31 results about "Fetal brain" patented technology

The invention relates to a fetal brain tissue segmentation method based on prior information guidance, and the method comprises the following steps: obtaining a public data set, and selecting a part of data in the public data set as a training set; preprocessing the training set to obtain a grey-white matter volume ratio, an edge feature map and a gestational week feature map; constructing a prior segmentation model GA-Swin, and designing a loss function LTotal to train the model; and finally obtaining a trained fetal brain segmentation model. According to the method, on the basis of following the development law, each tissue of the fetal brain can be precisely segmented, and collaborative optimization of precision interpretability and biological rationality in medical image analysis is achieved.

The invention belongs to the technical field of fetal brain age prediction, and relates to an earthworm cerebellar fetal brain age prediction method and system based on multi-modal feature fusion, an MST-Mamba segmentation network is adopted, and local-global aggregators are embedded in each level of an encoder, so that the cooperation of local detail capture and global semantic modeling is realized; meanwhile, a dynamic channel fusion device is deployed at the jump connection part of the encoder and the decoder, so that the problems of fuzzy boundary, missed division, wrong division and the like are avoided; through three parallel branches of a multi-granularity form-texture collaborative perception architecture, two types of explicit features of macroscopic geometry and topological form and implicit features of microscopic texture are synchronously extracted, and comprehensive characterization of the development features of the earthworm cerebellar part is realized; the explicit features are subjected to standardized calibration and then spliced and fused with the implicit features in the channel dimension, the problems that multi-modal feature fusion is insufficient and calibration lacks are solved, finally prediction is conducted through a multi-layer perceptron regression head, and the accuracy and stability of the brain age prediction result are guaranteed from the source.

The present invention is directed to genetic manipulation of neural cells in the gyrencephalic fetal brain for developing treatment strategies for various neurodevelopmental disorders.

The invention provides a fetal magnetic resonance image brain region segmentation method and system, computer equipment and a medium, and belongs to the technical field of automatic segmentation of fetal brain magnetic resonance imaging. The method comprises the steps that firstly, 2D low-resolution fetal magnetic resonance images collected in multiple directions are processed, and 3D high-resolution fetal brain images are generated; secondly, performing selective interlayer labeling on the 3D image, and generating a complete segmentation label through a contour interpolation algorithm; and finally, performing mutual supervision learning by using a double-independent initialized segmentation network, including the steps of data enhancement consistency constraint, cross pseudo label supervision, feature comparison learning and the like. According to the fetal magnetic resonance image brain region segmentation method and system, the computer equipment and the medium, a high-performance divider can be trained only through a very few labels, the labeling cost is remarkably reduced, the segmentation efficiency is improved, the method and system are suitable for actual clinical fetal brain magnetic resonance research, and efficient technical support is provided for fetal brain development evaluation.

The invention provides a fetal brain age prediction network training method, an application method and electronic equipment, and belongs to the technical field of medical image processing, and the training method comprises the steps: carrying out the similarity sorting conversion of a fetal brain magnetic resonance image and a corresponding brain age label, and obtaining a similarity sorting matrix, performing vector embedding reconstruction on the similarity sorting matrix to obtain an embedded vector, and determining an initial permutation entropy; performing median absolute deviation weighting on the initial permutation entropy to obtain a weighted permutation entropy, performing multi-scale ordinal number information reconstruction on the weighted permutation entropy to obtain a multi-scale permutation entropy, performing time sequence enhancement reconstruction on the multi-scale permutation entropy to obtain a time sequence multi-scale permutation entropy, and constructing permutation entropy regularization loss according to the time sequence multi-scale permutation entropy; and obtaining a fetal brain age prediction network according to permutation entropy regularization loss iterative training. According to the method, the loss function is constructed through the permutation entropy regularizer, so that the continuous ordered relation in regression can be captured, and the distinguishing ability and generalization ability of the fetal brain age prediction network are remarkably improved.

The present application relates to the field of data analysis, and in particular to a fetal brain MRI tissue analysis method, apparatus, and electronic device, comprising obtaining multiple post-treatment brain MRI images, each corresponding to a different gestational age; performing brain tissue segmentation on each post-treatment brain MRI image to obtain multiple post-treatment local brain tissue segmentation maps corresponding to multiple local brain tissues; obtaining, for each post-treatment brain MRI image, a pre-treatment local brain tissue segmentation map corresponding to each post-treatment local brain tissue segmentation map; determining, for each post-treatment brain MRI image, a deformation coefficient for each local brain tissue; generating, for each local brain tissue, a linear analysis map corresponding to each local brain tissue based on the deformation coefficients of the local brain tissue corresponding to all gestational ages; and determining final brain tissue analysis information based on the linear analysis maps corresponding to all local brain tissues. The present application facilitates a holistic analysis of the impact of changes before and after treatment on different gestational ages and different brain tissues.

The invention provides a cleaning and preserving fluid for fetal brain tissues and a preserving method thereof, and belongs to the technical field of tissue preservation. The cleaning and preserving fluid comprises trehalose, nerve growth factors, a GlutaMAX supplement, Y27632, S-nitrosoglutathione, tert-butylhydroquinone, a Versene solution and polyvinylpyrrolidone, compared with a traditional tissue preserving fluid, the cleaning and preserving fluid not only can improve the purity of neural stem cells, but also can maintain the activity and the yield of the neural stem cells in fetal brain tissue, and the cleaning and preserving fluid has the advantages that the cleaning and preserving fluid is simple in structure and convenient to use. The structural integrity of the cells is guaranteed, a high-quality sample is provided for subsequent research on proliferation, differentiation and the like of the neural stem cells, and the method has a wide application prospect.

The present invention provides a fetal brain tissue segmentation method, device, medium and terminal based on a cycle consistency network. By acquiring target fetal brain image data, inputting the target fetal brain image into a pre-trained cycle consistency network, and outputting a segmentation result of the target fetal brain image corresponding to the gestational week; The present invention adopts a learning framework combining cycle consistency and adversarial learning, and realizes the accurate capture of fine-grained domain-invariant brain structures in thick clinical and thin reconstruction cases of fetal brain MR images.

This application belongs to the field of fetal brain age prediction technology, and relates to a method and system for predicting fetal brain age of the cerebellar vermis based on multimodal feature fusion. It employs the MST-Mamba segmentation network, and achieves synergy between local detail capture and global semantic modeling by embedding local-global aggregators at each level of the encoder. Simultaneously, a dynamic channel fusion unit is deployed at the jump connection between the encoder and decoder to avoid problems such as boundary ambiguity, missed classification, and misclassification. Through three parallel branches of a multi-granularity morphology-texture collaborative perception architecture, it simultaneously extracts two types of explicit features (macro-geometric and topological morphology) and two types of implicit features (micro-texture), achieving a comprehensive representation of the developmental features of the cerebellar vermis. After standardizing and calibrating the explicit features, they are spliced ​​and fused with the implicit features along the channel dimension to solve the problems of insufficient multimodal feature fusion and lack of calibration. Finally, prediction is performed using a multilayer perceptron regression head, ensuring the accuracy and stability of the brain age prediction results from the source.

The invention discloses a fetal brain development assessment method and a computer program product, and belongs to the field of medical image analysis. The method comprises the following steps: firstly, acquiring a brain image of a fetus, and then segmenting the brain image by using a segmentation model trained based on a multi-gestational-age sample and a loss function adjusted along with gestational ages to obtain a brain segmentation result; calculating a brain development index of the fetus based on the segmentation result; estimating the gestational age of the fetus by using a gestational age estimation model, wherein the gestational age estimation model comprises a segmentation model serving as a generator and a discriminator obtained through adversarial training; acquiring a normal brain development index range of the corresponding gestational age from a reference database based on the estimated gestational age; and finally, comparing the calculated brain development index with a normal range to obtain a fetal brain development evaluation result.

The application provides a dynamic modeling method and system for multi-field skill AI automatic semantic labeling, and relates to information retrieval, medical health and cross-field skill fusion scene. Through nonlinear dynamic modeling and biomedical stability control, the semantic label automatic generation and real-time matching of talent skill and health intervention effectiveness are realized. The application innovatively integrates the sound wave frequency of fetal brain promoting music method, maternal action instruction and blood type nutrition scheme into the "skill-time" frequency domain space, combines the Gevrey smoothing operator and fractional derivative evolution equation, accurately separates the temporary fetal movement fluctuation and low-frequency core characteristics, and breaks through the characterization limitation of traditional models on nonlinear biological coupling effect. By introducing the "intervention effect-time" frequency domain component and local dependency constraint, the short-term effectiveness and long-term value of music intervention on fetal neurodevelopment are quantified, and the model distortion problem caused by extreme data or cross-field parameter resonance in traditional methods is solved.

The present invention relates to the field of medical MRI imaging, and more specifically to a deep learning-based fetal MRI brain tissue segmentation method and device. The method and device first perform data enhancement operations on fetal brain MRI, and then construct a feature pyramid model based on the Contextual Transformer block: the feature pyramid model introduces an attention structure CoT-Block in the encoder and decoder parts. The attention structure CoT-Block uses key context information to guide the learning of the dynamic attention matrix and enhance the features extracted from the fetal brain MRI image after data enhancement; the feature pyramid model introduces a hybrid dilated convolution module in the decoder part. The hybrid dilated convolution module expands the receptive field and retains detailed spatial information, and effectively extracts global context information in the medical image, thereby effectively improving the accuracy of segmentation and helping doctors to make clinical diagnoses to the greatest extent.

This invention provides a method, system, computer equipment, and medium for fetal magnetic resonance imaging (MRI) brain region segmentation, belonging to the field of automated segmentation technology for fetal brain MRI. The method includes: first, processing multi-planar acquired 2D low-resolution fetal MRI images to generate 3D high-resolution fetal brain images; second, performing selective inter-layer annotation on the 3D images and generating complete segmentation labels using a contour interpolation algorithm; and finally, using a dual-independent initialization segmentation network for mutual supervision learning, including steps such as data augmentation consistency constraints, cross-pseudo-label supervision, and feature comparison learning. This invention, employing the aforementioned fetal MRI brain region segmentation method, system, computer equipment, and medium, requires only a very small number of labels to train a high-performance segmenter, significantly reducing annotation costs and improving segmentation efficiency. It is suitable for practical clinical fetal brain MRI research, providing efficient technical support for fetal brain development assessment.

The present application relates to a kind of fetal brain brain age estimation method and device based on deep imbalance regression, the method includes: introducing label to fetal brain magnetic resonance image training set, using label distribution smoothing strategy to obtain effective label density distribution;Establish multi-scale hierarchical segmentation fetal brain feature extraction regression network;Regression focus mean square error loss function is constructed, and effective label density is used to reweighting regression focus mean square error loss function;Grade ordering similarity regularizer is constructed;With the reweighted focus mean square error regression loss function as main function, grade ordering similarity regularizer is used as balance regularization term, and the total loss function of fetal brain feature extraction regression network is constructed.The method can significantly improve the performance of regression model, can let model better learn the continuous information of regression age label, obtain lower mean absolute error, help to identify the abnormality of brain development and reduce the risk of adverse development.

The present invention discloses a method, apparatus, storage medium, and computer device for predicting gestational age based on fetal brain magnetic resonance images and prior information. A three-dimensional convolutional network is proposed to extract brain structural information from fetal MRI images to obtain fetal brain structural features. The network, composed of asymmetric convolutional layers and attention enhancement layers, uses the entire 3D image as input and selectively emphasizes key information features, adapting to random variations in the position and orientation of the fetal brain. A discrete area distribution vector of the fetal brain is proposed to represent the distribution of brain region areas in MRI images, improving the robustness and effectiveness of the introduced prior knowledge. The method also proposes a fusion regression module to integrate the fetal brain structural features and fetal brain area distribution features for gestational age estimation based on fetal brain MRI images. The proposed gestational age prediction method achieves optimal accuracy and robustness.

Disclosed is a method for reducing or preventing fetal opioid dependence in a drug dependent or opioid tolerant pregnant subject. The method involves administering to the pregnant subject a composition comprising an opioid antagonist in an amount effective to reduce or prevent fetal opioid dependence, wherein the opioid antagonist a) is orally available or delivered systemically and reaches the circulation of the pregnant subject, b) is substantially excluded from the subject's brain by the blood brain barrier, and c) penetrates the placenta and enters the fetal brain. The method also includes administering the opioid antagonist to the neonate in increasing amounts to facilitate weaning the neonate from continued opioid maintenance.

The present invention relates to a method and system for detecting standard sections of a fetal brain. The method comprises: step S1: acquiring a fetal brain ultrasound image; step S2: constructing a fetal brain standard section detection network model based on a YOLOv7 model, wherein the fetal brain standard section detection network model comprises a backbone network, a neck network, and a head network connected in sequence, wherein the backbone network and the neck network are improved, wherein the backbone network is used to extract image features, the neck network is used to perform feature fusion on the image features extracted by the backbone network, and the head network is used to detect the fused features obtained by the neck network; and step S3: identifying whether the fetal brain ultrasound image is a standard section image using the fetal brain standard section detection network model. The present invention can effectively detect standard section images of the fetal brain.

The present invention discloses a method for segmenting and extracting fetal brain images from twin MR images. The method includes training a target detector using a twin brain dataset with bounding box labels. The trained target detector is then tested on the twin brain dataset to obtain a twin brain dataset after removing maternal tissue. The single fetal brain dataset is then input into a segmentation network to encode the fetal brain region and extract initial low-level features. Low-resolution features are upsampled to obtain deep high-level features. Low-level features and high-level features of the same resolution are concatenated using skip connections. The output feature map is calculated to obtain a probability output, which is then input into a cross-entropy loss function along with the corresponding labels to calculate the loss value. The network parameters are then updated to obtain a pre-trained model. The pre-trained model is then loaded, and the twin brain dataset, after having been subjected to the target detector and removed maternal tissue, is input into a segmentation network and trained to obtain the final segmentation model. The present invention can quickly and efficiently segment and extract twin brain images.

The invention provides for the detection of a perturbed gene network, which includes highly expressed genes during fetal brain development, which is dysregulated in neuron models of autism spectrum disorder (ASD). High-confidence ASD risk genes are upstream regulators of the network modulating RAS / ERK, PI3K / AKT, and WNT / / β-catenin signaling pathways. The invention demonstrates how the heterogeneous genetics of ASD can dysregulate a core network to influence brain development at prenatal and very early postnatal ages and, thereby, the severity of later ASD symptoms. The invention provides a model for diagnosis, prognosis determination, and optionally treatment and monitoring, for any disease by comparing molecular marker patterns in non-affected tissues in a subject with healthy controls to determine a dysregulated network in the subject based on a co-expression pattern of interacting genes.

The invention discloses a method for generating a fetal brain nuclear magnetic volume image based on a diffusion model. The method comprises the following steps of: performing brain tissue extraction on an image data set of a fetal brain three-dimensional volume to obtain a real three-dimensional fetal brain volume and a corresponding image mask; constructing a diffusion model; gaussian noise is added to the real three-dimensional fetal brain volume according to the time step to obtain a noisy volume, the time step is embedded through linear layer processing to obtain a time step code, and the diffusion model is trained based on the noisy volume, the time step code and the image mask; initializing a noisy volume, performing iterative denoising based on the time step, outputting predicted noise based on the trained diffusion model, and calculating the noisy volume of the next time step; adding a fidelity optimization process in a set time step, and replacing the volume corresponding to the original time step with the volume of a fidelity optimization result; and outputting the completely denoised generation volume after iterative denoising. According to the invention, the reconstruction quality of the volume of the three-dimensional fetal brain nuclear magnetic image is improved.

The application provides a dynamic training optimization system and method based on multi-dimensional biological feedback, and relates to the technical field of intelligent sensing and behavior optimization.The application realizes accurate optimization of the mother-fetus interaction environment by constructing a joint evaluation matrix of physiological data of pregnant women and fetal development indicators, and introduces a regulation technology based on body dynamics and beta wave music cooperation, which significantly reduces the matching deviation of maternal physiological parameters and fetal needs.Meanwhile, by using dynamic nutrition intervention and amniotic fluid dynamics monitoring based on biological rhythm synchronization, the dynamic balance of the intervention during pregnancy and the efficient development of fetal synapses are realized, and combined with multi-dimensional sensory stimulation and neural plasticity enhancement scheme, not only the synaptic density and neural network efficiency of the fetal brain functional area are greatly improved, but also the key problems such as single stimulation, non-systematic intervention and development evaluation lag in the existing fetal education method are effectively solved.

The invention relates to the technical field of medical image processing, in particular to an unsupervised fetal cerebral hemorrhage detection and focus segmentation method and device and electronic equipment, and the method comprises the steps: obtaining the magnetic resonance imaging data of a normal fetal brain; the method comprises the following steps: synthesizing a plurality of pseudo fetal focus and intraventricular hemorrhage images from magnetic resonance imaging data of a normal fetal brain by using medical priori knowledge, and generating training data according to the plurality of pseudo fetal focus and intraventricular hemorrhage images; training a segmentation model by using the training data, inputting the magnetic resonance imaging data of the brain of the target fetus into the trained segmentation model, and outputting a segmentation result of the focus of the brain of the target fetus and the intraventricular hemorrhage by the segmentation model. Therefore, the problems that in the prior art, training data is scarce, and a large amount of manual annotation data needs to be relied on for model training are solved.

The invention relates to an application of TLR < 4 > siRNA (TLR < 4 > siRNA (at) LNP-CSA-BP) coated with TLR < 4 > siRNA (TLR < 4 > siRNA) connected with placental Chondroitin sulfate A binding peptide (Placental Chondroitin sulfate A binding peptide, CSA-BP) injected in a maternal pregnancy period, in improvement of pregnancy complications and prevention of progeny neurodevelopment disorder diseases, in particular to an application of TLR < 4 > siRNA coated with LNP-CSA-BP coated with TLR < 4 > siRNA coated with LNP-CSA-BP. According to the invention, TLR4siRNA (at) LNP-CSA-BP is used for carrying out caudal vein injection on a pregnant mouse, so that a placenta and fetal brain inflammation microenvironment (induced by toxoplasma gondii STAg) maternal immune activation can be inhibited. Behavior experiments further prove that under a maternal immune activation model, TLR4siRNA (at) LNP-CSA-BP caudal vein injection pregnant mice can significantly improve phenotypes of neurodevelopmental disorder diseases of filial generation mice, such as core symptoms (social ability and repeated engraving behaviors) of autism behaviors, and the promising transformation prospect is proved.

The invention relates to the technical field of medical image processing, in particular to a fetal brain magnetic resonance single thick layer scanning three-dimensional reconstruction method, device and equipment, and the method comprises the steps: obtaining single thick layer scanning data of a fetal brain during magnetic resonance imaging in any direction; generating a brain mask result of the fetal brain according to a single thick layer in the single thick layer scanning data; the fetal head orientation is judged according to the brain mask result, and a single thick layer in the single thick layer scanning data is registered based on the fetal head orientation and the brain mask result to obtain a target registration result; the target registration result is input into a reconstruction network, the reconstruction network outputs a three-dimensional reconstruction result of the fetal brain, the reconstruction network comprises a conditional potential diffusion model or a convolutional neural network, and the conditional potential diffusion model or the convolutional neural network performs three-dimensional reconstruction on the target registration result to obtain the three-dimensional reconstruction result of the fetal brain. Therefore, the problems of relatively long scanning and reconstruction time, relatively poor stability and the like of three-dimensional reconstruction in related technologies are solved.

Described are methods for identifying an ASD risk gene, NHIP, and methods for determining the risk of an offspring for developing an ASD. A common structural variant disrupting the proximity of NHIP to a fetal brain enhancer was associated with NHIP expression and methylation levels and ASD risk, demonstrating a common genetic influence. NHIP is a novel environmentally-responsive ASD risk gene relevant to brain development in a previously under characterized region of the human genome.

The present invention provides a fetal cerebellar vermis MR image segmentation method, belonging to the field of image processing technology, the method comprising acquiring a fetal brain MR image, and preparing a whole brain target detection data set and a cerebellar vermis image segmentation data set; locating the midsagittal plane of the fetal brain MR image to be segmented according to the whole brain target detection data set and the cerebellar vermis image segmentation data set; constructing a fetal cerebellar vermis MR image segmentation network based on global multi-scale feature aggregation; using the constructed fetal cerebellar vermis MR image segmentation network, segmenting the fetal cerebellar vermis MR image on the screened midsagittal plane. The present invention effectively achieves the segmentation of the fetal cerebellar vermis MR image.

The invention discloses a chopping device for fetal brain tissue before primary culture of neural stem cells, and relates to the technical field of fetal brain tissue chopping, the chopping device comprises a shell, a supporting column is fixedly connected to the side wall of one end of the shell, and a supporting plate is fixedly connected to one end of the supporting column; and the side wall of the bottom end of the supporting plate is fixedly connected with a uniform chopping assembly. According to the fetal brain tissue cutting device, a side plate can drive a cutter to transversely cut and separate fetal brain tissues extruded into a cutting groove through a second opening, at the moment, the fetal brain tissues are cut into small tissue blocks with uniform sizes by the cutter in a cutting plate, air is conveyed into a cavity through an air pump, and finally, the air is blown out through an air outlet hole; when the fetal brain tissue cutting device is used, the fetal brain tissue in the cutting groove is blown downwards, the cut fetal brain tissue is prevented from remaining in the cutting groove, and the situation that when researchers cut the fetal brain tissue through ophthalmic scissors, the fetal brain tissue floats around in a culture solution, and consequently the researchers cannot cut the fetal brain tissue evenly and rapidly and effectively is avoided.

The invention discloses a fetal brain age prediction method and system based on self-supervised structure perception fusion. The method comprises the steps of obtaining a fetal brain MRI image, and performing preprocessing and image segmentation to obtain a plurality of image blocks; calculating a structural complexity score for each image block, and generating a corresponding structural mask based on the structural complexity score; shielding the fetal brain MRI image through a structural mask to obtain a shielding image; inputting the occlusion image into a pre-trained structure perception encoder to obtain a structure perception feature map; inputting the fetal brain MRI image into a supervision encoder to obtain a high-level semantic feature map; and fusing the structure perception feature map and the high-level semantic feature map to obtain fused features, and inputting the fused features into a global average pooling layer and a full connection layer to obtain a gestational week prediction value. According to the invention, the precision and robustness of gestational week prediction are improved in a small sample and weak labeling scene.

The invention relates to a fetal brain development state assessment method and system, belongs to the technical field of brain development assessment, and solves the problems of high subjectivity, low efficiency and single analysis dimension when fetal brain development is assessed in the prior art. Comprising the steps of obtaining a to-be-evaluated fetal MRI image, and performing preprocessing to obtain an initial fetal MRI image; obtaining a fetal brain region image based on the initial fetal MRI image and a trained brain region recognition model; obtaining a gestational week stage of the fetal brain based on the fetal brain region image and a trained gestational week discriminator; based on the fetus brain region image, the gestational week stage of the fetus brain and a trained sectional type brain region segmentation model, obtaining a fetus brain region segmentation image, and further extracting features of each brain region of the fetus; based on the features of each brain region of the fetus, the equivalent gestational week of the fetal brain development is obtained, then the development offset is obtained according to the actual gestational week of the fetus, and then the evaluation result of the fetal brain development is obtained.

The invention provides a fetal brain age estimation network training method based on adaptive label distribution, and belongs to the technical field of medical image processing, and the training method comprises the steps: inputting a fetal brain magnetic resonance image into an initial fetal brain age estimation network, and obtaining brain age prediction distribution, determining prediction loss according to the brain age prediction distribution and the corresponding real brain age; constructing brain age target label distribution according to the real brain age, and determining probability distribution loss according to the brain age target label distribution and the brain age prediction distribution; constructing a target monotonicity indicator according to the brain age target label distribution, constructing a prediction monotonicity indicator according to the brain age prediction distribution, and determining unimodal distribution loss according to the target monotonicity indicator and the prediction monotonicity indicator; and performing iterative training according to the prediction loss, the probability distribution loss and the unimodal distribution loss to obtain a fetal brain age estimation network. According to the method, a finer supervision signal is provided through probability distribution loss simulation and unimodal distribution loss, and the accuracy of fetal brain age estimation is improved.