147 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 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 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 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 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 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.

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.

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.

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.

The utility model discloses a pathological dehydrator convenient to sample lifting and placing relates to pathological dehydrator technical field, including pathological dehydrator, the right side of pathological dehydrator is provided with and places mechanism for realizing sample lifting and placing, and places mechanism in including: lifting unit and placing unit, lifting unit sets up in the right side of pathological dehydrator, including fixed mounting in the right side of pathological dehydrator's base, the top fixed mounting of base has the installing rod, the top fixed mounting of installing rod has the roller bracket, and the both ends inside of roller bracket are rotationally installed with the guide wheel, and install the steel cable on the guide wheel, through setting up lifting unit and drive assembly, servo motor drive reel receives and releases the steel cable, drives T -shaped slide plate along T -shaped groove and lifts, thereby will sample from low -elevation promote to the height of pathological dehydrator's entrance, effectively alleviates the burden of operating personnel bare -handed lifting heavy sample basket, avoids shoulder waist injury, improves operating safety and efficiency.

The invention relates to the technical field of electrocardiosignal quality evaluation, and discloses an electrocardiosignal quality evaluation method based on an unsupervised cascade adaptive network, which comprises the following steps: S1, preprocessing an obtained original electrocardiosignal: removing power frequency interference through adaptive notch filtering, removing high-frequency myoelectricity noise through soft threshold wavelet filtering, and obtaining a pre-processed electrocardiosignal; keeping a potential pathological characteristic waveform in a filtering process to obtain a preprocessed electrocardiosignal; s2, unsupervised multi-modal feature extraction: an unsupervised feature extraction network is constructed based on an auto-encoder; a normal electrocardiosignal distribution rule is automatically learned through an auto-encoder, so that the dependence on labeling resources of professional doctors is reduced; meanwhile, by means of a two-stage self-adaptive evaluation network, significant noise is filtered first, then pathological signals and noise are accurately distinguished, it is effectively avoided that abnormal waveforms caused by diseases such as myocardial infarction and atrial fibrillation are misjudged as noise, the retention rate of the pathological signals is remarkably increased, and more complete effective data support is provided for clinical diagnosis.

The invention discloses a heart sound signal acquisition and automatic classification method based on deep learning, and aims to solve the problems that wireless transmission time delay of heart sound signals is high, weak pathological features are difficult to extract and classification accuracy is low. The method comprises the following steps: acquiring signals of four auscultation areas by using a high-fidelity wireless digital stethoscope; high-speed and low-delay transmission of medical-level signals is realized by utilizing a star flash transmission module and combining predictive coding and Huffman coding compression mechanisms; in the preprocessing stage, self-adaptive wavelet denoising based on signal energy entropy is adopted, a multi-resolution fusion feature extraction strategy is provided, the problem of time-frequency resolution tradeoff is solved through narrow window and wide window dual-channel parallel processing, and transient positioning features and pathological frequency domain textures are captured at the same time; the classification model adopts a multi-scale parallel convolution structure and is matched with a recurrent neural network and an attention mechanism, so that the problem that transient and continuous heart sound features are difficult to consider at the same time in a single scale is solved. According to the method, the accuracy and robustness of heart sound classification are remarkably improved.

The application discloses a fine segmentation method for prostate and internal lesion areas based on large pathological sections, and specific steps are as follows: step 1, sequentially performing fixation, paraffin embedding, continuous transverse sectioning and HE staining operations on the whole tissue; step 2, extracting an HE staining image; step 3, sequentially scanning the pathological sections in step 2 into digital pathology; step 4, processing the digital pathology; step 5, performing image registration and three-dimensional image reconstruction on analysis results of multiple pathological sections processed in step 4; step 6, training a magnetic resonance multi-modal sequence segmentation model; step 7, extracting features of normal prostate tissue and lesion tissue in three sequences; step 8, acquiring high-risk factor information and quantifying features; step 9, constructing a sample feature matrix; and step 10, predicting the malignancy degree of prostate cancer. The method can realize more accurate benign and malignant evaluation of prostate lesions and prediction of the malignancy degree of prostate cancer.

The present application relates to the technical field of pathological image classification, in particular to an intestinal mucosa tissue pathological image classification method and system based on artificial intelligence. The present application selects a histopathological region from a suspected pathological region, divides a sequence obtained by sequentially arranging the histopathological region into different subsequences, acquires pathological feature templates of the subsequences under each disease category, determines the disease category to which the histopathological region in the subsequence belongs according to the similarity between the texture distribution, blood vessel distribution characteristics of the histopathological region in the subsequence and the pathological feature templates, and acquires the feature templates of each subsequence under each disease category according to the pathological features of the histopathological region belonging to the same disease category and the pathological feature templates of the previous subsequence of each subsequence under each disease category. The present application realizes gradual and accurate matching of the pathological feature templates through dynamic and iterative optimization of the feature templates with the subsequences, and increases the accuracy of pathological feature matching of the intestinal mucosa pathological position.

The invention provides a Mama-based membranous nephropathy multi-mode pathological image quantitative analysis system and method, and belongs to the crossing field of biomedical engineering and artificial intelligence. The problems that in an existing membranous nephropathy diagnosis system, the diagnosis process is high in subjectivity, single-mode analysis is limited, lesion feature quantification is insufficient, and model calculation is complex are solved. According to the technical scheme, the system comprises an image preprocessing module, the image preprocessing module is in communication connection with a macroscopic lesion analysis module, a microstructure analysis module and a thickness quantification module, and the macroscopic lesion analysis module and the thickness quantification module are both in communication connection with a feature fusion and prediction module. The macroscopic lesion analysis module, the microstructure analysis module, the thickness quantification module and the feature fusion and prediction module are all in communication connection with the result visualization module, and multi-modal pathological image quantitative analysis of membranous nephropathy is realized; the method is applied to multi-mode pathological image analysis of membranous nephropathy.

A system (100) for causing a subject to receive a survey intended to assess a health status and / or performance status of the subject. The system comprises: one or more biosensors (105) adapted to detect, on one or more points of the body surface, a plurality of bioelectrical signals emitted by the body of the subject associated with at least one body region associated with the survey purpose; an acquisition module (120) configured to acquire the plurality of bioelectrical signals; one or more substances to which the subject must be exposed during the performance of the survey, where the one or more substances are configured to induce a reaction in one or more molecules by exposure to the subject, the one or more molecules participate in one or more biochemical reactions constituting a metabolic chain in the at least one body region; and an analysis device (140). The analysis device is configured to implement one or more mathematical algorithms, the method comprises the following steps: according to a first bioelectrical signal naturally emitted by the body of a subject under the condition that the subject is not exposed to one or more substances in the plurality of bioelectrical signals and a second bioelectrical signal naturally emitted by the body of the subject under the condition that the one or more substances are not exposed to the subject, determining a metabolic condition of the subject based on a difference between second bioelectrical signals emitted by the body of the subject if the subject is exposed to the one or more substances described above, exposing the subject to the one or more substances includes placing the one or more substances outside the subject's body, close to or in contact with the subject's body; identifying the metabolic condition and nutritional data and / or sports medical data of the subject, statistical data relating to one or more pathologies, diagnostic / clinical data of the subject obtained by one or more medical devices (130), measurements of vital signs of the subject performed by one or more measurement modules (115), and data relating to one or more pathologies of the subject. A correlation between at least one of medical data of the subject provided by one or more personal devices (135) of the subject, and medical history data of the subject, and a result of the survey is provided based on the metabolic condition and the correlation.

The invention belongs to the technical field of medical artificial intelligence, and discloses a decoupling pathology analysis method for multi-scale image context variation inference, a storage medium and a system. The method comprises the following steps: a first stage: data structuring and multi-scale representation; in the second stage, probabilization and decoupling coding of node features are carried out; a third stage: probability distribution prediction under a context condition; a fourth stage: performing quantitative detection and feature attribution of abnormity; and a fifth stage: structured output and report generation. And in the fourth stage, a morphological anomaly score of each node in the graph structure is constructed, key diagnosis area identification is carried out, and anomaly attribution vector construction is realized by calculating a KL divergence component of each node in the key diagnosis area on each dimension of a potential space. The technical problem that in the prior art, the abnormal level of the specific pathological feature corresponding to the dimension cannot be quantified, and then a quantitative and explainable targeted diagnosis decision cannot be provided is solved.

The application relates to the technical field of medical data processing, and discloses a critical patient multi-organ function failure evolution path prediction system, which comprises a collection and preprocessing module, an adaptive dynamic characteristic extraction module, a physical dissipation constraint causal topology analysis module, a closed-loop feedback controller and a cascade failure path deduction module. The system extracts dynamic characteristics and calculates a physical effectiveness coefficient based on multi-modal physiological signals, uses the coefficient to correct transfer entropy to construct a multi-organ coupling network; the closed-loop feedback controller dynamically adjusts the embedding dimension parameter of the front-end characteristic extraction according to the total in-degree coupling strength of the network, forming a bidirectional constraint closed loop between the physical layer and the information layer. The application can effectively identify a pathological driving source, deduce the cascade propagation sequence of organ function failure, eliminate false causal connections through physical mechanism constraint and feedback regulation, and improve the accuracy of evolution path prediction.

The utility model relates to the technical field of pathological slicing, and discloses a pathological sampling and slicing device which comprises a base, a supporting column is fixedly mounted at the top of the base, a mounting box is fixedly mounted at the top of the supporting column, a receiving hopper is fixedly mounted on the right side of the base, and a wax block fixing mechanism is arranged in the mounting box and extends to the right side. A reciprocating slicing mechanism is arranged at the top of the mounting box, the wax block fixing mechanism comprises a pushing assembly and a clamping assembly, the pushing assembly is arranged on the inner wall of the right side of the mounting box, and the pushing assembly is arranged in the mounting box. According to the pathological sampling and slicing device, the paraffin block fixing mechanism is arranged, in the using process, the four edges of a paraffin block are clamped and fixed through the four clamping blocks, only a small part of the paraffin block is exposed, therefore, it is guaranteed that the paraffin block is clamped stably, meanwhile, during slicing, the paraffin block is pushed outwards through a material pushing block, and therefore normal slicing of the paraffin block is guaranteed.

The invention relates to the technical field of artificial intelligence, and discloses a multi-site tumor subtype accurate detection method based on a multi-modal AI large model. The method comprises the following steps: acquiring a radiomics feature vector and a pathomics feature vector of a to-be-detected tumor area; mapping the two feature vectors to the same implicit phenotype space, and calculating phenotype mutual exclusion intensity and mutual exclusion fluctuation variance between the two feature vectors; generating a dynamic temperature coefficient based on the mutual exclusion fluctuation variance, modulating phenotype mutual exclusion intensity by using the temperature coefficient, and generating a consistency weight; taking the pathological omics feature vector as a residual trunk, performing weighting control on the radiomics feature vector by using a consistency weight, and then superposing the radiomics feature vector to the trunk to obtain a fusion feature vector; and finally inputting the fusion feature vector into a classification network to output a detection result. According to the method, multi-modal feature inconsistency caused by data artifacts or biological conflicts can be identified and inhibited, and the problem of false association caused by blind fusion is solved.