11 results about "Tumor control" patented technology

The invention provides a radiotherapy plan generation method and device, equipment and a medium, and the method comprises the steps: obtaining a target function image of a target object; the target function image comprises a target region, an organ at risk and a target part; determining target dose information of the target part based on the target function image, the target function partitioning result, the target region segmentation result and the endangered organ segmentation result; the target function partitioning result is used for indicating spatial distribution of a plurality of functional regions of the target part divided according to the functional state, and the target dose information comprises doses of different regions of the target part; and generating a radiotherapy plan based on the target dose information. By applying the embodiment of the invention, the set dose information of the target part is more reasonable, so that the radiotherapy plan generated based on the target dose information can ensure the accuracy of tumor control, reduce the risk of radioactive injury and realize targeted protection of the target part.

The present disclosure relates to methods of treating or inhibiting the growth of a tumor, wherein the methods include selecting a subject with cancer and administering to the subject in need thereof a therapeutically effective amount of a cancer vaccine (e.g., mRNA vaccine against a tumor) in combination with a bispecific antigen-binding molecule comprising a first antigen-binding domain that binds specifically CD28 and a second antigen-binding domain that binds specifically to a tumor-associated antigen (TAA). The combination therapy demonstrates increased anti-tumor efficacy, increased duration of tumor control and / or increased overall survival, as compared to a subject administered the cancer vaccine as monotherapy.

The invention discloses a system for predicting the risk of nerve injury caused by radiotherapy based on deep learning, and belongs to the technical field of medical artificial intelligence and radiotherapy, and the system comprises a neural structure automatic segmentation module, a dose-neural response modeling module, an individualized risk assessment module, a radiotherapy plan optimization module and a closed-loop feedback regulation unit. The system adopts an encoder-decoder deep network to perform high-precision segmentation on nervous tissues, establishes a dose-nerve response quantitative model by fusing dosiomics and radiomics characteristics, and realizes individualized risk assessment based on a multi-factor risk quantitative network. An optimization scheme for balancing tumor control and neuroprotection is generated through Pareto optimal search, collaborative optimization of all the modules is achieved through closed-loop feedback, and decision support is provided for precise radiotherapy.

The present disclosure relates to methods of treating or inhibiting the growth of a tumor, wherein the methods include selecting a subject with cancer and administering to the subject in need thereof a therapeutically effective amount of a cancer vaccine (e.g., mRNA vaccine against a tumor) in combination with a bispecific antigen-binding molecule comprising a first antigen-binding domain that binds specifically CD28 and a second antigen-binding domain that binds specifically to a tumor-associated antigen (TAA). The combination therapy demonstrates increased anti-tumor efficacy, increased duration of tumor control and / or increased overall survival, as compared to a subject administered the cancer vaccine as monotherapy.

The invention belongs to the technical field of postoperative cooling patches in clinical medicine, and particularly relates to a postoperative stepped continuous cooling patch which sequentially comprises a base layer, a quick-release cooling layer, a slow-release temperature stabilizing layer, a long-acting temperature slowing layer and an adhesive layer from outside to inside. The quick-release cooling layer comprises a double-layer wall material microcapsule, the core material of the double-layer wall material microcapsule is tetrafluoroethane, and the wall material of the double-layer wall material microcapsule is a polylactic acid-sodium alginate composite wall; the slow-release temperature stabilizing layer comprises menthol glyceryl ether and paraffin microspheres with the melting point of 18-20 DEG C; the long-acting temperature slowing layer is high-water-retention gel containing hyaluronic acid; the continuous cooling duration of the cooling patch is larger than or equal to 8 hours, and the cooling curve meets the conditions that the temperature is 15-20 DEG C within 0-2 hours, the temperature is 18-22 DEG C within 2-6 hours, and the temperature is 22-25 DEG C within 6-8 hours. According to the invention, the local temperature is controlled in a safe and effective interval of 15-25 DEG C, and the swelling control effect and the skin safety are both considered; meanwhile, through the design of the high-elasticity and high-fitness base material, the two hands of the patient are liberated, and cutting can be conducted to meet the movement requirements of different parts after an operation.

This disclosure relates to methods for treating or inhibiting tumor growth, wherein the method includes selecting a subject with cancer and administering to the subject in need a combination of a therapeutically effective amount of a targeted immune cytokine (e.g., a fusion protein comprising an IL2 moiety and an immunoglobulin antigen-binding domain binding to PD1) and a TAAxCDS bispecific antibody. Compared to subjects receiving targeted immune cytokines as monotherapy, the combination therapy has shown improved antitumor efficacy, increased duration of tumor control, and / or increased overall survival.

The invention provides a dose determination method and device, equipment and a medium, and the method comprises the steps: obtaining a functional image of a target object; the functional image comprises a target region, an organ at risk and a target part; based on the function image, dividing a function area of the target part according to the function state, and generating a function partitioning result; based on the functional image, the target region segmentation result, the endangered organ segmentation result and the functional partitioning result, dose information of the target part is determined; the dose information comprises doses of different areas of the target part. By applying the embodiment of the invention, the set dose information of the target part is more reasonable, so that the accuracy of tumor control can be ensured, the risk of radioactive injury is reduced, and the targeted protection of the target part is realized.

This disclosure relates to a method for improving the efficacy of adoptive cell therapy (ACT) and a method for treating cancer, wherein the method comprises administering a combination therapy comprising a therapeutically effective dose of ACT (e.g., immune cells comprising a modified T cell receptor (TCR) for tumor-associated antigens (TAAs) or a chimeric antigen receptor (CAR) for TAAs) and a therapeutically effective dose of a targeted immune cytokine (e.g., a fusion protein comprising an IL2 moiety and an immunoglobulin antigen-binding domain that binds to PD1) to a cancer subject in need thereof. This combination therapy demonstrates improved antitumor efficacy, improved duration of tumor control, and / or extended overall survival compared to subjects treated with ACT as monotherapy or with ACT in combination with untargeted immune cytokines.

The invention discloses a tumor radiotherapy dose prediction method and system, and belongs to the field of radiooncology and artificial intelligence crossing. In order to solve the problems that in an existing radiotherapy plan, a weight coefficient and an offset item depend on empirical assignment, the balance accuracy of TCP (tumor control probability) and multiple NTCPs (normal tissue complication probability) is insufficient, and individualized treatment pain points are difficult to adapt, a double-stage scheme is provided: in the first stage, target tumor TCP and normal tissue multiple NTCPs are accurately predicted through a deep learning model; obtaining optimization basic data; in the second stage, a special neural network is constructed, an optimal weight coefficient and an offset item are solved through forward propagation, self-defined loss function calculation and back propagation automatic iteration, the optimal weight coefficient and the offset item are substituted into a radiotherapy comprehensive evaluation formula to calculate comprehensive indexes of all plans, and the optimal radiotherapy dose is screened. According to the method, subjective experience assignment is replaced by data driving, TCP and multiple NTCPs are dynamically and accurately balanced, individual features of patients are adapted, clinical suitability and safety of radiotherapy dosage are improved, the occurrence rate of complications is reduced, the system is simple in structure, low in implementation cost and easy to be compatible and popularized with an existing radiotherapy planning system, and efficient and accurate technical support is provided for individualized radiotherapy.

The invention discloses a deep learning-based TCP and NTCP dosage scheme generation method and system, and the method comprises the following steps: obtaining multi-source heterogeneous data of a target patient group, carrying out the standardization processing of the multi-source heterogeneous data, and obtaining a data set with consistent dimensions; labeling corresponding TCP and NTCP labels according to the follow-up visit result of the patient; inputting the training data set into a TCP-NTCP combined prediction model, learning nonlinear correlation between data and TCP / NTCP, outputting prediction results under different doses, and substituting the prediction results into a TCP-NTCP combined dose-response function to establish a combined dose-response curve; and substituting into an optimal screening constraint condition formula of a radiotherapy dose scheme, and solving an optimal dose value considering both tumor control and normal tissue protection. Through multi-modal data fusion and a deep learning architecture, the model prediction precision and generalization ability are improved, collaborative optimization of TCP maximization and NTCP minimization in a normal tissue tolerance range is realized, and technical support is provided for radiotherapy individualized dose planning.

The invention belongs to the field of brain tumor classification, and particularly relates to a combined brain tumor MRI classification method based on domain alignment evidence, and the method comprises the steps of pre-defining, framework integration, domain alignment, evidence guide fusion, uncertainty weighted estimation based on fusion, uncertainty image weight reduction and tumor sub-region output. According to the scheme, a feature interaction bridge is established through two-way cross attention to achieve multi-scale two-way information complementation, shared embedding is generated, statistical attributes of a source domain and a target domain are matched, feature distribution convergence is forced by executing an adversarial alignment operation, a tumor core and a fuzzy boundary are effectively described, and missing detection and false positive are reduced; according to the method, difference priori is obtained through the difference value of the original tumor MRI image and the reconstructed tumor-free contrast image, the weight of double-source evidence is reduced by using a pixel-level uncertainty map, accurate and complete positioning guidance is provided for a segmentation decoder, and the positioning accuracy and boundary integrity of a segmentation task are improved.