Apparatus and method for management of analysis of cervical images, device and storage medium

Abstract

The present disclosure relates to an apparatus and method, device and storage medium for the analysis management of cervical images. The apparatus comprises at least one processor configured to: acquire at least one of a cervical liquid-based cell image, a cervical cell immunohistochemical image and a cervical histological image of a subject as an image to be analyzed; determine an analysis result based on the image to be analyzed and using a learning network; present at least part of the image to be analyzed; present an intermediate analysis interface in association with the at least part of the image based on the analysis result, wherein the intermediate analysis interface presents a corresponding image block and attributes of each detected object. The present disclosure can simultaneously present the analysis result and at least part of the image to be analyzed associated with the analysis result, thereby reducing the possibility of misdiagnosis / missed diagnosis in the analysis management of cervical images, improving the accuracy and convenience of the analysis management of cervical images, and further improving the quality of medical services.

Description

[0001] This application is a divisional application of Chinese Patent Application No. 202110754716.0, filed on July 5, 2021, entitled "Apparatus and Method, Device and Storage Medium for Analysis and Management of Cervical Images". Technical Field

[0002] This disclosure relates to the field of cervical image analysis technology, and more specifically, to an apparatus, method, device, and computer-readable storage medium for the analysis and management of cervical images. Background Technology

[0003] Cervical cancer is the most common gynecological malignancy, and its incidence has been trending towards younger ages in recent years. Worldwide, there are 528,000 new cases of cervical cancer and 266,000 deaths annually, with 85% of these deaths occurring in low- and middle-income areas with low screening rates. Furthermore, cervical cancer is a preventable and curable disease, with an early cure rate reaching 90%. Therefore, early screening and diagnosis are crucial for the prevention and control of cervical cancer. Current cervical cancer screening technologies can be divided into two categories: morphological methods, which examine at the cellular or tissue level to identify abnormalities, and molecular biology-based methods, which examine for cervical cancer markers such as cervical epithelial tumors. Traditional cervical cancer screening mainly relies on manual interpretation of images by doctors, which is not only labor-intensive and inefficient but also has a high rate of misdiagnosis, thus hindering the implementation of large-scale screening.

[0004] In recent years, with the development of artificial intelligence technology, intelligent screening and analysis of cervical cancer cells can be achieved by automatically capturing pathological images and automatically analyzing and identifying cancer cells. This effectively reduces the workload of doctors and improves diagnostic accuracy. However, existing deep learning-based intelligent cervical screening and analysis systems can only provide a single analysis result or screening image, making it impossible for doctors to make a correct diagnosis by combining it with surrounding pathological images. This leads to misdiagnosis / missed diagnosis during the analysis and management of cervical images. Therefore, the above problems pose a significant challenge to the application of intelligent cervical screening and analysis systems. Summary of the Invention

[0005] This disclosure is provided to address the aforementioned problems existing in the prior art.

[0006] This disclosure discloses an apparatus, method, device, and computer-readable storage medium for the analysis and management of cervical images. The apparatus acquires at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix as the image to be analyzed; determines the analysis result based on the image to be analyzed and using a learning network; presents at least a portion of the image to be analyzed; and presents an intermediate analysis interface in association with the analysis result and the at least a portion of the image. The intermediate analysis interface presents corresponding image blocks and attributes of each detected object, enabling doctors to review the analysis results by comparing them with the corresponding image blocks and attributes of the detected objects. The diagnostic information reviewed by the doctor is then used to generate the analysis report. This reduces the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images, improves the accuracy, convenience, and user-friendliness of cervical image analysis and management, and further enhances the quality of medical services.

[0007] According to a first aspect of this disclosure, an apparatus for the analysis and management of cervical images is provided. The apparatus includes at least one processor configured to: acquire at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of a subject as an image to be analyzed; determine analysis results based on the image to be analyzed and using a learning network; present at least a portion of the image to be analyzed; and present an intermediate analysis interface in association with the analysis results and the at least a portion of the image, wherein the intermediate analysis interface presents corresponding image blocks and attributes of each detected object.

[0008] According to a second aspect of this disclosure, a method for analyzing and managing cervical images is provided. The method includes: acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of a subject as an image to be analyzed, by at least one processor; determining analysis results based on the image to be analyzed and using a learning network, by at least one processor; presenting at least a portion of the image to be analyzed, by at least one processor; and presenting an intermediate analysis interface in association with the analysis results and the at least a portion of the image, wherein the intermediate analysis interface presents corresponding image blocks and attributes of each detected object.

[0009] According to a third aspect of this disclosure, an apparatus for the analysis and management of cervical images is provided, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement a method for the analysis and management of cervical images.

[0010] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, wherein the computer program instructions, when executed by a processor, implement a method for the analysis and management of cervical images.

[0011] Using the apparatus, method, device, and computer-readable storage medium for cervical image analysis and management according to various embodiments of the present disclosure, at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject is acquired as an image to be analyzed; an analysis result is determined based on the image to be analyzed and using a learning network; at least a portion of the image to be analyzed is presented; and an intermediate analysis interface is presented in association with the analysis result and the at least a portion of the image, wherein the intermediate analysis interface presents corresponding image blocks and attributes of each detected object, and is capable of presenting the analysis result and the intermediate analysis interface associated with the analysis result, enabling doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects. Therefore, the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images is reduced, the accuracy, convenience, and user-friendliness of cervical image analysis and management are improved, and the quality of medical services is further enhanced. Attached Figure Description

[0012] In drawings that are not necessarily drawn to scale, the same reference numerals may describe similar parts in different views. The same reference numerals with or without letter suffixes may indicate different instances of similar parts. The drawings illustrate various embodiments generally by way of example rather than limitation, and are used, together with the description and claims, to explain the disclosed embodiments. Where appropriate, the same reference numerals are used in all drawings to refer to the same or similar parts. Such embodiments are illustrative and not intended to be exhaustive or exclusive embodiments of the apparatus or method.

[0013] Figure 1 A block diagram of an apparatus for the analysis and management of cervical images according to an embodiment of the present disclosure is shown.

[0014] Figure 2(a) shows a schematic diagram of at least a portion of the image to be analyzed and an intermediate analysis interface presented in an associated manner according to an embodiment of the present disclosure;

[0015] Figure 2(b) shows a schematic diagram of at least a portion of an image and a preview image displayed in a picture-in-picture manner according to an embodiment of the present disclosure;

[0016] Figure 3 A flowchart illustrating a method for analyzing and managing cervical images according to an embodiment of the present disclosure is shown;

[0017] Figure 4A flowchart illustrating another method for the analysis and management of cervical images according to an embodiment of the present disclosure is shown;

[0018] Figure 5 A flowchart illustrating another method for the analysis and management of cervical images according to an embodiment of the present disclosure is shown;

[0019] Figure 6 A flowchart illustrating another method for analyzing and managing cervical images according to an embodiment of the present disclosure; and

[0020] Figure 7 A structural block diagram of an apparatus for the analysis and management of cervical images according to an embodiment of the present disclosure is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions of this disclosure, the disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments. The embodiments of this disclosure will be further described in detail below with reference to the accompanying drawings and specific examples, but this is not intended to limit the disclosure. If there is no necessary sequential relationship between the various steps described herein, the order in which they are described as examples should not be considered a limitation. Those skilled in the art should understand that the order can be adjusted as long as it does not disrupt the logical coherence between them and render the entire process impossible.

[0022] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0023] Unless the context explicitly requires it, the words "comprising," "including," and similar terms throughout the specification and claims should be interpreted as encompassing rather than being exclusive or exhaustive; that is, meaning "including but not limited to."

[0024] In the description of this disclosure, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0025] The following will describe in detail, with reference to the accompanying drawings, an apparatus and method for the analysis and management of cervical images according to embodiments of the present disclosure.

[0026] Figure 1 A block diagram of an apparatus for the analysis and management of cervical images according to an embodiment of the present disclosure is shown. Figure 1 As shown, the device may include at least one processor 102.

[0027] Specifically, at least one processor 102 is configured to acquire at least one of the following: a liquid-based cytology image of the subject's cervix, an immunohistochemical image of cervical cells, and a histological image of the cervix, as the image to be analyzed. Based on the image to be analyzed, an analysis result is determined using a learning network. Further, at least one processor 102 presents at least a portion of the image to be analyzed and presents an intermediate analysis interface in association with the analysis result and the at least a portion of the image. The intermediate analysis interface presents corresponding image blocks and attributes of each detected object. An example of this association is shown in Figure 2(a), but it is merely an example, and this disclosure is not limited thereto. Doctors can simultaneously view the intermediate analysis interface and at least a portion of the image to be analyzed within the same user interface (screen) without opening different user interfaces or switching between multiple different user interfaces. Thus, verification can be conveniently performed based on the corresponding image blocks and attributes of the detected objects (presentation of the AI's initial screening results) and compared with the corresponding partial images (detailed presentation in the original slide image). Furthermore, the left side of Figure 2(a) can display at least a portion of the image to be analyzed, while the right side of Figure 2(a) can display single cells, clusters of cells, and blurred clusters as detected objects, along with corresponding image blocks and attributes such as low-level, high-level, and microbial. Doctors can edit the intermediate analysis interface based on the review results. For example, they can select and confirm the analysis of detected objects as image blocks with certain attributes, and save them so that they can proceed to the "next step" along with other saved image blocks and attributes of detected objects reviewed by the doctor, for example, but not limited to, generating an analysis report. Regardless of whether it is used to generate an analysis report, presenting the intermediate analysis interface in association with the at least a portion of the image within the same user interface reduces the operational difficulty for doctors in the analysis and management of cervical images, lowers the possibility of misdiagnosis / missed diagnosis, improves the accuracy, convenience, and user-friendliness of cervical image analysis and management, and further enhances the quality of medical services.

[0028] In some embodiments, the association between at least some images and the intermediate analysis interface also ensures that once a user edits either the images or the intermediate analysis interface, the other will automatically change accordingly. For example, a user can mark at least some images using editing tools, such as marking (e.g., outlining) the corresponding image blocks of manually identified objects, or manually entering the attributes of the corresponding image blocks. If the AI's initial screening results miss the corresponding image block, the corresponding image block of the manually identified object will be automatically added to the intermediate analysis interface. Furthermore, the attributes of the manually entered text for the corresponding image block can be processed using NLP to present the attributes of the added image block in the intermediate analysis interface. As another example, a user can discard the AI's initial screening results for image blocks with certain attributes in the intermediate analysis interface. Once the user provides manual attribute annotations for the corresponding image blocks on at least some images, both can be highlighted simultaneously (e.g., highlighted) to indicate the correlation between them, thereby precisely attracting the user's attention to both for comparison and more accurate verification results.

[0029] Here, at least one processor 102 can be a processing device that includes more than one general-purpose processing device, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, at least one processor 102 can be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor running other instruction sets, or a processor running a combination of instruction sets. At least one processor 102 can also be more than one special-purpose processing device, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a system-on-a-chip (SoC), etc. Furthermore, at least one processor 102 can also present a user interface to prompt the user to input settings for the structure of the learning network. For example, a list or menu of various learning network structures can be presented on the user interface for the user to select, and the learning network with the predetermined structure selected by the user is used in the subsequent analysis process.

[0030] Liquid-based cytology, also known as liquid-based thin-layer cytology, uses a liquid-based thin-layer cytology system to detect and classify cervical cells, making it the most advanced cervical cancer screening technology internationally. Compared to traditional Pap smears, liquid-based cytology significantly improves specimen quality and the detection rate of abnormal cervical cells. It can also detect some precancerous lesions and microbial infections such as fungi, trichomonas, viruses, and chlamydia, making it the most advanced technology for cervical cancer screening.

[0031] Immunohistochemistry, or immunohistochemistry, applies the fundamental principles of immunology—the antigen-antibody reaction, specifically the binding of antigens to antibodies. It uses a chemical reaction to develop the color of labeled antibody-containing chromogenic agents (fluorescein, enzymes, metal ions, isotopes) to identify antigens (peptides and proteins) within tissue cells. This allows for the localization, qualitative analysis, and relative quantification of these antigens. Cervical immunohistochemistry is used for further diagnostic purposes, including disease staging and classification.

[0032] Histology is the study of the fine structures and related functions of the normal human body. It is a branch of anatomy within medical science. Fine structures refer to structures that can only be clearly observed under a microscope. Images of normal fine structures obtained from histological studies are a necessary foundation for pathological histology. Only with a clear understanding of normal fine structures can pathological histology explore abnormal changes in these fine structures during disease processes.

[0033] Cervical liquid-based cytology images, cervical cell immunohistochemical images, and cervical histology images can be in formats such as "SVS", "ndpi", "Kfb", and "mrxs". Cervical cell immunohistochemical images and cervical histology images can be images obtained by staining against the same group of cancer-specific genes and / or antigens. Here, cancer-specific genes refer to genes specifically expressed or significantly overexpressed only in cancer cells, and cancer-specific antigens refer to neoantigens expressed only on the surface of certain cancer cells and not present on normal cells. It should be noted that cervical liquid-based cytology images, cervical cell immunohistochemical images, and cervical histology images can be images acquired in real-time from medical imaging devices such as microscopes and cameras via a communication interface, or they can be full-view digital pathological slide images acquired from a server; this disclosure does not limit this.

[0034] Here, the communication interface may include network adapters, cable connectors, serial connectors, USB connectors, parallel connectors, high-speed data transmission adapters (such as fiber optic, USB 3.0, Thunderbolt interfaces, etc.), wireless network adapters (such as WiFi adapters), telecommunications (such as 3G, 4G / LTE, etc.) adapters, etc. The server may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. This disclosure does not limit this aspect.

[0035] The learning network can be a deep learning (DL) network and has diverse analytical categories. Further, the learning network can include one or a combination of Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Recursive Neural Networks (RNNs). A CNN is a type of feedforward neural network (FNN) that includes convolutional computations and has a deep structure. CNNs have representation learning capabilities and can perform translation-invariant classification of input information according to their hierarchical structure. The convolutional layers of a CNN model can include at least one filter or kernel. More than one parameter of at least one filter (such as kernel weights, size, shape, and structure) can be determined, for example, through training processing based on backpropagation. A RNN is a type of recurrent neural network that takes sequential data as input, recursively processes the data in the direction of sequence evolution, and all nodes (recurrent units) are connected in a chain-like manner. A recurrent neural network is an artificial neural network (ANN) with a tree-like hierarchical structure where network nodes recursively process input information according to their connection order.

[0036] Furthermore, the deep learning network is trained by pre-setting its structure as a network model and defining a loss function. Here, deep learning is a type of machine learning (ML), which is an essential path to achieving artificial intelligence (AI). Deep learning discovers distributed feature representations of data by combining low-level features to form more abstract high-level representations of attribute categories or features. The network model can be trained using supervised learning. The architecture of the network model can include stacks of different blocks and layers, each transforming more than one input into more than one output. Examples of different layers can include more than one convolutional or fully convolutional layer, non-linear operator layers, pooling or subsampling layers, fully connected layers, and / or a final loss layer. Each layer can be connected to an upstream layer and a downstream layer. Network models may include Residual Network (ResNet) models, UNet models, AlexNet models, GoogLeNet models, Visual Geometry Group (VGG) models, Pyramid Scene Parsing Network (PSPNet) models, DeepLabV3 network models, etc., and this disclosure does not limit the types of models. A loss function is a function that maps the values ​​of a random event or its related random variables to non-negative real numbers to represent the "risk" or "loss" of that random event.

[0037] The analysis results can be binary analysis results of the analysis categories of the learning network, such as normal cells and abnormal cells, or negative cells and positive cells. Here, cell categories can include single cells and clusters of cells. Single cells can include one or more of low-grade squamous epithelial lesion cells, high-grade squamous epithelial lesion cells, microbial cells, metaplastic cells, endocervical cells, and inflammatory cells; clusters of cells can include one or more of low-grade squamous epithelial lesion cells, high-grade squamous epithelial lesion cells, adenocarcinoma cells, microbial cells, metaplastic cells, endocervical cells, and inflammatory cells. Furthermore, the analysis results can also include image satisfaction, inflammatory cell grade, and blurred clusters.

[0038] In some embodiments, the intermediate analysis interface refers to an interface that presents the corresponding image blocks and attributes of each detected object to the user based on the analysis results and at least a portion of the image to be analyzed. As shown in Figure 2(a), the intermediate analysis interface can present the corresponding image block labels and attribute labels of each detected object in a list format. By presenting the results in a list format, the user can simultaneously see the corresponding image blocks and attributes of each detected object and easily select or reject image blocks of various attributes detected by the AI. Specifically, the user can choose to approve (select) or reject (abandon) the AI ​​detection results of image blocks of various attributes. In some embodiments, a corresponding intermediate analysis interface is presented for each slice (or target region). In addition to the detected objects, slice-level evaluation results, such as "slice satisfaction evaluation," "inflammation level," "AI initial screening opinion," etc., can also be presented in the intermediate analysis interface for user reference and manual correction by the user.

[0039] For example, if a user is dissatisfied with the slice quality after comparing it with at least a portion of the image to be analyzed, the "Slice Satisfaction Evaluation" result can be changed from "Satisfied" to "Unsatisfied." In this case, the AI ​​initial screening analysis results corresponding to that intermediate analysis interface will be discarded and not included in further consideration. As another example, if the AI ​​initial screening's "Inflammation Level" is "None," but the user obtains different manual screening results, corresponding corrections can be made, and so on.

[0040] In some embodiments, the rows and columns of the list represent the physical morphology type and physiological level of each detected object, respectively. Check boxes are provided in association with each corresponding image block. Users can select the AI ​​detection result of the corresponding image block by checking the check box, and can reject and discard the AI ​​detection result of the corresponding image block by unchecking the check box.

[0041] Furthermore, the intermediate analysis interface can present blurred clusters as detected objects, which can serve as areas for doctors to focus on for review. The number of blurred clusters can be used as one of the parameters for image quality assessment.

[0042] The detected objects can be cells or tissues in the image. In cervical liquid-based cytology images, cervical liquid-based cells appear as discs and are reddish-blue in color; in cervical cell immunohistochemistry images, cervical cells appear as discs and are a slightly darker brownish color; in cervical histology images, cervical tissue has an irregular shape that is not disc-shaped. Therefore, cervical liquid-based cytology images and cervical cell immunohistochemistry images can be distinguished based on the color of cervical liquid-based cells in cervical liquid-based cytology images and the color of cervical cells in cervical cell immunohistochemistry images. Furthermore, cervical liquid-based cytology images and cervical cell immunohistochemistry images can be distinguished from cervical histology images based on the morphology of cervical liquid-based cytology cells in cervical liquid-based cytology images, the morphology of cervical cells in cervical cell immunohistochemistry images, and the morphology of cervical tissue in cervical histology images.

[0043] The apparatus for cervical image analysis and management according to embodiments of the present disclosure acquires at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of cervical tissue as an image to be analyzed; determines the analysis result based on the image to be analyzed and using a learning network; presents at least a portion of the image to be analyzed; and presents an intermediate analysis interface in association with the analysis result and the at least a portion of the image, wherein the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object, and is capable of presenting the analysis result and the intermediate analysis interface associated with the analysis result, enabling doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects. Therefore, it reduces the possibility of misdiagnosis / missed diagnosis in the process of cervical image analysis and management, improves the accuracy and convenience of cervical image analysis and management, and further enhances the quality of medical services.

[0044] In some embodiments, at least one processor 102 is further configured to: receive a first operation by a user to edit a target region in at least a portion of an image; and, upon receiving the first operation, present an intermediate analysis interface corresponding to the target region, such that the intermediate analysis interface presents corresponding image blocks and attributes of each detected object in the target region.

[0045] Specifically, upon receiving a first operation from a user to edit a target region in at least a portion of the image, at least one processor 102 switches the currently presented analysis state interface to an intermediate analysis interface corresponding to the target region. This presents the corresponding image blocks and attributes of each detected object within the target region to the user, enabling targeted editing of the target region. This improves the accuracy of cervical image analysis and management, saves time in cervical image analysis and management, and further enhances the quality of medical services. Here, the editing operation may include one or more of the following: click operation, add operation, modify operation, delete operation, outline operation, and association operation.

[0046] In some embodiments, at least one processor 102 is further configured to: receive a second operation by a user in an intermediate analysis interface to edit each detected object; and, upon receiving the second operation, adjust at least a portion of the image to present the corresponding image blocks and attributes of each detected object after editing.

[0047] Specifically, upon receiving a second operation from the user to edit each detected object in the intermediate analysis interface, at least one processor 102 adjusts at least a portion of the image to present the corresponding image blocks and attributes of each detected object after editing, that is, to make the adjusted image include all detected objects edited using the second operation along with their surrounding areas.

[0048] In some embodiments, at least one processor 102 is further configured to: mark each detected object in at least a portion of the image and present associated analysis results; receive a third operation by a user to edit the detected objects and / or associated analysis results; and, upon receiving the third operation, adjust an intermediate analysis interface to present the edited detected objects and / or associated analysis results.

[0049] Specifically, at least one processor 102 marks each detected object in at least a portion of the image and presents associated analysis results. Upon receiving a third operation from the user to edit the detected objects and / or associated analysis results, at least one processor 102 adjusts the intermediate analysis interface to present the edited detected objects and / or associated analysis results.

[0050] In some embodiments, at least one processor 102 is further configured to: present a surrounding image patch containing all detected objects along with surrounding regions presented by the intermediate analysis interface, and to treat the surrounding image patch as at least a partial image.

[0051] In some embodiments, the apparatus for analyzing and managing cervical images further includes: a receiving unit 104 configured to receive a fourth operation by a user confirming each intermediate analysis interface; and a generating unit 106 configured to generate an analysis report upon receiving the fourth operation for all intermediate analysis interfaces.

[0052] Specifically, the receiving unit 104 receives a fourth operation from the user confirming each intermediate analysis interface. Upon receiving the fourth operation for all intermediate analysis interfaces, the generation unit 106 generates an analysis report. This analysis report can be an independent report or a combined report, and this embodiment of the present disclosure does not impose any limitations on this. Here, an independent report may include an analysis report generated based on cervical liquid-based cytology images, an analysis report generated based on cervical cell immunohistochemistry images, and an analysis report generated based on cervical histology images; a combined report may be a report generated by fusing cervical liquid-based cytology images, cervical cell immunohistochemistry images, and cervical histology images.

[0053] In some embodiments, the apparatus for analyzing and managing cervical images further includes a display unit 108 configured to display, in a picture-in-picture manner, a preview image of the detected object in at least a portion of the image at a reduced scale.

[0054] Specifically, the display unit 108 can display at least a portion of the image and a preview image of the detected object in at least a portion of the image in a picture-in-picture manner, as shown in FIG2(b). Furthermore, upon receiving a user's click operation on any location in the preview image, the display unit 108 can automatically locate the corresponding location in at least a portion of the image based on that location, allowing the user to perform a comprehensive analysis by referring to the pathological conditions of the surrounding area at that location, thereby improving the accuracy of the analysis results for cervical image analysis and management. Here, the preview image can be an image of the detected object, such as cells or tissues, as shown in the upper left corner of FIG2(b); the at least a portion of the image can be the portion of FIG2(b) excluding the preview image.

[0055] Figure 3 A flowchart illustrating a method for analyzing and managing cervical images according to an embodiment of this disclosure is shown. Figure 3 As shown, the method for analyzing and managing cervical images may include acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as an image to be analyzed, using at least one processor (step 302). The method may also include determining analysis results based on the image to be analyzed and utilizing a learning network, using at least one processor (step 304). The method may further include presenting at least a portion of the image to be analyzed, using at least one processor (step 306). The method may further include presenting an intermediate analysis interface, associated with the analysis results and at least a portion of the image, using at least one processor, wherein the intermediate analysis interface presents corresponding image patches and attributes of each detected object (step 308).

[0056] The method for analyzing and managing cervical images according to embodiments of this disclosure involves acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as an image to be analyzed; determining the analysis result based on the image to be analyzed and utilizing a learning network; presenting at least a portion of the image to be analyzed; and presenting an intermediate analysis interface in association with the analysis result and the at least a portion of the image. The intermediate analysis interface presents corresponding image blocks and attributes of each detected object, enabling doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects. This reduces the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images, improves the accuracy and convenience of cervical image analysis and management, and further enhances the quality of medical services.

[0057] In some embodiments, at least one processor presents an intermediate analysis interface based on analysis results and associated with at least a portion of the images, including: receiving a first operation by a user to edit a target region in at least a portion of the images; and, upon receiving the first operation, presenting an intermediate analysis interface corresponding to the target region, such that the intermediate analysis interface presents corresponding image blocks and attributes of each detected object in the target region.

[0058] In some embodiments, at least one processor presents an intermediate analysis interface based on analysis results and in association with at least a portion of the images, including: at least one processor receiving a second operation from a user in the intermediate analysis interface to edit each detected object; and at least one processor, upon receiving the second operation, adjusting at least a portion of the images to present the corresponding image blocks and attributes of each detected object after editing.

[0059] In some embodiments, at least one processor presents an intermediate analysis interface based on analysis results and in association with at least a portion of the image, including: at least one processor marking each detected object in at least a portion of the image and presenting the associated analysis results; at least one processor receiving a third operation from a user to edit the detected objects and / or the associated analysis results; and at least one processor, upon receiving the third operation, adjusting the intermediate analysis interface to present the edited detected objects and / or the associated analysis results.

[0060] In some embodiments, editing operations include one or more of the following: click operation, add operation, modify operation, delete operation, highlight operation, and associate operation.

[0061] In some embodiments, at least one processor presents an intermediate analysis interface based on analysis results and associated with at least a portion of the image, including: presenting a peripheral image patch containing all detected objects presented by the intermediate analysis interface along with surrounding regions, and treating the peripheral image patch as at least a portion of the image.

[0062] In some embodiments, upon receiving a second operation, at least a portion of an image is adjusted by at least one processor to present the corresponding image blocks and attributes of each detected object after editing, including: at least a portion of the image is adjusted by at least one processor to include all detected objects edited using the second operation along with surrounding areas.

[0063] In some embodiments, the intermediate analysis interface presents the corresponding image patches and attributes of each detected object in a list format.

[0064] In some embodiments, the intermediate analysis interface presents fuzzy clusters as the detection targets.

[0065] In some embodiments, the rows and columns of the list represent the physical morphology type and physiological level of each detected object, respectively, and check boxes are provided in association with each corresponding image block.

[0066] In some embodiments, the method for analyzing and managing cervical images further includes: receiving a fourth operation from a user confirming each intermediate analysis interface by at least one processor; and generating an analysis report by at least one processor upon receiving the fourth operation for all intermediate analysis interfaces.

[0067] In some embodiments, the method for analyzing and managing cervical images further includes: displaying a preview image of at least a portion of the image in a picture-in-picture manner at a reduced scale.

[0068] Figure 4 A flowchart illustrating another method for the analysis and management of cervical images according to an embodiment of this disclosure is shown. Figure 4As shown, the method for analyzing and managing cervical images may include the following steps. The method begins with at least one processor acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as the image to be analyzed (step 402). The method may further include at least one processor determining the analysis result based on the image to be analyzed and utilizing a learning network (step 404). The method may further include at least one processor presenting at least a portion of the image to be analyzed (step 406). The method may further include at least one processor receiving a first operation from a user to edit a target region in at least one portion of the image (step 408). The method may further include at least one processor, upon receiving the first operation, presenting an intermediate analysis interface corresponding to the target region, such that the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the target region (step 410). The method may further include receiving a fourth operation from the user confirming each intermediate analysis interface (step 412). The method may further include generating an analysis report upon receiving the fourth operation on all intermediate analysis interfaces (step 414).

[0069] The method for analyzing and managing cervical images according to embodiments of this disclosure involves acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as an image to be analyzed; determining the analysis result based on the image to be analyzed using a learning network; presenting at least a portion of the image to be analyzed; receiving a first operation from a user to edit a target region in at least a portion of the image; upon receiving the first operation, presenting an intermediate analysis interface corresponding to the target region, such that the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the target region; receiving a fourth operation from the user to confirm each intermediate analysis interface; generating an analysis report upon receiving the fourth operation on all intermediate analysis interfaces; and displaying a preview image of at least a portion of the image in a picture-in-picture manner, which can present the analysis result and the intermediate analysis interface associated with the analysis result, presenting the corresponding image blocks and attributes of each detected object. This allows doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects, thus reducing the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images, improving the accuracy and convenience of cervical image analysis and management, and further enhancing the quality of medical services.

[0070] Figure 5 A flowchart illustrating another method for analyzing and managing cervical images according to an embodiment of this disclosure is shown. Figure 5As shown, the method for analyzing and managing cervical images may include the following steps. The method begins with at least one processor acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as the image to be analyzed (step 502). The method may further include at least one processor determining the analysis result based on the image to be analyzed and utilizing a learning network (step 504). The method may further include at least one processor presenting at least a portion of the image to be analyzed (step 506). The method may further include at least one processor receiving a second operation from a user editing individual detected objects in an intermediate analysis interface (step 508). The method may further include at least one processor adjusting at least a portion of the image upon receiving the second operation to present the corresponding image blocks and attributes of each detected object after editing (step 510). The method may further include receiving a fourth operation from a user confirming each intermediate analysis interface (step 512). The method may further include generating an analysis report upon receiving the fourth operation on all intermediate analysis interfaces (step 514).

[0071] The method for analyzing and managing cervical images according to embodiments of this disclosure involves acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as an image to be analyzed; determining the analysis result based on the image to be analyzed and utilizing a learning network; presenting at least a portion of the image to be analyzed; receiving a second operation from a user in an intermediate analysis interface to edit each detected object; adjusting at least a portion of the image to present the corresponding image blocks and attributes of each detected object after editing; receiving a fourth operation from the user to confirm each intermediate analysis interface; generating an analysis report upon receiving the fourth operation on all intermediate analysis interfaces; and displaying a preview image of at least a portion of the image in a picture-in-picture manner, which can present the analysis result and the intermediate analysis interface associated with the analysis result, presenting the corresponding image blocks and attributes of each detected object. This allows doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects, thus reducing the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images, improving the accuracy and convenience of cervical image analysis and management, and further enhancing the quality of medical services.

[0072] Figure 6 A flowchart illustrating another method for analyzing and managing cervical images according to an embodiment of this disclosure is shown. Figure 6As shown, the method for analyzing and managing cervical images may include the following steps. The method begins with at least one processor acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as the image to be analyzed (step 602). The method may further include at least one processor determining the analysis results based on the image to be analyzed and utilizing a learning network (step 604). The method may further include at least one processor presenting at least a portion of the image to be analyzed (step 606). The method may further include at least one processor marking each detected object in at least a portion of the image and presenting the associated analysis results (step 608). The method may further include at least one processor receiving a third operation from a user to edit the detected objects and / or the associated analysis results (step 610). The method may further include at least one processor, upon receiving the third operation, adjusting an intermediate analysis interface to present the edited detected objects and / or the associated analysis results (step 612). The method may further include a fourth operation receiving confirmation from a user of each intermediate analysis interface (step 614). The method may also include generating an analysis report (step 616) upon receiving a fourth operation on all intermediate analysis interfaces.

[0073] The method for analyzing and managing cervical images according to embodiments of this disclosure involves acquiring at least one of a liquid-based cytology image, an immunohistochemical image of cervical cells, and a histological image of the cervix of a subject as an image to be analyzed; determining analysis results based on the image to be analyzed and utilizing a learning network; presenting at least a portion of the image to be analyzed; marking each detected object in the at least a portion of the image and presenting the associated analysis results; receiving a third operation from the user to edit the detected objects and / or the associated analysis results; upon receiving the third operation, adjusting the intermediate analysis interface to present the edited detected objects and / or the associated analysis results; and receiving user comments on each... The fourth operation involves confirming the results on all intermediate analysis interfaces; generating an analysis report upon receiving the fourth operation on all intermediate analysis interfaces; displaying a preview image of at least a portion of the images in a picture-in-picture manner at a reduced size; presenting the analysis results and the corresponding image blocks and attributes of each detected object associated with those results on the intermediate analysis interfaces; enabling doctors to make correct diagnoses based on the corresponding image blocks and attributes of the detected objects; thus reducing the possibility of misdiagnosis / missed diagnosis during the analysis and management of cervical images, improving the accuracy and convenience of cervical image analysis and management, and further enhancing the quality of medical services.

[0074] Figure 7 A structural block diagram of an apparatus for the analysis and management of cervical images according to an embodiment of the present disclosure is shown. Figure 7As shown, the device for analyzing and managing cervical images is a general-purpose data processing device, including a general-purpose computer hardware structure. This device includes at least a processor 702 and a memory 704. The processor 702 and the memory 704 are connected via a bus 706. The memory 704 is adapted to store instructions or programs executable by the processor 702. The processor 702 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 702 executes the commands stored in the memory 704, thereby performing the method flow described above in this embodiment of the present disclosure to process data and control other devices. The bus 706 connects the aforementioned components together, and also connects these components to a display controller 708, a display device, and an input / output (I / O) device 710. The input / output (I / O) device 710 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output (I / O) device 710 is connected to the system via the input / output (I / O) controller 712.

[0075] The memory 704 can store software components, such as an operating system, a communication module, an interaction module, and application programs. Each of the modules and application programs described above corresponds to a set of executable program instructions that perform one or more functions and the methods described in the embodiments of the invention.

[0076] In some embodiments, the device for analyzing and managing cervical images can be located in one place, distributed in multiple locations, or be a distributed device, such as one located in the cloud; this disclosure does not impose any limitations on this. Accordingly, the display for presenting the results of the analysis and management of cervical images can be located locally or remotely on the device for analyzing and managing cervical images; this is not limited thereto.

[0077] The flowcharts and / or block diagrams of methods, systems, and computer program products according to embodiments of this disclosure describe various aspects of this disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions (executed via the processor of the computer or other programmable data processing apparatus) create means for implementing the functions / actions specified in the flowchart and / or block diagram blocks or blocks.

[0078] Furthermore, as those skilled in the art will recognize, various aspects of the embodiments of this disclosure can be implemented as a system, method, or computer program product. Therefore, various aspects of the embodiments of this disclosure can take the form of a completely hardware implementation, a completely software implementation (including firmware, resident software, microcode, etc.), or an implementation combining software and hardware aspects, which may generally be referred to herein as a "circuit," "module," or "system." Additionally, aspects of this disclosure can take the form of a computer program product implemented in one or more computer-readable media having computer-readable program code implemented thereon.

[0079] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, (but not limited to) an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination thereof. More specific examples (not an exhaustive list) of computer-readable storage media will include: an electrical connection having one or more wires, a portable computer floppy disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the context of embodiments of this disclosure, a computer-readable storage medium can be any tangible medium capable of containing or storing a program used by or in conjunction with an instruction execution system, device, or apparatus.

[0080] Computer-readable signal media may include propagated data signals having computer-readable program code implemented therein, such as in baseband or as part of a carrier wave. Such propagated signals may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and can communicate, propagate, or transmit a program used by or in conjunction with an instruction execution system, device, or apparatus.

[0081] Program code implemented on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, or any suitable combination thereof.

[0082] Computer program code used to perform operations relating to the aspects of this disclosure may be written in any combination of one or more programming languages, including: object-oriented programming languages ​​such as Java, Smalltalk, C++, PHP, Python, etc.; and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may be executed as a standalone software package entirely on the user's computer, partially on the user's computer, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, 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 provided by an Internet service provider).

[0083] These computer program instructions may also be stored in a computer-readable medium that can direct a computer, other programmable data processing apparatus or other means to operate in a particular manner, such that the instructions stored in the computer-readable medium produce an article of writing that includes instructions that implement the functions / actions specified in flowchart and / or block diagram blocks or blocks.

[0084] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operable steps to be performed on the computer, other programmable apparatus or other device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide for implementing the functions / actions specified in flowchart and / or block diagram blocks or blocks.

[0085] Furthermore, although exemplary embodiments have been described herein, their scope includes any and all embodiments based on this disclosure that have equivalent elements, modifications, omissions, combinations (e.g., schemes involving intersections of various embodiments), adaptations, or alterations. Elements in the claims will be interpreted broadly based on the language used in the claims and are not limited to the examples described in this specification or during the implementation of this application, and such examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered illustrative only, and the true scope and spirit are indicated by the full scope of the following claims and their equivalents.

[0086] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more thereof) can be used in combination with each other. Other embodiments may be used by those skilled in the art upon reading the above description. Furthermore, in the above detailed description, various features may be grouped together to simplify this disclosure. This should not be construed as an intention that a disclosed feature, which is not claimed, is necessary for any claim. Rather, the subject matter of the invention may be less than all the features of a particular disclosed embodiment. Thus, the following claims are incorporated herein by reference as examples or embodiments, wherein each claim is independently considered as a separate embodiment, and these embodiments are contemplated as being possible in various combinations or arrangements. The scope of the invention should be determined by reference to the appended claims and the full scope of their equivalents.

Claims

1. A device for analyzing and managing cervical images, characterized in that, The device includes at least one processor, the at least one processor being configured to: At least one of the subject’s cervical liquid-based cytology image, cervical cell immunohistochemistry image, and cervical histology image is obtained as the image to be analyzed. The analysis results are determined based on the image to be analyzed and using a learning network. Based on the analysis results, at least a portion of the images to be analyzed are presented separately in association with an intermediate analysis interface. The intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the at least a portion of the images in a table. The rows and columns of the table represent the physiological level and physical morphology type of each detected object as the attributes. When one of the at least partial images and the intermediate analysis interface is edited, causing a corresponding change in the other includes: in response to a user-identified missed detection object marking operation in the at least partial images that is not presented in the intermediate analysis interface, automatically adding the corresponding image block of the missed detection object to the intermediate analysis interface, and presenting the attributes of the added image block of the missed detection object in the intermediate analysis interface; allowing the user to discard image blocks with specific attributes in the intermediate analysis interface; and, when the user provides manual annotation of attributes for the image block corresponding to the detected object in at least partial images, and the user wants to discard the image block with that attribute in the intermediate analysis interface, linking and highlighting the two together.

2. The apparatus according to claim 1, characterized in that, The physical morphology type includes fuzzy clusters.

3. The apparatus according to claim 1, characterized in that, At least a portion of the image to be analyzed is presented separately from the intermediate analysis interface in the same frame.

4. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to: When at least a portion of the image and the intermediate analysis interface are edited, the other side undergoes a corresponding change.

5. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to receive a user's review operation.

6. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to generate an analysis report using the analysis results reviewed by the user.

7. The apparatus according to claim 1, characterized in that, The at least one processor is further configured such that the intermediate analysis interface also provides checkboxes in a table associated with each corresponding image patch. Receive user's check or decheck operation on the selected box; If a checkbox is received, the analysis result of the image block is selected; if a decheckbox is received, the analysis result of the image block is rejected.

8. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to: Receive a first operation from the user to edit a target region in at least a portion of the image; Upon receiving the first operation, an intermediate analysis interface corresponding to the target region is presented, such that the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the target region.

9. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to: Receive a second operation from the user in the intermediate analysis interface to edit each detected object; Upon receiving the second operation, the at least part of the image is adjusted to present the corresponding image blocks and attributes of each detected object after editing.

10. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to: Each detected object is marked in at least a portion of the image and the associated analysis results are presented; The third operation receives user edits of detected objects and / or associated analysis results; Upon receiving the third operation, the intermediate analysis interface is adjusted to present the edited detected objects and / or associated analysis results.

11. The apparatus according to any one of claims 8 to 10, characterized in that, The editing operations include one or more of the following: click operation, add operation, modify operation, delete operation, highlight operation, and associate operation.

12. The apparatus according to claim 1, characterized in that, The at least one processor is further configured to: The system presents a surrounding image patch containing all detected objects along with their surrounding areas as presented by the intermediate analysis interface, and uses the surrounding image patch as the at least partial image.

13. The apparatus according to claim 9, characterized in that, The at least one processor is further configured to: Adjust the at least part of the image to include all detected objects along with their surrounding areas after editing using the second operation.

14. The apparatus according to any one of claims 1 to 10, characterized in that, The device further includes: The receiving unit is configured to receive the fourth operation from the user's confirmation of each intermediate analysis interface; The generation unit is configured to generate an analysis report upon receiving a fourth operation on all intermediate analysis interfaces.

15. The apparatus according to any one of claims 1 to 10, characterized in that, The device further includes: The display unit is configured to display a preview image of the detected object in the at least part of the image in a picture-in-picture manner at a reduced size.

16. A method for analyzing and managing cervical images, characterized in that, The method includes: At least one processor acquires at least one of the following images of the subject's cervix: liquid-based cytology image, cervical cell immunohistochemistry image, and cervical histology image, as the image to be analyzed. The at least one processor determines the analysis result based on the image to be analyzed and using a learning network. Based on the analysis results, the at least one processor separately presents at least a portion of the image to be analyzed in association with an intermediate analysis interface, wherein the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the at least a portion of the image in a table, and the rows and columns of the table represent the physiological level and physical morphology type of each detected object as the attributes, respectively. When one of the at least partial images and the intermediate analysis interface is edited, causing a corresponding change in the other includes: in response to a user-identified missed detection object marking operation in the at least partial images that is not presented in the intermediate analysis interface, automatically adding the corresponding image block of the missed detection object to the intermediate analysis interface, and presenting the attributes of the added image block of the missed detection object in the intermediate analysis interface; allowing the user to discard image blocks with specific attributes in the intermediate analysis interface; and, when the user provides manual annotation of attributes for the image block corresponding to the detected object in at least partial images, and the user wants to discard the image block with that attribute in the intermediate analysis interface, linking and highlighting the two together.

17. The method according to claim 16, characterized in that, The physical morphology type includes fuzzy clusters.

18. The method according to claim 16, characterized in that, At least a portion of the image to be analyzed is presented separately from the intermediate analysis interface in the same frame.

19. The method according to claim 16, characterized in that, The at least one processor is further configured to: When at least a portion of the image and the intermediate analysis interface are edited, the other side undergoes a corresponding change.

20. The method according to claim 16, characterized in that, The at least one processor is further configured to receive a user's review operation.

21. The method according to claim 16, characterized in that, The at least one processor is further configured to generate an analysis report using the analysis results reviewed by the user.

22. The method according to claim 16, characterized in that, The at least one processor is further configured such that the intermediate analysis interface also provides checkboxes in a table associated with each corresponding image patch. Receive user's check or decheck operation on the selected box; If a checkbox is received, the analysis result of the image block is selected; if a decheckbox is received, the analysis result of the image block is rejected.

23. The method according to claim 16, characterized in that, The presentation of an intermediate analysis interface by the at least one processor, based on the analysis results and in association with the at least partial image, includes: The at least one processor receives a first operation from the user to edit a target region in the at least part of the image; Upon receiving the first operation, the at least one processor presents an intermediate analysis interface corresponding to the target region, such that the intermediate analysis interface presents the corresponding image blocks and attributes of each detected object in the target region.

24. The method according to claim 16, characterized in that, The presentation of an intermediate analysis interface by the at least one processor, based on the analysis results and in association with the at least partial image, includes: The at least one processor receives a second operation from the user in the intermediate analysis interface to edit each detected object; Upon receiving the second operation, the at least one processor adjusts the at least part of the image to present the corresponding image blocks and attributes of each detected object after editing.

25. The method according to claim 16, characterized in that, The presentation of an intermediate analysis interface by the at least one processor, based on the analysis results and in association with the at least partial image, includes: The at least one processor marks each detected object in the at least part of the image and presents the associated analysis results; The at least one processor receives a third operation from the user to edit the detected objects and / or associated analysis results; Upon receiving the third operation, the at least one processor adjusts the intermediate analysis interface to present the edited detected objects and / or associated analysis results.

26. The method according to any one of claims 23 to 25, characterized in that, The editing operations include one or more of the following: click operation, add operation, modify operation, delete operation, highlight operation, and associate operation.

27. The method according to claim 16, characterized in that, The presentation of an intermediate analysis interface by the at least one processor, based on the analysis results and in association with the at least partial image, includes: The at least one processor presents a surrounding image patch containing all detected objects along with their surrounding areas as presented by the intermediate analysis interface, and uses the surrounding image patch as the at least partial image.

28. The method according to claim 24, characterized in that, The step of adjusting at least a portion of the image by the at least one processor upon receiving the second operation to present the edited corresponding image blocks and attributes of each detected object includes: The at least one processor adjusts the at least part of the image to include all detected objects along with their surrounding areas, as edited using the second operation.

29. The method according to any one of claims 16 to 25, characterized in that, The method further includes: The fourth step is to receive confirmation from the user for each intermediate analysis interface; Upon receiving the fourth operation on all intermediate analysis interfaces, an analysis report is generated.

30. The method according to any one of claims 16 to 25, characterized in that, The method further includes: A preview image of the detected object in at least a portion of the image is displayed in a picture-in-picture manner at a reduced size.

31. An apparatus for analyzing and managing cervical images, comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to perform the operations performed by the method for analysis and management of cervical images as described in any one of claims 16 to 30.

32. A computer storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, they perform the operations carried out by the method for analyzing and managing cervical images as described in any one of claims 16 to 30.

Images