684 results about "Mri image" patented technology

The invention discloses a brain tumor multi-mode large model construction method, device and equipment and a storage medium, and is applied to the technical field of brain tumor imagines.The method comprises the steps that pixel-concept level alignment is conducted on a multi-mode MRI image and a pathological text; constructing a multi-modal feature fusion network for fusing image features and text features by adopting an attention mechanism of pathology perception and combining medical semantic information; training the multi-modal feature fusion network to generate an analysis report and a segmentation result; according to the technical scheme of multi-task cooperation, cross-modal pathological semantic accurate alignment, pathological knowledge graph injection and lightweight and continuous optimization parallelization, full-process coverage of brain tumor accurate segmentation, analysis report generation and prognosis prediction is achieved, the problems that a traditional model lacks pathological semantic support and is insufficient in clinical adaptability are solved, and the clinical adaptability of the traditional model is improved. And the deployment feasibility and the dynamic optimization capability are also considered.

The invention discloses a multi-organ medical image segmentation method based on a multi-feature fusion Swindow-Unet architecture, and belongs to the field of medical image processing. The core of the method is that CT and MRI images are input into a pre-trained CMFSA-UNet model for segmentation, and the model comprises an encoder, an MAFR module, an MFDF module, a decoder and a jump connection layer. CNN-Swin Transform double branches are adopted by the encoder, local details and long-range semantics are extracted, and Attention Gate reinforcement is carried out; the MAFR module widens a receptive field through double branches, combines an attention mechanism with residual connection, reduces the calculated amount and gives consideration to local and global features; and the MFDF module fuses multi-scale dense connection and frequency domain processing, so that feature loss is reduced. The decoder extracts features through Swin Transform Block, resolutions are recovered through 4 times of up-sampling, and the segmentation precision is optimized in combination with depth supervision and a mixed loss function. According to the method, local and long-range feature modeling is efficiently cooperated, precision and efficiency are balanced, segmentation global consistency, boundary accuracy and training stability are improved, the method is suitable for multi-modal multi-organ segmentation, and reliable support is provided for clinical diagnosis and the like.

The invention discloses a head and neck MRI image classification method, system and terminal, and the method comprises the steps: constructing an image classification model which comprises an improved U-Net segmentation module and an edge perception learning module; inputting the head and neck MRI images into an improved U-Net segmentation module to obtain multi-scale features, performing aggregation to obtain associated features, performing up-sampling on the associated features to obtain up-sampling features, performing adaptive fusion perception on the up-sampling features and the multi-scale features to obtain fusion features, and generating fine masks according to the fusion features; inputting the associated features into an edge perception learning module for semantic decoupling and up-sampling to obtain three regional masks; calculating edge loss according to the three regional masks; obtaining a target model according to the loss optimization model; and obtaining a target head and neck MRI image, inputting the head and neck MRI image into the target model, and outputting a classification result of the head and neck MRI image. According to the method, the accuracy of a head and neck MRI image classification result is effectively improved.

The invention provides a multi-mode nuclear magnetic resonance image glioma segmentation method and application thereof, and belongs to the field of medical image processing. The invention provides an M2ES-UNet network aiming at the problems of insufficient utilization of spatial features, single multi-modal fusion mechanism and cross-level semantic loss of an existing segmentation method. According to the method, multi-view anatomical information is extracted through a multi-plane feature collaboration module; utilizing an orthogonal dimension fusion convolution and modal introspection-collaboration module to respectively realize differential fusion of shallow and deep features; and the progressive jump transmission of the features is realized through a coding information smooth transmission module. According to the method, multi-plane and multi-mode complementary information can be effectively mined, the boundary precision and robustness of brain glioma segmentation are remarkably improved, and clinical diagnosis is assisted.

Systems and methods for fast reconstruction of motion-resolved magnetic resonance images using space-time-coil convolutional networks are disclosed. The system can receive a plurality of k-space data sets. The system can detect a motion signal therefrom. The system can classify the k-space data sets according to states of the motion signals. The system can resolve the k-space data set to Euclidean space images. The system can resolve the Euclidean space images to a combined Euclidian space image. For example, the system can use a convolutional network that exploits spatial, temporal and coil correlations without k-space data consistency to minimize computation time.

The invention discloses a scanning control method and system for a magnetic resonance spectrometer, and the method comprises the following steps: an upper computer analyzes and loads sequence file parameters meeting the Pulseq standard, and integrates the sequence file parameters and pre-configured system parameters into a scanning parameter set; the upper computer generates an executable spectrometer hardware control instruction based on the scanning parameter set, and writes the spectrometer hardware control instruction into a register of a PCIE board card through a PCIE driving module; the PCIE board card generates a hardware control signal according to the content written in the register, controls the spectrometer hardware module to execute corresponding operation, and generates magnetic resonance original data; and the upper computer reads the magnetic resonance original data and reconstructs the magnetic resonance original data into magnetic resonance image data based on analysis of the magnetic resonance original data. According to the invention, the compatibility and flexibility of the system are significantly improved, different upper computers can communicate and cooperate with the spectrometer hardware module, sequence sharing and use among different devices are facilitated, and the integration and maintenance costs of the system are reduced.

The invention discloses an artery plaque detection and evaluation method and device, and relates to the technical field of image recognition. The method comprises the following steps: acquiring a to-be-used image group, wherein the to-be-used image group comprises at least one modal magnetic resonance image; performing blood vessel wall segmentation operation on the to-be-used image group to obtain a binary blood vessel skeleton image; inputting the to-be-used image group and the binarized vascular skeleton image into a trained plaque segmentation model to obtain a binarized plaque mask combination; inputting the binarized plaque mask combination and the to-be-used image group into a trained plaque component recognition model to obtain a multi-label segmentation result image; and performing plaque vulnerability judgment according to the multi-label segmentation result image so as to obtain plaque vulnerability judgment information. According to the method, the problems of high subjectivity, poor generalization ability, sensitivity to image quality and the like caused by dependence on artificial feature extraction and threshold segmentation in a traditional method are solved.

The invention discloses a multi-contrast magnetic resonance image reconstruction method and device based on detail contour feature perception. The method comprises the following steps: acquiring a target modal initial image and an auxiliary modal initial image; constructing an iterative network formed by alternately cascading image domain reconstruction units and data consistency layers, wherein each image domain reconstruction unit comprises an encoder and a decoder; in the first iteration, target modal initial images and auxiliary modal initial images are spliced and then input, an encoder extracts shared features firstly, then global contour features and high-frequency detail features are separated in parallel, and potential features are obtained through collaborative fusion; the decoder takes the potential features as input and outputs an image domain preliminary reconstruction result; the data consistency layer transforms the preliminary result into a k space, performs consistency correction on the preliminary result and a target modal sampling point, and then inversely transforms the preliminary result back to an image domain to complete one iteration; and splicing the current output and the auxiliary modal initial image again, inputting the spliced image into a next round of iteration, and repeating the process until a preset number of times to obtain a final target modal magnetic resonance image.

The invention provides a brain glioma CT-MRI (Computed Tomography-Magnetic Resonance Imaging) multi-modal fusion intelligent grading method and a brain glioma CT-MRI multi-modal fusion intelligent grading system, and relates to the field of medical image processing and intelligent diagnosis, and the method comprises the following steps: obtaining CT image and MRI image data of a brain glioma patient through a medical image acquisition device, carrying out standardized preprocessing on the CT image and the MRI image data, and generating a preprocessed image data set; and spatial alignment is carried out on the preprocessed image data set, CT-MRI registration image data are output, and a multi-scale registration method is adopted for spatial alignment. According to the CT-MRI multi-modal fusion intelligent grading method and system based on the brain glioma, by providing the CT-MRI multi-modal fusion intelligent grading method, the problem that in the prior art, image registration and feature fusion are not accurate is solved. A multi-scale registration method and a weighted combined feature extraction mode are adopted, accurate registration of CT and MRI images and efficient fusion of features are ensured, and therefore the accuracy and stability of a grading model are improved.

The invention discloses a brain tumor MRI image segmentation method based on a soft clustering KAN network, and belongs to the technical field of medical information processing, and the method comprises the steps: carrying out the voxel alignment and intensity normalization of a multi-modal three-dimensional brain tumor MRI image, and constructing a unified input sample; layer-by-layer downsampling and multi-scale feature extraction are realized through a KAN residual encoder formed by alternately cascading double-layer KAN attention subnets and three-dimensional maximum pooling layers; three-dimensional position coding is added to the highest-layer features, and bottleneck features containing global structure priori are obtained through soft K-means clustering bottleneck layer modeling; fusing the jump connection feature and the up-sampling feature by using an attention gating mechanism to complete decoding; and through soft clustering regularization and a multi-scale depth supervision constraint optimization model, finally through fusion of a main segmentation branch and a refined branch, outputting a multi-subarea three-dimensional segmentation result of the whole tumor, the tumor core and the enhanced tumor.

The invention provides a brain tumor classification method and device based on a magnetic resonance image, and a medium. The method comprises the following steps: obtaining a magnetic resonance image to be processed; preprocessing the magnetic resonance image to obtain a preprocessed first image; the first image is input into a trained implicit high-dimensional state space hybrid network, a classification result corresponding to the first image is obtained, the implicit high-dimensional state space hybrid network comprises a convolutional embedding layer, a backbone network and a classification module which are cascaded, the backbone network is composed of a plurality of stages, and the classification module is used for classifying the first image; each stage includes a number of stacked state space multiplicative interaction blocks. The backbone network adopts a multi-layer state space multiplicative interaction block stacking structure, and through selective long-range aggregation and implicit high-order feature interaction, the computational complexity is reduced, and meanwhile, the perceptual ability to a tumor region and a boundary thereof is enhanced; on the premise of ensuring the light weight of the model, the accuracy and generalization ability of the brain tumor multi-classification task are remarkably improved.

The invention discloses an improved multi-modal MRI (Magnetic Resonance Imaging) brain tumor segmentation method, which comprises the following steps of: firstly, acquiring a multi-modal MRI image containing a brain tumor, and preprocessing the multi-modal MRI image; secondly, based on the preprocessed multi-modal MRI image, enhanced modal correlation modeling and feature fusion are carried out, and smooth edge features are obtained; and finally, based on the smooth edge features, performing multi-task decoding and result output to obtain a complete brain tumor segmentation image. According to the method, the key problems of insufficient modal feature alignment, inter-task information segmentation, fuzzy segmentation boundary and the like in the existing multi-modal brain tumor segmentation are effectively solved.

The invention provides a medical magnetic resonance image reconstruction method and system, and belongs to the technical field of image reconstruction, and the method comprises the steps: obtaining sampling coding and under-sampling k space data; processing the under-sampled k space data through inverse Fourier transform, and converting the k space data into an image domain to obtain under-sampled image data with blurring or artifacts; carrying out preliminary restoration on the undersampled image data based on sampling coding, further applying data consistency operation on the image to obtain a rough image, and taking the rough image as an image condition vector after underspace coding; acquiring a text serving as a cue word, inputting the text into a text encoder, and encoding the text into a high-dimensional semantic embedding vector by the text encoder; and inputting the high-dimensional semantic embedding vector and the image condition vector into a reconstruction model based on the correction flow to predict a full-sampling MRI image, and generating a final reconstructed MRI image.

The invention relates to the technical field of edge segmentation, in particular to a tumor interventional therapy preoperative planning system based on artificial intelligence image recognition, and the method comprises the steps: preliminarily screening out an infiltration edge region based on the gray distribution asymmetry condition of a sliding window in a CT image and the texture disorder condition in an MRI image; further fusing DSA blood vessel data, and screening a concerned infiltration region by analyzing the position distribution condition of the blood vessel region of the infiltration edge region; analyzing curvature mutation conditions of the tumor associated blood vessel segments on the basis of the concerned infiltration region to generate a blood vessel anomaly index; and finally, fusing the infiltration index and the blood vessel characteristics to construct a blood vessel-infiltration coupling index, and correcting the edge strength map according to the blood vessel-infiltration coupling index, so that the boundary optimization based on risk classification is realized, the accuracy of the obtained tumor region edge structure curve is higher, and the accuracy of tumor region segmentation according to the tumor region edge structure curve is improved.

The invention belongs to the technical field of medical image segmentation, and relates to a dual-path fusion neural network for prostate precise segmentation and a segmentation method, the neural network constructs a dual-path decoupling encoder architecture based on an nnU-Net framework, captures fine anatomical structure and local texture information through a context sensing residual encoder of a local path, and obtains a dual-path fusion neural network for prostate precise segmentation. A long-range dependency relationship is modeled with linear complexity through a visual state space module of a global path, a double-flow alignment gating module is designed to realize self-adaptive alignment and fusion of cross-path features, and model training is optimized in combination with a mixed loss function and a depth supervision strategy; according to the method, the limitation of an existing segmentation model in the aspect of local structure and global semantic integration is solved, and the segmentation precision, the boundary goodness of fit and the generalization performance of the focus and gland region in the prostate MRI image are improved.

The invention provides a thyroid-related eye disease intraorbital soft tissue volume measurement method and system, and is applied to the technical field of data processing. Three-dimensional medical image data and system abnormal state information are obtained, the three-dimensional medical image data comprise CT images and MRI images, and the system abnormal state information comprises artifacts, isolated noisy points and irregular boundaries; data preprocessing is carried out on the three-dimensional medical image data, standardized image data is generated, and the standardized image data is formed by carrying out ternary processing on spatial registration, noise suppression and gray level normalization; processing the standardized image data and the system abnormal state information to generate an initial segmentation mask; processing the initial segmentation mask to generate an optimized mask; processing the optimized mask and the three-dimensional medical image data to generate soft tissue volume data; and processing the soft tissue volume data, the system abnormal state information and the historical volume data to generate a volume dynamic change report.

The invention discloses a pelvic soft osteosarcoma MRI (Magnetic Resonance Imaging) segmentation method based on edge-guided multi-scale fusion. The method comprises the following steps: firstly, acquiring an MRI image of a patient with soft osteosarcoma of pelvis, and preprocessing the image; and then, constructing a pelvic soft osteosarcoma MRI segmentation network model, namely an EMU-Net segmentation network, based on edge-guided multi-scale fusion. And training the network by using the preprocessed training data, inputting a pelvic soft osteosarcoma MRI image to be segmented into the trained network, outputting a corresponding segmentation probability graph, and obtaining a final tumor segmentation mask by setting a threshold value. The method not only effectively overcomes the clinical segmentation bottleneck, but also realizes full-automatic and high-efficiency precise segmentation by means of an end-to-end deep learning architecture, and has remarkable advantages in the aspects of precision and robustness.

The invention discloses a pulmonary nodule MRI segmentation method based on attention-guided cross-modal fusion, belongs to the field of medical image processing, and aims to solve the problems of high missing detection rate of small nodules, insufficient multi-modal fusion and low boundary segmentation precision in existing pulmonary nodule MRI segmentation. The method comprises the following steps: preprocessing a lung multi-modal MRI image and generating a pulmonary nodule multi-modal attention feature map; constructing a segmentation network with attention jump connection and a cross-modal fusion network based on a conditional diffusion model, and forming a dual-branch joint optimization framework of segmentation and fusion decoupling; and end-to-end training is completed through a joint loss function including segmentation loss, fusion loss and consistency loss. According to the method, the pulmonary nodule segmentation precision and the model robustness are remarkably improved, and the method is suitable for accurate diagnosis scenes of clinical pulmonary nodules.

The invention relates to the field of medical image processing, in particular to a cross-modal medical image alignment method based on anatomical feature one-dimensional distribution, and the method comprises the steps: obtaining a computed tomography (CT) image sequence and a magnetic resonance imaging (MRI) image sequence of a hip joint region of a patient; extracting a CT one-dimensional anatomical feature sequence representing the morphological change of the first side femoral head from the CT image sequence; extracting an MRI one-dimensional anatomical feature sequence representing the morphological change of the first side femoral head from the MRI image sequence; based on the CT one-dimensional anatomical feature sequence and the MRI one-dimensional anatomical feature sequence, a similarity alignment process is executed; wherein the similarity alignment process comprises the following steps: determining an optimal similarity alignment offset between a CT image sequence and an MRI image sequence, and aligning the MRI image sequence and the CT image sequence according to the optimal similarity alignment offset. According to the method, the cross-modal image alignment problem is subjected to dimensionality reduction into one-dimensional anatomical feature sequence matching, so that the precision, efficiency and robustness of registration are remarkably improved.

The present disclosure provides an apparatus for restoring the quality of magnetic resonance images based on a deep learning model and a method of controlling the same. The method includes: obtaining a training image corresponding to each magnetic resonance image by applying at least one of a plurality of elements set in connection with the quality of the magnetic resonance image to a magnetic resonance signal corresponding to the magnetic resonance image; obtaining a training dataset including the magnetic resonance image as label data and the obtained training image as input data matching the label data; and training a neural network model based on the training dataset and context data corresponding to the training image. Obtaining the training image includes distorting the magnetic resonance signal by applying the at least one of the plurality of elements and obtaining the training image based on the distorted magnetic resonance signal.

The invention provides a breast cancer patient pCR prediction classification method based on image-gene interpretability deep learning. The method comprises the following steps: dividing an obtained data set into a training set and a test set; splitting all the three-dimensional MRI images into two-dimensional slice images; the gene text features of each breast cancer patient are classified into N different sets; segmenting a two-dimensional slice image corresponding to the training set into a plurality of patches; each patch and the gene text feature corresponding to each patch are converted into a corresponding high-dimensional Embedding (high-dimensional Embedding); respectively multiplying H by Wk and Wv to obtain K and V; multiplying G by WQ to obtain Q; obtaining a gene guidance image feature CoAttn; the CoAttn and the Q are fused to obtain a feature set F; inputting the F into a network model, and training the network model based on a loss function; inputting the two-dimensional slice image corresponding to the test set into the trained network model, and outputting a plurality of classification results; and adopting a maximum voting strategy to make decisions on the plurality of classification results. According to the method, pCR and npCR classification is carried out on the patient based on a co-attention mechanism of gene text features and MRI images, the interpretability of model decision is enhanced, and a more visual and reliable auxiliary diagnosis tool is provided for clinicians.

The invention discloses an intelligent sketching method for a cervical cancer radiotherapy target area and organs at risk, and relates to the technical field of medical images, and the method comprises the following steps: obtaining a CT and MRI image data set of a cervical cancer patient; inputting the CT and MRI images containing the metal artifacts into a pre-trained metal artifact removal model to obtain CT and MRI images without the metal artifacts; inputting the CT and MRI images with the metal artifacts removed into a double-encoder U-Net network comprising a cross-modal attention fusion gating module to obtain final fusion features; processing the final fusion feature through a U-Net decoder, constructing a small sample adaptive mixed loss function to optimize network parameters, and outputting a segmentation mask; and carrying out contour processing on the segmented mask to complete the delineation of the target region and the endangered organ. Through high-precision and high-efficiency automatic sketching, a patient can obtain higher-quality and higher-efficiency treatment, and meanwhile, the working intensity of a doctor is relieved.

A method for acquiring a magnetic resonance image dataset of an object includes using an imaging protocol in which a number of k-space lines are acquired in one shot. The imaging protocol includes a plurality of shots. A plurality of additional k-space lines are acquired in at least a subset of the shots, such that movement of the object is detected throughout the imaging protocol. A method for generating a motion-corrected magnetic resonance image dataset from the dataset thus acquired, a magnetic resonance imaging apparatus, and a computer program are also provided.

The invention belongs to the technical field of medical image artificial intelligence and body composition analysis, and particularly relates to an MRI-based whole body muscle fat quality evaluation system, which comprises an MRI image data acquisition module, an image preprocessing module, an AI segmentation module, a quantitative calculation module, a database comparison module and a visual report generation module, according to the scheme, an improved U-Net framework is adopted, a KAN layer is embedded behind each Stage of a Swin Transform backbone network, fixed nonlinear activation in a traditional MLP is replaced, high-precision and interpretable modeling of local strength changes is achieved, and the boundary recognition capacity is remarkably improved; according to the scheme, a multi-level fusion mechanism combining SDI and KAN is introduced, the mechanism effectively strengthens a tissue related region and inhibits irrelevant or noise response, high-order nonlinear correction is performed on fused features by using a KAN layer, and complex intensity distribution at a muscle-fat junction is accurately described.

The invention discloses a brain abnormal development trajectory identification method and system, and belongs to the technical field of magnetic resonance image analysis, and the method comprises the following steps: obtaining T1 weighted magnetic resonance images of a plurality of healthy individuals, and carrying out the offset correction of the structure index of each brain region in the images, a generalized additive position-scale-shape model of the healthy crowd is constructed; generating a norm development trajectory curve and a normal change range thereof; obtaining a T1 weighted magnetic resonance image of a to-be-evaluated individual, and selecting a target brain region of the to-be-evaluated individual; obtaining various offset corrected structure indexes of the target brain region of the individual to be evaluated; obtaining a mean value and a standard deviation of each structure index at the position of the brain region corresponding to the same-age healthy population of the individual to be evaluated; and generating a recognition report of the abnormal brain development trajectory of the to-be-evaluated individual. The problem that it is difficult to accurately, clearly and visually reflect the abnormal recognition condition of the brain trajectory of the individual to be evaluated and the position of the corresponding abnormal brain region is solved.

The invention discloses a magnetic resonance image target identification method based on multi-modal feature fusion, and the method comprises the steps: firstly obtaining multi-sequence magnetic resonance image data of the same object, the data comprising a structure sequence, a function sequence and a quantization parameter sequence, and carrying out the synchronous preprocessing; the pre-processed data is input to a feature extraction network to obtain a multi-dimensional feature representation. A cross-modal interaction map is constructed based on feature representation, interaction and fusion of different modal features are realized through an attention mechanism, and a fusion feature vector is obtained. And generating a focus candidate region set, and correcting the candidate region in combination with the related information of the patient to obtain a corrected focus region set. And inputting the corrected target area set into a discrimination network, and outputting a positioning result and a type result of the target. According to the method, through multi-modal feature fusion and map modeling, the accuracy and robustness of focus recognition are effectively improved, misjudgment caused by single-modal limitation is reduced, and the method has high clinical application value.

The invention provides a three-dimensional medical image segmentation method and system for thyroid-related eye diseases, and is applied to the technical field of data processing. Multi-modal medical image data, a coarse-grained segmentation result and a fine-grained segmentation result are obtained, the multi-modal medical image data comprise a CT image and an MRI image, the multi-modal medical image data are preprocessed, a fused image body is generated, and the fused image body is formed by registration and feature fusion of the CT image and the MRI image; processing the fused image body and the coarse-grained segmentation result to generate a fine segmentation result; processing the fine segmentation result to generate a preliminary segmentation mask; processing the preliminary segmentation mask and the multi-modal medical image data to generate a mixed loss function; and processing the preliminary segmentation mask, the mixed loss function and the extraocular muscle attachment point position based on a dynamic post-processing strategy to generate a final segmentation result.

The invention relates to the technical field of medical image processing, in particular to a prostate MRI image segmentation method based on an anatomical structure relationship, and the method comprises the steps: obtaining a to-be-segmented prostate region and a rectum reference region as an anatomical reference from a prostate MRI image; segmenting the prostate region to be segmented based on a fixed anatomical relationship between the prostate and the rectum by taking the rectum reference region as an anatomical reference to obtain an initial prostate segmentation result; identifying a prostate junction partition region in the prostate initial segmentation result and a rectum junction partition region corresponding to the rectum reference region; and based on the boundary features of the rectum junction partition, performing boundary optimization on the prostate junction partition to obtain an accurate prostate segmentation result. According to the invention, the recognition accuracy of the prostate region is improved.

The invention relates to a minimally invasive implantable frontal lobe brain-computer interface method and device, and the method comprises the steps: constructing an individualized brain three-dimensional model according to CT and MRI image data of a patient, presetting an optimal nasal implantation path, and carrying out the implantation of the patient through a nose under the dual guidance of a nasal endoscope and a three-dimensional navigation system, constructing a skull base passage through minimally invasive trimming of a nasal cavity / paranasal sinus structure, and performing real-time matching and overlapping on an endoscope view and the three-dimensional model by using a rigid body transformation algorithm to display the position of a surgical instrument; windowing at a preset target point, implanting the flexible electrode array into a target brain region according to a planned depth and angle through a controllable propulsion mechanism, and establishing a neural signal acquisition or stimulation interface; intelligent mode recognition is carried out on the collected neural signals, the intention or brain state of the user is decoded, and corresponding neural stimulation or feedback signals are generated. According to the method, accurate, safe and minimally invasive clinical intervention is realized through a full-chain technical scheme of individualized planning, real-time navigation, minimally invasive implantation and biological integration, and the application value of a brain-computer interface technology is remarkably improved.

A system for generating contrast-enhanced magnetic resonance images of a subject includes an input configured to receive at least one non-contrast enhanced image of the subject, and a contrast-enhanced magnetic resonance (MR) image synthesis neural network coupled to the input and configured to generate a contrast-enhanced magnetic resonance image of the subject based on the at least one non-contrast enhanced image of the subject. The contrast-enhanced MR image synthesis neural network is trained using a set of training data comprising at least quantitative data.