208 results about "Pathological" patented technology

The invention discloses a glioma T cell prediction and prognosis evaluation method based on pathological images, particularly relates to the field of patient prognosis health evaluation, and aims to solve the problems that existing pathological evaluation is difficult to combine with tumor structure heterogeneity and immune infiltration distribution, and the future progress risk of a patient cannot be predicted based on follow-up visit pathological data. A spatial heterogeneity map of a tumor core area and an invasion edge is constructed in a digital pathological section, density gradients of T cells in different areas are calculated to generate a distribution heterogeneity coefficient, interaction processing is performed on the two types of characteristics in combination with historical follow-up visit records, and a time sequence neural network constructed based on a gating structure is combined to obtain a high-efficiency characteristic of the tumor. And outputting disease progress probabilities of a plurality of follow-up visit time points in the future to form a prognosis trajectory prediction curve, calculating a quantitative recurrence risk score according to curve slope change and an immune fluctuation mode, and finally generating an individualized management scheme, thereby realizing quantitative prediction evaluation and risk management of the prognosis trend of the glioma patient.

The invention provides a patient pathological data analysis and evaluation method for clinical nursing, and relates to the technical field of nursing informatization. Comprising the steps of collecting biochemical and pathological data of a patient and standardizing units and reference values, analyzing the dynamic trend of detection values and classifying change directions and amplitudes, matching pathological labels and establishing association with nursing items, comparing differences between nursing records and the pathological data and establishing a transverse index relationship, and judging whether the nursing task difference exceeds a threshold value or not and adjusting a nursing path generation scheme. By integrating multi-source pathological data and standardizing units and reference intervals, data consistency and comparability are ensured, the index fluctuation trend is dynamically tracked, the change direction and amplitude are quantitatively analyzed, disease course evolution is accurately captured, direct mapping between pathological categories and nursing items is established, logic binding is clear, intervention precision is improved, and the method is suitable for clinical application. Differences between nursing records and pathological data are transversely compared, nursing dynamic adaptation is optimized, a path scheme is rapidly adjusted through threshold judgment, and the lagging or misjudgment risk is reduced.

The invention discloses an auxiliary film reading method and system based on artificial intelligence, and the method comprises the steps: 1, collecting a pathological WSI, an electronic medical record, detection data and equipment parameters, correcting the equipment difference through adaptive dyeing normalization, and constructing a structured data package associated with an ID-timestamp of a patient; 2, developing a dynamic branch CNN, migrating teacher model knowledge through knowledge distillation, and introducing federated learning; step 3, the edge generates a thermodynamic diagram to mark a suspicious area, and the cloud outputs a structured report; step 4, constructing a normal tissue feature space by the variational auto-encoder, detecting abnormal slices and triggering expert re-checking; a reverse automatic encoder generates a pseudo-health image to compare and position a pathological area, and dynamic weight adjustment balances the federal learning convergence speed; 5, integrating the thermodynamic diagram, the gene data and the clinical indexes by a three-dimensional platform, and supporting multi-dimensional superposition display; webGL realizes browser end rendering, and NLP automatically generates a report abstract marked with a key evidence chain and is in butt joint with an international diagnosis and treatment guide.

The invention provides a medical examination data analysis system and method based on artificial intelligence. The method comprises the steps of obtaining a time sequence data matrix of multiple examination indexes of a target patient at different time nodes through medical examination data of the target patient; labeling pathological labels of various examination indexes in the medical examination data, and determining medical semantic association features among different examination indexes of the target patient through the pathological labels; according to the medical semantic association features and the time sequence data matrix, determining a time sequence association relationship of different inspection indexes of the target patient on a pathological level, and generating a fusion feature vector of the health state of the target patient according to the time sequence association relationship; and an abnormal evolution feature of the current health state of the target patient is obtained by combining an abnormal detection model with the fusion feature vector, and then an auxiliary analysis result of the pathological risk of the target patient is output to medical personnel. By adopting the scheme of the invention, the dynamic change trend analysis of the disease course risk state of the patient can be realized based on the medical semantic perception ability.

The invention relates to the technical field of medical big data analysis and intelligent monitoring, in particular to a medical time series data anomaly detection system which comprises a multi-modal data fusion module used for obtaining a physiological sensor data stream of a target object, performing multi-source heterogeneous synchronization and tensor coding on the physiological sensor data stream, and obtaining a multi-modal data fusion result; constructing a multi-modal physiological time sequence tensor; and the phase-space reconstruction module is used for performing high-dimensional dynamic mapping on the multi-modal physiological time sequence tensor. The one-dimensional time sequence signals are mapped to the high-dimensional Euclidean space through the phase-space reconstruction module, the dynamic manifold structure of the physiological system is restored, abnormity is recognized by detecting the morphological variation of attractor tracks in the high-dimensional space, and even if the physiological parameters do not reach the alarm threshold value in numerical value, the abnormity is recognized. As long as an internal nonlinear dynamic structure is changed, the system can carry out sensitive capture, so that the problem that a traditional system misses detection of early-stage hidden pathological features is effectively solved.

The invention relates to the field of man-machine interaction, and particularly discloses a multi-mode man-machine interaction application system for sky-eye insight based on a pathologist visual angle, which is characterized in that firstly, a candidate focus thermodynamic diagram is generated through rapid scanning of a full-slice image, low-power lens global browsing of a doctor is simulated, and the doctor is guided to lock a key area interactively through professional judgment; therefore, the processing efficiency of the oversized image is greatly improved. And then, the system only performs high-resolution deep analysis on the focus confirmed by the doctor, and performs multi-modal fusion on the extracted microscopic visual features and the patient text information to generate a preliminary report with an interpretable basis, so that the problem that the multi-modal function deviates from a clinical core task is solved. Finally, the doctor can check and finalize the report through visual interaction, and the dominant position and the final decision making right of the doctor in the diagnosis process are ensured, so that the bottlenecks of black box operation and low clinical acceptability of a traditional AI system are overcome.

The invention discloses a medical question-answering method, device, equipment and program product, and is applied to the technical field of medical question-answering. The method comprises the following steps: acquiring a disease image and disease chief complaint information; performing feature extraction on the disease image and the disease chief complaint information to obtain pathological visual features and chief complaint text features; performing feature fusion on the pathological visual features and the chief complaint text features to obtain target fusion features; determining a dynamic cue word template based on the information type of the target fusion feature; and inputting the dynamic cue word template and the disease image into a preset large language model, and generating a medical question and answer result by the large language model. According to the method, a complete, dynamic and adaptive cue word template is generated according to the consistency or conflict fuzziness embodied by the multi-modal information, so that the dynamic cue word template can further put forward a more complex task with question and answer guidance to a large language model, the pertinence and depth of medical question and answer are improved, and the medical question and answer efficiency is improved. And the precision of medical questions and answers is effectively improved.

The invention relates to a pathological section intelligent auxiliary differential diagnosis system based on multi-modal fusion, in particular to the field of clinical pathology, semantic unification of multi-modal data is achieved through meta-task construction and a cross-modal alignment technology, and transferable diagnostic knowledge is extracted by utilizing a meta-learning framework; the method combines a generative model and knowledge constraints to generate high-quality synthetic data, and finally fuses real and synthetic samples through a self-adaptive diagnosis mechanism, thereby remarkably improving the differential diagnosis capability of rare lesions, effectively solving the problem of model generalization in a training data scarcity scene, and improving the accuracy of model identification. And efficient and reliable intelligent auxiliary decision support is provided for clinical pathological diagnosis.

The invention relates to the technical field of medical information, in particular to a multi-source data health intervention method, which comprises the following steps: firstly, acquiring texts, vital signs, image vectors and wearable signals, generating a unified vector through multi-modal coding, and extracting a topological life vector; constructing a spiking neuro-causal diagram based on a unified vector, and injecting a life vector as an external field into a Sheng differential equation to generate a dynamic pathological manifold; compressing the manifold into a tensor network state, constructing a quantum optimization model in combination with a causal diagram, minimizing energy expectation and topological risk to obtain an optimal intervention sequence, and reinjecting a target gradient to adjust the manifold in real time; after the sequence is subjected to clinical logic verification, a commitment value and a zero-knowledge proof are generated and written into a Byzantine account book, and meanwhile a control instruction is issued to an execution terminal. According to the method, millisecond-level decision making is achieved, the false alarm rate is reduced, and chain traceability is provided.

The invention relates to the technical field of disease diagnosis, in particular to a digital pathological section diagnosis method based on a link algorithm, and the method comprises the following steps: creating a tissue; creating a link algorithm; marking the digital pathological section data; checking the digital pathological section data; corresponding parameters are set for a link algorithm, and training is carried out; if the training effect of the link algorithm meets the requirement, cascading a new module, and if the training effect of the link algorithm does not meet the requirement, continuing to enrich the data set until the requirement is met; and after the whole link algorithm is trained, exporting a trained model, and reasoning the digital pathological section by using the model. According to the method, a link algorithm is created, so that operators influencing the reasoning speed and memory occupation are removed while the precision is kept; by creating a link algorithm, a user can train a data set in a highly self-defined manner in combination with various downstream tasks so as to generate a model meeting own requirements.

The invention discloses a double-domain RAG-driven multi-omics fusion pathology analysis system, and belongs to the technical field of artificial intelligence of medical data. Pathology image feature data and structured multi-omics data of a patient are fused in a semantic layer through a multi-modal fusion module, a semantic layer fusion result is obtained, and a comprehensive representation vector of the patient is generated; the double-domain retrieval module obtains internal reference evidence corresponding to a hospital case knowledge base and external reference evidence corresponding to an external medical literature knowledge base; the consistency gating fusion module analyzes the consistency of the internal reference evidence and the external reference evidence, and fuses the internal reference evidence and the external reference evidence to obtain a fused credible evidence; and the report generation module generates a medical auxiliary report with an evidence chain based on a large language model according to the semantic layer fusion result and the credible evidence. According to the embodiment of the invention, the interpretability and credibility of the diagnosis conclusion can be enhanced.

The invention provides a pathological section human-like reading track generation method based on reinforcement learning. The method comprises the following steps: constructing a training data set; the training data set comprises a plurality of WSIs and corresponding doctor film reading track data; an RL frame is built, and parameters of the built RL frame are initialized; wSI local image features and a WSI current film reading state are taken as a state S, position movement in eight directions and a preset fixed step length is taken as an action A, and a pathological expectation value output by a PEAN model is taken as a reward R; and training a PEAN model agent based on the deep reinforcement learning Q network and a sequence of the state S, the action A, the reward R and the next state S stored in the experience playback pool to realize iterative optimization of the deep reinforcement learning Q network so as to finally generate a human-like film reading track of which the coincidence degree with the doctor film reading track is greater than or equal to a preset coincidence degree. According to the method, the macroscopic and microcosmic film reading logic of a doctor is reproduced, and the WSI diagnosis efficiency is greatly improved.

The invention relates to the technical field of medical image diagnosis, and discloses a radiation-pathological diagnosis evaluation method based on weak supervision cross-modal deep fusion. The method comprises the following steps: receiving case-level radiation image data and pathological section data, combining with a weak supervision consistency label, realizing cross-modal semantic alignment through a double-branch feature extraction network, and generating aligned radiation feature vectors and pathological feature vectors; based on the aligned feature vector, a cross-modal attention fusion mechanism is adopted to complete deep fusion, and a fusion feature vector is obtained; a consistency evaluation task is executed based on a multi-task learning framework, and a consistency classification result, an inconsistency attribution result and a risk area positioning result are output; and based on the evaluation result, generating a visual diagnosis report through an interpretability analysis model. According to the method, cross-modal data can be effectively fused under a weak supervision condition, the accuracy and interpretability of diagnosis consistency evaluation are improved, and clinical data annotation requirements are met.

The invention discloses an intraocular light field simulation method and system based on physiological constraint and pathology traceability, the system takes a Physics Informed Kolmogorov-Arnold Net (PI-KAN) network as a core, namely physical information KAN, the method comprises the following steps: obtaining personalized parameters of eyeballs; 5-dimensional light field parameters including space, wavelength and time are input into a pre-trained PI-KAN model for light field solving, a three-layer network architecture including an input layer, a hidden layer and an output layer is established, a physical information edge function is constructed, and training is performed through fusion of a Helmholtz equation and a loss function of boundary conditions; generating an OCT image based on the light field solved by simulation; by analyzing side function mapping, visualization and pathological traceability of a light field propagation physical mechanism are realized. According to the method, the sparsity and interpretability of PI-KAN are utilized, the problems that a traditional method is low in calculation efficiency, difficult in high-dimensional modeling, weak in physical constraint and poor in interpretability are solved, millisecond-level, high-precision and interpretable simulation of the eye light field is achieved, and the method is suitable for ophthalmic clinical auxiliary diagnosis, surgical planning and equipment optimization.

The invention discloses an intelligent insurance underwriting method. Insurance requirements, health notification information and multi-mode physical examination data of a user are obtained through a dialogue interaction interface; extracting text physiological indexes by adopting a named entity recognition technology, analyzing medical images through a visual language model to generate pathological descriptions, and mapping the pathological descriptions into standard medical term codes; performing preliminary screening based on a decision tree rule engine, and calculating a deviation degree of health indexes and terms in combination with a disease correlation model to screen candidate products; constructing a hierarchical cue word template to drive the large language model to execute clause semantic analysis, and outputting a structured underwriting conclusion; and generating a product recommendation sequence by using a weighted scoring model, or triggering a difference comparison description. Through multi-modal data fusion, dynamic deviation calculation and an anti-factual reasoning mechanism, the problems that unstructured data is difficult to process and clause matching is rigid in traditional underwriting are solved, the underwriting accuracy is effectively improved, the decision-making efficiency is remarkably improved, real-time synchronous updating of supervision clauses is supported, and the compliance risk is remarkably reduced.

The invention discloses a cardiovascular risk early warning method based on multi-modal time sequence data, relates to the technical field of medical health information monitoring, and aims to solve the problem of confusion of causes of dyspnea at night by constructing a cross-modal direction and time delay relation in a sliding time window. Phenotype similar phenomena such as pure blood oxygen reduction / wake-up are decomposed into a comparable time sequence interaction structure, so that a blocking chain type process and a non-blocking type heart failure related process can be distinguished on the structural level, and therefore false alarm and missing alarm caused by confusion are reduced. Meanwhile, a multi-channel signal is firstly converted into a time sequence causal diagram, and then in-window statistical characteristics are combined for judgment, so that the model not only utilizes the self change of each channel, but also utilizes the interaction evidence of the first and second channels, the influence direction and the delay length, and the expression ability of the pathophysiological chain difference is improved.

The invention discloses a myocardial transmembrane potential segmented time sequence reconstruction method based on a physical information neural network, and the method improves the model generalization ability: a physical information data generation step, especially a diversified generation strategy, can create large-scale training data covering wide physiological and pathological states, and improves the model generalization ability. According to the method, a deep learning model can learn robustness characterization of various complex electrocardio phenomena, and the generalization ability of the model and the applicability of the model in a real scene are greatly improved. According to the composite loss function, especially a physical consistency loss item, the physical law describing propagation of an electric signal from the heart to the body surface serves as a soft constraint to be embedded into the training process, a solution output by a forcing network must be capable of'explaining 'observed body surface potential BSP data, and the BSP data can be used as a soft constraint. The method greatly reduces the understanding space, and effectively inhibits the generation of artifacts and wrong solutions which do not accord with physical laws.

The invention discloses a perioperative period risk prediction and intervention method and system based on multi-modal data fusion, and relates to the technical field of medical artificial intelligence, and the method comprises the following steps: S100, building a data collection mechanism, obtaining perioperative period related data from a plurality of medical information systems, the data comprises structured examination indexes, text medical history records, medical image report conclusions and pathological diagnosis results. According to the method, the high-dimensional feature vector is constructed by fusing the structured test data, the text medical history, the image conclusion and the pathological result, and the quantitative prediction of the postoperative complications is realized in combination with the trained risk prediction model; the system can automatically generate a natural language interpretation and personalized intervention plan, and an electronic medical record is embedded, so that closed-loop management of risk identification, cause interpretation and intervention execution is realized, the intelligent, standardized and personalized level of perioperative period management is improved, and the occurrence rate of complications is remarkably reduced.

The invention provides a hierarchical multi-modal heart data completion method based on double knowledge guidance, which comprises the following steps: S1, extracting complete multi-modal joint features from complete multi-modal data through a teacher network, and carrying out cross-sample comparative learning and dynamic feature fusion on missing modal data through a student network to obtain a multi-modal data fusion model; generating completion features containing individual specific information; s2, based on the completion features, constructing a category prototype vector of the heart disease subtype, and generating semantic constraints representing disease subtype rules through prototype perception comparison distillation and moving average evolutionary strategies; s3, the complementation features and the semantic constraints are combined, network parameters and prototype vectors are optimized through back propagation iteration, complementation data are generated, and the complementation data comprise individual electrophysiological features and pathological subtype marks. By adopting the method, the individual specificity and the pathological evolution rule can be considered, and the reconstruction data can be ensured to meet the accurate heart disease diagnosis requirement at the same time.

The invention relates to a pathological full-slice image classification method based on multi-branch independent mask and Dirichlet evidence fusion, and belongs to the crossing field of biological information and artificial intelligence. Aiming at the problems of excessive attention concentration and static fusion defects of a traditional multi-instance learning method in a weak supervision classification task of a pathological full-slice image, dynamic mask parameters are independently set through multiple branches, different branches are forced to pay attention to differentiated pathological areas, and the problem of insufficient feature diversity caused by attention concentration is solved; dirichlet distribution is combined to quantify the confidence and uncertainty of branch prediction, the branch fusion weight is dynamically adjusted based on the evidence theory, and the fusion robustness of a multi-branch prediction result is improved. Experiments prove that compared with an MIL method, the method disclosed by the invention has the advantages that the AUC index is improved by 1.1-2.4%, and the accuracy and generalization ability of pathological WSI classification are remarkably enhanced.

The invention provides a postoperative patient supervision system for neural interventional therapy, and relates to the technical field of medical big data and artificial intelligence, and the system comprises a multi-modal data collection center, an interference feature decoupling unit, a trust capital quantification unit, a game strategy arbitration unit and a supervision execution unit. The multi-modal data acquisition center is configured to call time sequence monitoring data of a monitoring object; the trust capital quantification unit performs trust loss evaluation analysis on historical interaction feedback data; and the game strategy arbitration unit is configured to perform comparative analysis on the current clinical trust capital index and a preset trust threshold. According to the system, time-frequency domain matching is carried out on the residual error sequence and behavior state marking data, it is ensured that the system only carries out risk evolution prediction on neurogenic hemodynamic changes, and therefore the false alarm rate caused by external interference in a complex postoperative monitoring environment is remarkably reduced, and pure pathological feature components are extracted.

The invention discloses a pathological complete remission prediction method and device based on difference radiomics, and relates to the field of medical images.The method comprises the steps that a preoperative medical image and preoperative clinical data of a patient to be predicted are obtained; inputting the preoperative medical image and the preoperative clinical data into the trained pathology complete remission prediction model, and outputting a pathology complete remission result of the patient to be predicted by the pathology complete remission prediction model; the pathology complete remission prediction model is constructed by a joint prediction model and prediction factors screened from sample clinical data, and the joint prediction model is constructed by utilizing pre-treatment radiomics characteristics, post-treatment radiomics characteristics and difference-radiomics characteristics. Whether a non-small cell lung cancer patient receiving neoadjuvant immunochemotherapy reaches complete pathological remission or not is represented in a non-invasive mode, so that medical staff are assisted in formulating a personalized treatment scheme, and the clinical result of the patient is improved.

The invention discloses a multi-level and multi-link electrocardiosignal classification and identification method, system and device. The method comprises the following steps: collecting a body surface electrocardiogram signal of a subject, constructing a time domain feature, a frequency domain feature and an electrocardio dynamic feature, respectively inputting the three features into a preset neural network model, and calculating the local confidence of the features; calculating the global confidence coefficient according to the topological difference of the electrocardio dynamics; and judging whether the current classification is used as a final result or not according to the relationship between the global confidence and the local confidence of the corresponding feature, or further judging by adopting the next feature. According to the method, the dynamic change of the electrocardiosignal is more comprehensively described, and the multi-dimensional information of the signal is fully utilized. The multi-level feature extraction strategy can more comprehensively represent the characteristics of the electrocardiosignals in different physiological and pathological states; and a multi-link mechanism is introduced, and cooperative verification and dynamic decision of global confidence and local confidence are utilized, so that the reliability of a classification result is remarkably improved, and misjudgment can be effectively avoided.

1. The name of the design product: pathological analysis machine (AI intelligent pathological image analysis system). 2. The use of the design product: for pathological reading whole process collection and analysis. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: front view.

The invention discloses a pathological image classification method and system for assisting pathological diagnosis, and aims to solve the problems that the traditional pathological diagnosis is low in efficiency and the accuracy depends on artificial experience. According to the method, a pathological image is collected, denoising, enhancement and other preprocessing operations are executed, a pre-trained deep learning model is utilized to automatically extract image features, and classification results of benign, malignant or specific disease types are output in combination with a classification algorithm, so that efficient and accurate automatic diagnosis is realized; the system integrates image acquisition, preprocessing, feature classification and result display modules, supports multi-user concurrent access and cloud deployment, is equipped with model updating and user interaction functions, and can continuously optimize model performance based on new data. In addition, remote pathological diagnosis is supported, and balanced distribution of medical resources is promoted through a digital system; the method can significantly reduce the workload of pathologists, reduces the risk of human misdiagnosis, and is suitable for rapid classification and diagnosis of various pathological images such as tissue slices, cell smears and the like.

The invention relates to the field of medical systems, in particular to a molecular pathology automatic diagnosis method and system and a storage medium, and the method comprises the steps: reading pathology data, and establishing a pathology database; reading case data; determining diagnosis data by using the case data and the pathological data; and outputting the diagnosis data and the case data corresponding to the diagnosis data to a user for confirmation. The method has the effect of improving the diagnosis efficiency.

This invention discloses a cross-modal medical image segmentation method based on pathological anchoring. Using pathological priors as semantic anchors, this method integrates cross-scale collaboration and uncertainty perception in a closed-loop prompting refinement process. This achieves interpretable suppression and robust learning of cross-modal domain shifts, forming a closed-loop path from structure to semantics to noise control. Under strong cross-modal zero-sample settings such as multi-source ultrasound cross-domain segmentation and color dermoscopy, stable and consistent improvements are achieved, manifested in more precise boundaries, better calibration, and more robust generalization. This provides technical support for disease image diagnosis.

A double-module dynamic series cascade network system for predicting preoperative T stage of gastric cancer belongs to the technical field of medical artificial intelligence. The system adopts a deep learning architecture of double-module dynamic series connection. The first module realizes T1-T4 stage screening based on a hybrid model of parallel CNN and hierarchical Transformer. If it is judged as T1-T3 stage, the output result is output, and the second module is not entered. If it is judged as T4 stage, the second module is automatically triggered to perform T4 subtype differentiation task based on ResNet-152 submodel, and the output result is T4a or T4b. The system uses postoperative pathological results as the T stage gold standard, and shows high accuracy and universality in multicenter retrospective and prospective verification. The results show that the macro average AUC of the model in external verification reaches 0.964, the accuracy is 94.4%, and the T4 subtype recognition accuracy is highest, reaching 96.2%. The present application does not depend on labeled data, can significantly improve the accuracy and consistency of preoperative staging of gastric cancer, realize automatic and fine intelligent evaluation, has strong generalization ability and important clinical application value.

The invention discloses a pathological full-slice interpretable analysis method and system based on dynamic causal discovery, and the method comprises the steps: segmenting an input full-slice image into a plurality of image blocks, carrying out the spatial clustering of the image blocks, generating an anchor point, obtaining the representation of an initial region through the correlation between a learnable kernel and the anchor point, and obtaining the representation of the initial region; splicing the initial region representations into a learnable global token to obtain region kernel features; the global token only receives causal information of all regional nodes through a self-attention mechanism; modeling a causal relationship between the pathological areas based on a directed acyclic graph to obtain a causal graph between the pathological areas; propagating a causal relationship in the causal graph through a graph convolution operation, and performing N-renn iterative optimization to obtain an iteratively optimized region kernel feature and a final causal graph; the features of the global token in the final causal graph serve as final global representation, and an interpretable causal chain is formed. The objective of the invention is to model a causal relationship between pathological areas and diagnosis decision dependence, and improve the fine granularity and interpretability of tumor analysis.

This invention provides a deep learning-based method for fine-tuning the general representation of gastritis pathological images. The method includes: obtaining a pathological feature extraction network based on a first pathological image and a training strategy; obtaining a pathological evolution manifold based on the pathological feature extraction network and training a lesion reversal simulator to obtain a pathological evolution base model; obtaining a downstream task classification head and a second pathological image; freezing the parameters of the pathological evolution base model and inserting cue vectors into the pathological feature extraction network; training the cue vectors and the downstream task classification head using the second pathological image to obtain a fine-tuned model; inputting a third pathological image into the fine-tuned model, obtaining analysis results, and using the pathological evolution base model to generate lesion deviation data for the third pathological image. This invention achieves efficient adaptation to downstream tasks under small sample conditions while not forgetting the internalized disease continuity evolution patterns of the model.