stage, a scanning module and a control module;

[0011] The automatic stage is used to carry the fluorescence in situ hybridization sample;

[0012] The scanning module is used to scan the fluorescence in situ hybridization sample using a multi-channel fluorescence filter, collect the sample image, and generate a unique identification code for the sample image;

[0013] The control module is used to communicate with the signal processing subsystem through an API data interface or an SDK toolkit and control the scanning parameters of the scanning module.

[0014] In an optional embodiment, the signal processing module includes an algorithm building unit and a first signal processing unit;

[0015] The algorithm building unit is used to build an initial target detection model, an initial segmentation model, and an initial classification model, and obtain historical samples, and respectively train and adjust the initial target detection model, the initial segmentation model, and the initial classification model through the historical samples to obtain an optimized target detection model, an optimized segmentation model, and an optimized classification model;

[0016] The first signal processing unit is used to use the optimized target detection model to identify multiple fluorescence signal points in the preprocessed sample image, use the optimized segmentation model to segment multiple fluorescence signal areas in the preprocessed sample image according to each of the fluorescence signal points, and use the optimized classification model to classify the signal patterns of the fluorescence signal points in each of the fluorescence signal areas to obtain classified fluorescence signal data.

[0017] In an optional embodiment, the signal processing module further includes a second signal processing unit and a signal detection unit;

[0018] The second signal processing unit is configured to separate the multi-color signals in the classified fluorescence signal data and analyze the overlapping signals in the separated fluorescence signal data;

[0019] The signal detection unit is used to perform noise filtering on the analyzed fluorescence signal data using a preset noise threshold to obtain the signal processing data.

[0020] In an optional embodiment, the signal statistics module includes a report generating unit and a checking unit;

[0021] The report generating unit is configured to generate a structured report based on the fluorescence in situ hybridization evaluation result;

[0022] The inspection unit is used to connect to a database, perform consistency inspection on the fluorescence in situ hybridization evaluation results according to the database, determine abnormal results, and generate early warning information according to the abnormal results.

[0023] In an optional embodiment, the system further includes a signal storage subsystem and an interaction subsystem;

[0024] The signal storage subsystem is communicatively connected to the signal processing subsystem, and the interaction subsystem is communicatively connected to the signal storage subsystem;

[0025] The signal storage subsystem is configured to store the sample image, the signal processing data, the preset threshold value, and the fluorescence in situ hybridization evaluation result;

[0026] The interactive subsystem is used to monitor the scanning progress and device status of the image acquisition subsystem in real time, and to display the sample image, the signal processing data, the preset threshold value and the fluorescence in situ hybridization evaluation result.

[0027] In an optional embodiment, the signal storage subsystem includes a local storage module, a cloud storage module and a data security module;

[0028] The local storage module is used to store the signal processing data, the preset threshold and the fluorescence in situ hybridization evaluation result;

[0029] The cloud storage module is used to store the sample image and the model parameters of the optimized object detection model, the optimized segmentation model and the optimized classification model;

[0030] The data security module is used to encrypt the data in the local storage module and the cloud storage module, and control the access rights of the local storage module and the cloud storage module.

[0031] In a second aspect, an embodiment of the present disclosure provides a fluorescence in situ hybridization signal processing method, which is applied to the fluorescence in situ hybridization signal processing system as described in the first aspect, wherein the system includes an image acquisition subsystem and a signal processing subsystem, wherein the signal processing subsystem includes a preprocessing module, a signal processing module, and a signal statistics module, and the method includes:

[0032] Scanning the fluorescence in situ hybridization sample by the image acquisition subsystem to acquire a sample image;

[0033] Preprocessing the sample image by the preprocessing module to obtain a preprocessed sample image, wherein the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching;

[0034] The signal processing module performs signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model to obtain signal processing data;

[0035] A preset threshold is set by the signal statistics module, and the signal processing data is evaluated according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result.

[0036] In a third aspect, an embodiment of the present disclosure provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the fluorescence in situ hybridization signal processing method described in the second aspect are implemented.

[0037] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the fluorescence in situ hybridization signal processing method described in the second aspect are implemented.

[0038] Beneficial effects of this application:

[0039] The fluorescence in situ hybridization signal processing system provided in the embodiment of the present application includes an image acquisition subsystem and a signal processing subsystem, the image acquisition subsystem and the signal processing subsystem are communicatively connected, and the signal processing subsystem includes a preprocessing module, a signal processing module and a signal statistics module; the image acquisition subsystem is used to scan the fluorescence in situ hybridization sample and acquire a sample image; the preprocessing module is used to preprocess the sample image to obtain a preprocessed sample image, and the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching; the signal processing module is used to use a pre-acquired optimized target detection model, an optimized segmentation model, and an optimized classification model to perform signal processing on the preprocessed sample image to obtain signal processing data; the signal statistics module is used to set a preset threshold and evaluate the signal processing data according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result. The present application effectively realizes the efficient automation of the entire fluorescence in situ hybridization project, supports large-scale data analysis, is conducive to reducing the project time of fluorescence in situ hybridization detection, and improves detection efficiency.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. Similar components are numbered similarly in the various drawings.

[0042] Figure 1 A schematic structural diagram of a fluorescence in situ hybridization signal processing system provided in an embodiment of the present application is shown;

[0043] Figure 2 A schematic structural diagram of an image acquisition subsystem provided in an embodiment of the present application is shown;

[0044] Figure 3 A schematic structural diagram of a signal processing module provided in an embodiment of the present application is shown;

[0045] Figure 4 A schematic structural diagram of a signal statistics module provided in an embodiment of the present application is shown;

[0046] Figure 5 A schematic structural diagram of another fluorescence in situ hybridization signal processing system provided in an embodiment of the present application is shown;

[0047] Figure 6 A schematic structural diagram of a signal storage subsystem provided in an embodiment of the present application is shown;

[0048] Figure 7 A flowchart of a fluorescence in situ hybridization signal processing method provided in an embodiment of the present application is shown;

[0049] Figure 8 A structural diagram of a computer device provided in an embodiment of the present application is shown.

[0050] Specific component symbol description:

[0051] 100-fluorescence in situ hybridization signal processing system; 110-image acquisition subsystem; 111-automatic stage; 112-scanning module; 113-control module; 120-signal processing subsystem; 121-preprocessing module; 122-signal processing module; 1221-algorithm construction unit; 1222-first signal processing unit; 1223-second signal processing unit; 1224-signal detection unit; 123-signal statistics module; 1231-report generation unit; 1232-inspection unit; 130-signal storage subsystem; 131-local storage module; 132-cloud storage module; 133-data security module; 140-interaction subsystem. DETAILED DESCRIPTION

[0052] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0053] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used in the template description herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0055] Example 1

[0056] like Figure 1 FIG. 1 is a schematic diagram of the structure of a fluorescence in situ hybridization signal processing system 100 according to an embodiment of the present application. The fluorescence in situ hybridization signal processing system 100 provided in the embodiment of the present application includes an image acquisition subsystem 110 and a signal processing subsystem 120. The image acquisition subsystem 110 and the signal processing subsystem 120 are communicatively connected. The signal processing subsystem 120 includes a preprocessing module 121, a signal processing module 122, and a signal statistics module 123.

[0057] In this embodiment, the image acquisition subsystem 110 is used to scan the fluorescence in situ hybridization sample and acquire the sample image. Figure 2 As shown, the image acquisition subsystem 110 includes an automatic stage 111 , a scanning module 112 and a control module 113 .

[0058] The automatic stage 111 is used to carry fluorescence in situ hybridization samples. It realizes continuous scanning of batch samples through precise mechanical structure and motor control. It can move automatically to ensure that all parts of the sample can be accurately covered during the scanning process, realizing efficient and orderly batch processing and significantly improving the processing speed (e.g., 200 samples / hour).

[0059] The scanning module 112 integrates an existing high-sensitivity fluorescence microscope and an automatic scanner, and is also equipped with a multi-channel fluorescence filter for scanning fluorescence in situ hybridization samples using the multi-channel fluorescence filter. It can support multi-color fluorescence in situ hybridization signal separation to collect sample images with different fluorescence signals, generate a unique identification code for the sample image, and store the unique identification code of the sample image and the corresponding project information to facilitate subsequent identification and management of the sample image.

[0060] The control module 113 is used to communicate with the signal processing subsystem 120 through the API data interface or SDK toolkit, and control the scanning parameters of the scanning module 112 (such as exposure time, filter channel, focus, etc.), flexibly adapting to the characteristics and detection requirements of different samples to obtain the best image acquisition effect.

[0061] In this embodiment, the preprocessing module 121 is used to preprocess the sample image to obtain a preprocessed sample image. The preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching, among which autofocus and image stitching are mainly for large field of view scanning. Image denoising can remove random noise interference in the image to make the fluorescence signal clearer; background correction can eliminate the masking effect of background impurities on the fluorescence signal; contrast enhancement helps to highlight the difference between the fluorescence signal area and the background; autofocus ensures that the image is accurately focused to avoid blurring that affects subsequent analysis; image stitching is mainly for images scanned with a large field of view, stitching images of multiple fields of view into a complete sample image, which is convenient for evaluating the overall sample situation.

[0062] In this embodiment, the signal processing module 122 is used to perform signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model to obtain signal processing data.

[0063] Preferably, if Figure 3 As shown, the signal processing module 122 includes an algorithm building unit 1221 and a first signal processing unit 1222 .

[0064] Algorithm building unit 1221 is used to build an initial target detection model (such as Faster R-CNN, YOLOv5), an initial segmentation model (such as U-Net, Mask R-CNN) and an initial classification model (such as ResNet, EfficientNet), and obtain historical samples. The initial target detection model, the initial segmentation model and the initial classification model are trained and adjusted using the historical samples to obtain an optimized target detection model, an optimized segmentation model and an optimized classification model. Preferably, an attention mechanism can be introduced into each model to make the model pay more attention to the key areas of the fluorescence signal and improve the analysis stability of complex samples; an adversarial training method can be used to improve the generalization ability and robustness of the model, and ultimately an optimized target detection model, an optimized segmentation model and an optimized classification model are obtained.

[0065] The first signal processing unit 1222 is used to use the optimized target detection model to identify multiple fluorescent signal points in the preprocessed sample image, use the optimized segmentation model to segment the multiple independent fluorescent signal areas in the preprocessed sample image according to each fluorescent signal point, and use the optimized classification model to classify the signal patterns of the fluorescent signal points in each fluorescent signal area (such as gene amplification, deletion, rearrangement, etc.) to obtain classified fluorescent signal data. After the AI ​​model is introduced and based on deep learning, accurate recognition and classification of fluorescent signals can be achieved, the accuracy rate can be improved, and key basic data can be provided for subsequent in-depth analysis.

[0066] Preferably, if Figure 3 As shown, the signal processing module 122 further includes a second signal processing unit 1223 and a signal detection unit 1224 .

[0067] The second signal processing unit 1223 is used to separate the multi-color signals in the classified fluorescence signal data, distinguish the different biological meanings represented by the fluorescence signals of different colors, and analyze the overlapping signals in the separated fluorescence signal data to disassemble the specific information of each overlapping signal, so as to make the signal clearer and reduce the cross-interference rate, which is convenient for subsequent accurate evaluation.

[0068] The signal detection unit 1224 is used to filter the noise of the analyzed fluorescence signal data using a preset noise threshold, remove interference signals, retain valid fluorescence signal data, and obtain signal processing data, providing a purer and more reliable basis for subsequent evaluation.

[0069] In this embodiment, the signal statistics module 123 is used to set preset thresholds to evaluate signal quality (clarity, signal-to-noise ratio). The preset thresholds include a signal quantity threshold and a background noise threshold. The signal processing data is evaluated based on the preset thresholds to determine the signal quality, such as signal clarity, signal-to-noise ratio, etc., thereby obtaining a fluorescence in situ hybridization evaluation result that intuitively reflects the actual situation of the fluorescence signal in the sample and the corresponding related information.

[0070] Preferably, if Figure 4 As shown, the signal statistics module 123 further includes a report generating unit 1231 and a checking unit 1232 .

[0071] The report generation unit 1231 is used to generate a structured report (PDF / Excel format, etc.) based on the fluorescence in situ hybridization evaluation results, so that users can view, record and organize the analysis results, and facilitate subsequent scientific research, clinical application or archiving operations.

[0072] Inspection unit 1232 is used to connect with the clinical database (PRD system) and perform consistency checks on the fluorescence in situ hybridization evaluation results based on the relevant data in the database, determine abnormal results, and generate early warning information based on the abnormal results to trigger manual review (such as retaining samples for retesting) to further verify the situation and ensure the accuracy and reliability of the results.

[0073] In this embodiment, if Figure 5 As shown, the fluorescence in situ hybridization signal processing system 100 further includes a signal storage subsystem 130 and an interaction subsystem 140 . The signal storage subsystem 130 is communicatively connected to the signal processing subsystem 120 , and the interaction subsystem 140 is communicatively connected to the signal storage subsystem 130 .

[0074] The signal storage subsystem 130 is used to store various data related to FISH signal processing, including sample images, signal processing data, preset thresholds, and FISH evaluation results, to ensure secure storage and convenient retrieval of data.

[0075] The interactive subsystem 140 is used to monitor the scanning progress of the image acquisition subsystem 110 in real time, so that the user can promptly understand the progress of the scanning task, know when the scan can be completed, the current amount of work completed, and other information; at the same time, it can also monitor the device status in real time, including whether the device is operating normally and whether there are any faults, so as to promptly discover and handle problems and ensure the smooth progress of image acquisition.

[0076] The interactive subsystem 140 is also used to display various types of information such as sample images, signal processing data, preset thresholds, and fluorescence in situ hybridization evaluation results, and supports multi-layer overlay and separation, making it convenient for users to view and analyze data from different angles and levels, and intuitively grasp the sample conditions and the results and details of each link of signal processing.

[0077] Optionally, the interactive subsystem 140 also allows the user to manually correct the results of the automatic evaluation based on his or her own professional knowledge and experience. When it is found that the automatic evaluation may have deviations, the user can manually adjust the evaluation results to further improve the accuracy of the results. This also reflects the advantages of human-computer collaboration and makes the system more in line with actual needs and professional requirements.

[0078] Preferably, if Figure 6 As shown, the signal storage subsystem 130 includes a local storage module 131 , a cloud storage module 132 and a data security module 133 .

[0079] The local storage module 131 is used to store signal processing data, preset thresholds and fluorescence in situ hybridization evaluation results, which facilitates local and rapid access and use of these data without relying on network connection, improves data reading efficiency, and ensures the security and stability of data in the local environment.

[0080] The cloud storage module 132 is used to store sample images and model parameters of the optimized target detection model, optimized segmentation model and optimized classification model. Cloud storage is highly scalable and flexible, which makes it convenient for users in different regions and different devices to retrieve data through the network. It also facilitates centralized management and update maintenance of model parameters. At the same time, it can also serve as an effective way to back up data and prevent irreparable losses caused by the loss of locally stored data.

[0081] The data security module 133 is used to encrypt the data in the local storage module 131 and the cloud storage module 132 to prevent security issues such as data leakage and tampering, and to control the access rights of the local storage module 131 and the cloud storage module 132. Only authorized personnel and devices can legally access the relevant data, ensuring the security and integrity of the entire system data.

[0082] This system automates the entire process from sample loading, scanning, image processing to result generation, without the need for human intervention. It also performs intelligent quality control, automatically detects image quality (such as blur and noise), triggers rescanning or manual review, and reduces labor costs. Cloud resource sharing reduces hardware investment, and the modular design facilitates upgrades and maintenance, reducing long-term operating costs.

[0083] The fluorescence in situ hybridization signal processing system 100 provided in the embodiment of the present application effectively realizes efficient automation of the entire fluorescence in situ hybridization project, supports large-scale data analysis, is conducive to reducing the project time of fluorescence in situ hybridization detection, and improves detection efficiency.

[0084] Example 2

[0085] like Figure 7 FIG. 1 is a flow chart of a fluorescence in situ hybridization signal processing method according to an embodiment of the present application. The fluorescence in situ hybridization signal processing method provided in the embodiment of the present application is applied to the fluorescence in situ hybridization signal processing system according to Example 1. The system includes an image acquisition subsystem and a signal processing subsystem. The signal processing subsystem includes a preprocessing module, a signal processing module, and a signal statistics module. The specific method includes the following steps:

[0086] Step S110, scanning the fluorescence in situ hybridization sample by the image acquisition subsystem to acquire a sample image;

[0087] Step S120, preprocessing the sample image by a preprocessing module to obtain a preprocessed sample image, where the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus, and image stitching;

[0088] Step S130, performing signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model through the signal processing module to obtain signal processing data;

[0089] Step S140 : setting a preset threshold through the signal statistics module, and evaluating the signal processing data according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result.

[0090] The fluorescence in situ hybridization signal processing method provided in the embodiment of the present application can implement each process of the fluorescence in situ hybridization signal processing system corresponding to Example 1 and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0091] The fluorescence in situ hybridization signal processing method provided in the embodiments of the present application effectively realizes the efficient automation of the entire fluorescence in situ hybridization project, can process large quantities of samples and upload data to the cloud to realize data sharing and remote collaboration, support large-scale data analysis, and is conducive to reducing the project time of fluorescence in situ hybridization detection and improving detection efficiency.

[0092] Example 3

[0093] The present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0094] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with a memory 81, a processor 82, and a network interface 83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0095] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0096] The memory 81 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or D slot compatibility test memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as the hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk equipped on the computer device 8, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions for the slot compatibility test method. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0097] In some embodiments, the processor 82 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other fluorescence in situ hybridization signal processing chip. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to execute computer-readable instructions or process data stored in the memory 81, such as computer-readable instructions for executing the slot compatibility testing method.

[0098] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0099] The computer device provided in this embodiment can execute the above-mentioned fluorescence in situ hybridization signal processing method, which can be the fluorescence in situ hybridization signal processing method of each of the above-mentioned embodiments.

[0100] Example 4

[0101] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the fluorescence in situ hybridization signal processing method in the embodiment are implemented.

[0102] In this embodiment, the computer-readable storage medium includes flash memory, hard disks, multimedia cards, card-type memories (e.g., SD or DX memories), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk equipped with the computer device, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Of course, the computer-readable storage medium may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store the operating system and various application software installed on the computer device. In addition, the computer-readable storage medium may also be used to temporarily store various types of data that have been output or are about to be output.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes 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 box in the structure diagram and / or flowchart, and the combination of boxes in the structure diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0104] In addition, the functional modules or units in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0105] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and other media that can store program codes.

[0106] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A fluorescence in situ hybridization signal processing system, characterized in that: The system includes an image acquisition subsystem and a signal processing subsystem, wherein the image acquisition subsystem and the signal processing subsystem are communicatively connected, and the signal processing subsystem includes a preprocessing module, a signal processing module and a signal statistics module; The image acquisition subsystem is used to scan the fluorescence in situ hybridization sample and acquire the sample image; The preprocessing module is used to preprocess the sample image to obtain a preprocessed sample image, wherein the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching; The signal processing module is used to perform signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model to obtain signal processing data; The signal statistics module is used to set a preset threshold and evaluate the signal processing data according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result.

2. The fluorescence in situ hybridization signal processing system according to claim 1, characterized in that: The image acquisition subsystem includes an automatic stage, a scanning module and a control module; The automatic stage is used to carry the fluorescence in situ hybridization sample; The scanning module is used to scan the fluorescence in situ hybridization sample using a multi-channel fluorescence filter, collect the sample image, and generate a unique identification code for the sample image; The control module is used to communicate with the signal processing subsystem through an API data interface or an SDK toolkit, and control the scanning parameters of the scanning module.

3. The fluorescence in situ hybridization signal processing system according to claim 1, characterized in that: The signal processing module includes an algorithm building unit and a first signal processing unit; The algorithm building unit is used to build an initial target detection model, an initial segmentation model, and an initial classification model, and obtain historical samples, and respectively train and adjust the initial target detection model, the initial segmentation model, and the initial classification model through the historical samples to obtain an optimized target detection model, an optimized segmentation model, and an optimized classification model; The first signal processing unit is used to use the optimized target detection model to identify multiple fluorescence signal points in the preprocessed sample image, use the optimized segmentation model to segment multiple fluorescence signal areas in the preprocessed sample image according to each of the fluorescence signal points, and use the optimized classification model to classify the signal patterns of the fluorescence signal points in each of the fluorescence signal areas to obtain classified fluorescence signal data.

4. The fluorescence in situ hybridization signal processing system according to claim 3, characterized in that: The signal processing module further includes a second signal processing unit and a signal detection unit; The second signal processing unit is configured to separate the multi-color signals in the classified fluorescence signal data and analyze the overlapping signals in the separated fluorescence signal data; The signal detection unit is used to perform noise filtering on the analyzed fluorescence signal data using a preset noise threshold to obtain the signal processing data.

5. The fluorescence in situ hybridization signal processing system according to claim 4, characterized in that: The signal statistics module includes a report generating unit and a checking unit; The report generating unit is configured to generate a structured report based on the fluorescence in situ hybridization evaluation result; The inspection unit is used to connect to a database, perform consistency inspection on the fluorescence in situ hybridization evaluation results according to the database, determine abnormal results, and generate early warning information according to the abnormal results.

6. The fluorescence in situ hybridization signal processing system according to claim 1, characterized in that: The system also includes a signal storage subsystem and an interaction subsystem; The signal storage subsystem is communicatively connected to the signal processing subsystem, and the interaction subsystem is communicatively connected to the signal storage subsystem; The signal storage subsystem is used to store the sample image, the signal processing data, the preset threshold value and the fluorescence in situ hybridization evaluation result; The interactive subsystem is used to monitor the scanning progress and device status of the image acquisition subsystem in real time, and to display the sample image, the signal processing data, the preset threshold value and the fluorescence in situ hybridization evaluation result.

7. The fluorescence in situ hybridization signal processing system according to claim 6, characterized in that: The signal storage subsystem includes a local storage module, a cloud storage module and a data security module; The local storage module is used to store the signal processing data, the preset threshold and the fluorescence in situ hybridization evaluation result; The cloud storage module is used to store the sample image and the model parameters of the optimized object detection model, the optimized segmentation model and the optimized classification model; The data security module is used to encrypt the data in the local storage module and the cloud storage module, and control the access rights of the local storage module and the cloud storage module.

8. A fluorescence in situ hybridization signal processing method, characterized in that: The method is applied to the fluorescence in situ hybridization signal processing system according to any one of claims 1 to 7, wherein the system comprises an image acquisition subsystem and a signal processing subsystem, wherein the signal processing subsystem comprises a preprocessing module, a signal processing module, and a signal statistics module. Scanning the fluorescence in situ hybridization sample by the image acquisition subsystem to acquire a sample image; Preprocessing the sample image by the preprocessing module to obtain a preprocessed sample image, wherein the preprocessing operations include image denoising, background correction, contrast enhancement, autofocus and image stitching; The signal processing module performs signal processing on the pre-processed sample image using the pre-acquired optimized target detection model, optimized segmentation model, and optimized classification model to obtain signal processing data; A preset threshold is set by the signal statistics module, and the signal processing data is evaluated according to the preset threshold to obtain a fluorescence in situ hybridization evaluation result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the fluorescence in situ hybridization signal processing method according to claim 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the fluorescence in situ hybridization signal processing method according to claim 8 are implemented.

Images