1644results about "Acquiring/recognising microscopic objects" patented technology

The invention discloses an alimentary canal pathological diagnosis visual language large model construction method based on reinforcement learning and application thereof, and belongs to the technical field of medical image processing. The method comprises the following steps: firstly, extracting pathological information through layout analysis and adaptive threshold processing, and recombining the pathological information into a structured data set containing an inference chain; secondly, a visual encoder and a multi-branch classifier are used for extracting features and confidence coefficients, and dynamic structured cue words are generated; and finally, inputting the image and the cue word into a multi-modal large model, carrying out supervised fine-tuning hot start, and carrying out reinforcement learning training by adopting a group relative strategy optimization algorithm in cooperation with a composite reward function containing format, semantics and diagnosis dimensions. The problems that a general model is prone to generating illusion in a pathological scene and lacks reasoning logic are solved, and the accuracy and logicality of pathological report generation are remarkably improved.

The invention discloses a titanium alloy microscopic structure prediction method and system based on a conditional generative adversarial network and a storage medium, and belongs to the following steps: firstly, constructing a process-structure mapping model, and taking the output of the model as a rule constraint condition; inputting the random noise vector and the rule constraint condition into a conditional generative adversarial network to generate a prediction image; according to the generative adversarial network, thermal dynamic constraints based on physical quantities of microscopic structures are introduced in the training process, so that the interpretability of a prediction result is improved. And carrying out quantitative comparison on the predicted image and the real image, verifying the consistency of the statistical characteristics, and if the verification is passed, outputting a prediction result. According to the method, end-to-end prediction from process parameters to microscopic structure images is realized, the limitation that only symbolization or parameterization prediction can be carried out in a traditional method is broken through, and the intuition, the interpretability and the engineering application value of the method are remarkably enhanced.

The invention discloses a multi-modal neural network fusion system fusing an attention mechanism, and particularly relates to the technical field of environmental monitoring artificial intelligence. The defects of high meteorological / water quality monitoring false alarm rate and large response delay caused by static weighted fusion, insufficient domain feature extraction and edge deployment bottleneck of an existing multi-modal fusion system are overcome. According to the method, meteorological satellite / water quality sensor data are fused in a cross-modal manner by adopting a dynamic attention mechanism, domain features are extracted in combination with space-time convolution and graph convolution, and the domain features are deployed to edge equipment through hybrid quantization compression. The severe convection weather identification and pollutant traceability precision is improved, and the real-time early warning capability of a field terminal is guaranteed.

The invention relates to the technical field of medical image processing and computer vision, in particular to a parasitic ovum microscopic image detection method and system based on polymorphic prior, and the method comprises the steps: obtaining a to-be-detected microscopic image, and carrying out the feature extraction of the to-be-detected microscopic image through a convolutional neural network, and obtaining an initial feature map; constructing a polymorphic convolution kernel library based on preset biological morphological characteristics of the parasitic ova; performing deep convolution and feature fusion operation on the initial feature map by using a polymorphic convolution kernel library to generate a space attention map; performing feature enhancement processing on the initial feature map by using the spatial attention map to obtain an enhanced feature map; and performing bounding box regression and category prediction on the enhanced feature map to obtain a parasitic ovum detection result. According to the method, morphological priori and attention mechanisms are introduced, so that the problems of egg form similarity, background interference and the like are solved, accurate and robust automatic detection is realized, and the clinical diagnosis efficiency is remarkably improved.

The invention discloses a reticulocyte recognition and grading system based on a blood smear, and particularly relates to the field of medical cell morphology examination, and the system comprises an image acquisition module, a staining normalization module, an instance segmentation module, an erythrocyte classification module, a reticulocyte grading module and a statistics output module. The image acquisition module adopts an automatic microscope platform to continuously scan the blood smear under a 100-time visual field, acquires a high-quality bright field channel image through an automatic focusing technology, and monitors image definition, contrast and illumination uniformity; the statistical output module is used for calculating the proportion and bluish violet intensity statistics of reticulocytes of each level, and generating a visual quality control result and a diagnostic report; according to the invention, full-automatic processing from samples to reports is realized, interpretability and high classification precision are both considered, subjective difference and omission ratio of manual microscopic examination are significantly reduced, and efficiency and consistency of clinical detection are improved.

The invention discloses a method and device for identifying organic matter pores in a shale electron microscope scanning image, and the method comprises the steps: obtaining a shale scanning electron microscope original image, carrying out the manual marking, and generating an original image and mask image data set; performing synchronous data enhancement on the data set and dividing a training set and a verification set; constructing an improved U-Net model containing a multi-scale feature fusion input module, a residual attention module and a wavelet domain feature enhancement center module; training the model by adopting a dynamic mixed loss function and an AdamW optimizer; and verifying the model through an average intersection-to-union ratio, a pore Dice coefficient and a pore error, and identifying the pores of the image to be processed after reaching the standard. The device correspondingly comprises an image acquisition annotation module, a data preprocessing module, a model construction module, a training module, a verification module and a pore recognition module. According to the method, full-automatic identification is realized, the multi-scale pore segmentation precision and the low-porosity sample adaptability are improved, and the efficient characterization requirement of the shale gas reservoir is met.

The invention discloses a probiotic packaging stability control method based on deep learning, and the method comprises the following steps: collecting multi-source data in a packaging process, and carrying out the preprocessing of the multi-source data; performing time sequence feature analysis on the standardized structured data set, and extracting multi-scale time sequence features; performing target segmentation and multi-dimensional structure feature extraction on the standardized microscopic image data set; feature fusion is carried out, a probiotic packaging stability feature space is constructed, and a stable feature vector is generated; inputting a time sequence prediction network, and carrying out time sequence modeling and prediction processing; performing control parameter adjustment and constraint optimization based on a difference value between a prediction result and stability reference data; and executing and updating the packaging control adjustment scheme according to feedback to complete a packaging control closed loop. According to the method, deep learning and multi-source data analysis are fused, intelligent prediction and adaptive control of the probiotic packaging process are realized, and the method has the advantages of high stability and high precision.

The invention discloses a super-lens image restoration method based on fuzzy prior and semantic segmentation. The method comprises the following steps: eliminating an image visual angle displacement error by adopting a feature point automatic registration algorithm; the method comprises the following steps: designing a parallel multi-scale convolution adapter on the basis of an encoder optimized by a pre-trained visual Transform model, and generating encoding features adaptive to the degradation characteristics of a super lens; splicing the degraded image and the semantic segmentation mask into a joint tensor along a channel dimension, and obtaining a prior feature based on a fuzzy prior extraction network; performing spatial feature enhancement on the semantic segmentation mask based on a semantic segmentation graph convolutional network to obtain graph features aligned with the coding features; splicing the coding features, the prior features and the image features along channel dimensions to generate fusion features, and finally outputting a preliminary recovery image; and optimizing the whole model by adopting a staged training strategy, and finally outputting a high-quality recovery graph. According to the method, the physical rationality and detail fidelity of the recovery quality are improved.

Methods and systems for performing a clinical prediction are provided. In one example, the method comprises: receiving first molecular data of a patient, the first molecular data including at least gene expressions of the patient; receiving first biopsy image data of the patient; processing, using a machine learning model, the first molecular data and the first biopsy image data to perform a clinical prediction of the patient's response to a treatment, wherein the machine learning model is generated or updated based on second molecular data including at least gene expressions and second biopsy image data of a plurality of patients; and generating an output of the clinical prediction.

The invention provides a stacked cell hierarchy judgment method based on contour concavity and convexity. The method comprises the following steps: performing contour extraction on a cell binary image; calculating a convex hull for the contour point set of each cell, and taking the convex hull as an ideal form reference of the cell in an unshielded state; detecting the convexity defect between the contour point set of each cell and the corresponding convex hull, and quantifying the characteristic parameter of each convexity defect; screening the convexity defects according to the characteristic parameters to determine significant recesses, marking cells with at least one significant recess as concave cells, and marking cells without significant recesses as convex cells; screening candidate cell pairs according to the spatial position relationship between the cells; according to the convex-concave attributes of the two cells in the candidate cell pair and the position relation between the coordinates of the center of mass and the remarkable concave area, the shielding relation between the two cells is judged; and constructing an attribute graph by taking each cell as a node and taking the occlusion relationship as an edge, and generating a cell stacking hierarchy sequence through topological sorting.

An apparatus an method for generating three-dimensional representations of serial sections, wherein the method includes creating a plurality of slide images using a slide scanner, the slide scanner comprising an image sensor and a stage, receiving, using at least a processor, the plurality of slide images from the slide scanner, extracting, using the at least a processor, a plurality of features from the plurality of serial slide section images using a feature extraction algorithm, registering, using the at least a processor, the plurality of serial slide section images as a function of the plurality of feature, generating, using the at least a processor, a three-dimensional (3D) stack view, wherein the 3D stack view comprises the plurality of serial slide section images, and displaying the 3D stack view through a display device.

The invention provides a deep learning-based junction point relation network training and cell occlusion judgment method, which comprises the following steps of: performing instance segmentation on a cell microscopic image to obtain a cell instance mask, and extracting a cell boundary based on the cell instance mask; performing junction point detection on the cell boundary to obtain cell shielding junction points, and classifying the cell shielding junction points into cell T-shaped shielding points, cell Y-shaped convergent points or cell X-shaped cross points; cutting the local image patch by taking the cell shielding junction point as a center, and constructing a multi-channel sample containing the local image patch; adopting a unified relationship label to label the multichannel sample, wherein the unified relationship label comprises a shielding relationship, a same-layer relationship and an unjudgeable relationship; training a deep learning network by using the labeled multi-channel sample, wherein the deep learning network outputs probability distribution of a junction point relationship category; and inputting a multi-channel sample of a to-be-detected cell microscopic image into the trained deep learning network, and outputting a junction point relationship category and a confidence coefficient thereof.

The invention discloses a breast cancer recurrence risk prediction method and system based on multi-modal data missing interpolation and gene interpretability enhancement. The method comprises the following steps: firstly, dynamically generating and complementing features of a missing mode by matching a generative adversarial network with a mode missing mask matrix; then, a feature screening mechanism driven by gene information is introduced, through a multi-task learning network, image feature extraction is supervised by using a gene expression tag in a model training process, and image features highly associated with recurrence-related genes are screened out; and finally, fusing the complemented multi-modal time sequence characteristics by adopting Transform, and outputting a recurrence risk probability. According to the method, the robust prediction performance can be realized under the condition of data missing, and meanwhile, image interpretation with a molecular biology basis is provided for the feature screening process of the model, so that the reliability and clinical acceptability of the whole system are enhanced.

The invention relates to the technical field of image recognition, in particular to a plastic particle black spot defect online detection method based on deep learning. Performing non-linear space conversion on the original image, and separating a background field component and a significance component; constructing a reverse compensation item by using the background field component, carrying out dynamic gain correction on an original brightness channel, and carrying out multi-channel weighted fusion on the original brightness channel and the saliency component to generate a saliency feature map; inputting the saliency feature map into a multi-scale topology enhancement network, extracting edge distribution features, and performing closed contour extraction and Euclidean distance transformation to generate a topology thickness energy map; the high-frequency gradient magnitude of the original image is calculated, mask smoothing processing is carried out on the gradient of the black spot region by using the saliency feature map, and a joint dissipation field is constructed; and taking a local maximum value point in the topological thickness energy diagram as a morphology seed point, executing controlled watershed evolution under the topological constraint of the joint dissipation field, realizing boundary stripping of an adhesive particle region, and generating a particle morphology diagram.

The invention relates to the technical field of image recognition, in particular to a packaging film defect detection system based on image recognition, which comprises a candidate region extraction module, a form enhancement module, a feature extraction module, a fuzzy evaluation module and a defect judgment module. According to the method, a self-adaptive binarization value is generated by calculating a pixel local neighborhood gray average value and a standard deviation, background texture noise and illumination non-uniform interference are effectively suppressed by using a dynamic threshold, a defect entity contour is reconstructed by combining polygonal broken line approximation and morphological filling operation, key geometric angular points are reserved, and internal fracture textures are repaired. Constructing a multi-dimensional feature vector set covering a texture energy entropy value and illumination uniformity, deeply analyzing a defect surface microscopic optical structure, introducing a Gaussian fuzzy membership function and an information entropy weight distribution mechanism, objectively quantifying the affiliation probability of feature components to different defect categories, and determining the defect surface microscopic optical structure. The limitation of a single rigid criterion is broken through, and accurate classification of fuzzy boundary defects is realized.

The invention discloses a cell occlusion relation estimation method and system based on a pixel-level focus evaluation curve. The method comprises the following steps: acquiring a multi-focal plane cell image sequence of the same view at different focusing positions; performing cell instance segmentation on the image sequence to obtain a two-dimensional cell instance mask; calculating the definition value of each pixel in the mask on each focal plane, and constructing a pixel-level focus response curve; determining a focus depth interval of each pixel according to the peak position of the focus response curve and a preset relative threshold value; and comparing focus depth intervals of different cell pixels in the cell overlapping region, and judging the up-and-down shielding relationship between the cells. According to the method, automatic analysis from the original microscopic data to the cell upper and lower layer relation is realized through pixel-level depth modeling and interval comparison, the spatial resolution and credibility of occlusion relation judgment are improved, the compatibility with a conventional microscopic imaging process is high, and deployment and popularization are easy.

The invention provides a method for identifying a microscopic association body structure in a heavy oil molecule simulation trajectory, which comprises the following steps of: analyzing a molecular dynamics trajectory, identifying an aromatic ring structure in a heavy oil molecule component, calculating a geometric center of the aromatic ring structure, combining a periodic boundary condition, and applying an improved DBSCAN clustering algorithm to realize automatic identification and clustering of an association body; and performing post-processing optimization on the clustering result, merging the shared clusters to generate a final association body set, and analyzing the number, size distribution, morphological characteristics and dynamic evolution information of the association bodies based on the structural characteristics of the final association body set. The method can accurately capture pi-pi accumulation behaviors of heavy oil molecules, further reveals morphological characteristics and dynamic evolution laws of heavy oil microassociates and influences of the heavy oil microassociates on the apparent viscosity of heavy oil, provides theoretical support for heavy oil viscosity-causing mechanism analysis and viscosity reducer design, can complement experimental research, and has a wide application prospect. And efficient development and green utilization of a complex thickened oil system are promoted.

The invention relates to a CACNA1A-based mental patient heart death intelligent identification system and method, the system comprises an immunohistochemical staining device, an image acquisition unit, an image analysis unit and an intelligent identification unit, the immunohistochemical staining device is used for performing CACNA1A immunohistochemical staining on formalin-fixed paraffin-embedded heart tissue slices; the image acquisition unit is used for shooting and obtaining a heart tissue CACNA1A immunohistochemical staining image; the image analysis unit is used for processing the heart tissue CACNA1A immunohistochemical staining image so as to determine a tissue staining region and image features thereof; and the intelligent identification unit outputs an identification prediction result of heart death of the mental patient according to the image features of the tissue staining region. Compared with the prior art, the mental patient heart death identification system can intelligently and accurately identify mental patient heart death.

The invention belongs to the technical field of medical diagnosis, and discloses a quantum multicolor immune digital pathological diagnosis analysis system, which comprises the following steps: acquiring high-resolution digital images of an immunohistochemical or immunofluorescence slice and a slide, and analyzing multicolor signal distribution in the images to obtain a quantum chromatographic image set; pixel-level color separation and intensity quantization are carried out on the quantum chromatographic image set, and a quantum intensity index set of each pixel is generated; performing multi-target color overlay analysis and post-translational modification protein specificity evaluation on the quantum intensity index set to construct a multi-color modification index set; identifying a single cell boundary and a multi-cell community based on the multicolor modification index set, and extracting a cell morphological parameter and a spatial adjacency relation to obtain a cell quantum analysis set; performing consistency correction and traceable recording by applying an automatic quality control mechanism, and generating a digital diagnosis report; the accuracy of accurate qualitative and quantitative analysis of immunohistochemistry and immunofluorescence is greatly improved.

The invention belongs to the technical field of image analysis, and particularly discloses an acute leukemia classification method and system based on frequency domain attention and multi-scale fusion, and the method comprises the following steps: collecting an acute leukemia microscopic image of a patient, inputting the acute leukemia microscopic image into a deep residual network ResNet50 backbone network, a frequency domain attention module DCT is introduced into a plurality of deep processing stages, an efficient multi-scale attention module EMA is introduced between the last-stage deep processing stage and the frequency domain attention module, and a subnet is remodeled through channel grouping; the output ends of all the frequency domain attention modules are input into the multi-scale feature pyramid network, and a fusion feature set is extracted; features extracted by the backbone network and the multi-scale feature pyramid network are fused, a full-connection classification head is input, and a classification result is output. By the adoption of the technical scheme, the problems that a traditional network is weak in tiny feature extraction capacity and a model is insufficient in multi-scale feature fusion are solved, and a more accurate classification result is obtained.

The invention discloses a coke microscopic optical tissue extraction method based on a multi-attention neural network, and the method comprises the following steps: obtaining and cutting a coke microscopic image, and constructing a data set containing a manually labeled optical tissue label and a background label; dividing the data set into a training set, a verification set and a test set, and performing data enhancement on the training set; constructing a multi-attention U-shaped neural network model, wherein the multi-attention U-shaped neural network model comprises an encoder, a bridging module, a bottleneck module and a decoder which are connected in sequence; a training set is adopted to train the multi-attention U-type neural network model, multi-scale prediction masks are generated at all stages of a decoder through a deep supervision mechanism, and the multi-scale prediction masks and final output jointly participate in loss function calculation; and inputting a to-be-processed coke microscopic image into the trained multi-attention U-shaped neural network model, and outputting an optical tissue extraction result.

The invention discloses a salt lake carbonate rock multi-parameter quantitative classification and reservoir evaluation method, and relates to the technical field of oil-gas exploration. The method comprises the following steps: selecting a key well in an exploration block, collecting a plurality of salt lake carbonate rock samples, preparing an analysis sample under an anhydrous condition, quantitatively measuring a salinity parameter, a mixing index and a diagenesis strength parameter by utilizing the analysis sample, and determining a salinity code, a mixing code and a diagenesis phase code. And naming the salt lake carbonate rock based on the salinity code, the mixed product code and the lithogenous phase code, directly evaluating the salt lake carbonate rock reservoir according to a naming result, and performing single well comprehensive evaluation on the salt lake carbonate rock reservoir. According to the method, the influence of salinity, mixed accumulation and diagenesis strength on formation and evolution of the salt lake carbonate rocks is fully considered, accurate division of the types of the salt lake carbonate rocks is achieved, the reservoir naming result is directly associated with reservoir evaluation, and technical support is provided for standardized evaluation of the salt lake carbonate reservoir.

The invention provides a chromosome image enhancement method and system based on semantic guidance. The method comprises the following steps: S1, preprocessing; s2, outputting a deep-band probability graph, a grey-band probability graph and a shallow-band probability graph through a semantic segmentation network composed of a lightweight encoder and a multi-scale decoder; s3, implementing differential layered enhancement according to a band type: adopting local adaptive histogram equalization for a deep band, adopting central axis constraint bilateral filtering for a gray band, adopting dynamic threshold truncation and gamma correction for a shallow band, and performing weighted fusion for a transition region according to probability; s4, carrying out structure strengthening, wherein the structure strengthening comprises centromere local sharpening, stripe phase alignment, edge sensing super-resolution and overlapping region separation; and S5, performing quality evaluation based on the deep band integrity, the band stripe contrast uniformity, the SSIM and the noise density, and triggering adaptive re-enhancement if necessary. According to the scheme, the contrast ratio and details are remarkably improved while the stripe structure and the position relation are kept, and the method has the advantages of light weight, interpretability and cross-sample robustness and is suitable for being integrated into an automatic karyotype analysis process.

The invention relates to the technical field of image analysis, in particular to a targeted drug curative effect prediction method based on image recognition, which comprises the following steps: acquiring tissue images and nuclear morphological parameters by a microscope, establishing a database in combination with transcripts, extracting an injury area, recognizing image features through a convolutional neural network, and constructing a prediction model; and inputting candidate drug molecular structures for molecular docking, calculating a repair progress by combining animal verification to establish a curative effect model, predicting drug scores and response time based on the curative effect model to generate a ranking list, screening high-score drug cells, verifying monitored survival, comparing, predicting and outputting a result. The method comprises the following steps: extracting a cell nucleus form, revealing a relation between damage and molecular abnormality in combination with a transcriptome, identifying a target spot corresponding to an abnormal mode and pathological change through deep learning, performing affinity prediction and animal verification on a drug structure, quantifying the repair progress by adopting image difference, and evaluating the curative effect with two dimensions of structure and function. And curative effect scores and response prediction are output to realize system sequencing, so that drug screening is more accurate and practical.

The application discloses a kind of visual-based end mill flank wear detection method and its image acquisition device, method includes fixing tool on the tool holder of image acquisition device, and the wear area of tool is observed by microscope of image acquisition device and S is photographed End mill flank wear picture under multiple shooting angles;Contrast the topography of tool flank face in the picture shot before and after wear, measure the wear of tool flank face in the picture shot, obtain S group of tool wear data under different shooting angles;Establish the mathematical model of tool wear and shooting angle, solve the only fitting function describing the change of tool wear with shooting angle;Draw the image of fitting function y (x) in the shooting range K, solve image peak value.The maximum wear of tool can be obtained simply, intuitively and accurately by the application.Under the premise of image acquisition automation, automatic measurement of tool wear can be realized, and has high engineering application value.

The invention relates to a hyperspectral bacteria classification method based on lightweight deep learning and membership width learning, and belongs to the technical field of hyperspectral image processing and microbiological detection. The method comprises the following steps: collecting hyperspectral image data of food-borne pathogenic bacteria, and carrying out correction and region-of-interest extraction to obtain bacterial spectral data; the method comprises the following steps: preprocessing bacterial spectral data by using a fractional differential method, enhancing spectral features and suppressing noise to obtain enhanced spectral data, and inputting the enhanced spectral data into a lightweight deep network to extract multilevel space-spectral features to obtain depth features; inputting the depth features into a membership width learning module, and outputting a bacterial category classification result; wherein the membership width learning module comprises operations of defining a membership function, constructing a fuzzy score membership matrix and optimizing a width learning weight matrix. The objective of the invention is to solve the technical problems of insufficient feature extraction, outlier interference and high model complexity in hyperspectral bacterial classification in the prior art.

The invention relates to the technical field of microbiological detection and image detection, and provides a microwell plate microbiological growth state detection method, system and equipment based on artificial intelligence. The system comprises an image acquisition module, an image segmentation module, a data set construction module, an image data enhancement module, an image classification module, a classification result determination module and a reasoning module, and is used for detecting whether bacteria grow in the microwell plate; or the system comprises an image regression module and a regression error evaluation module and is used for detecting the biomass of the thalli. According to the invention, a self-built photographing device can be adopted to realize on-site direct automatic detection without sampling, so that high-throughput automatic accurate analysis of the growth state of microorganisms in the microwell plate can be conveniently and quickly realized, experiment consumables and biological samples can be saved, the contamination risk can be reduced, and the experiment efficiency can be remarkably improved. Therefore, the working intensity of detection personnel is reduced, and the method has wide application value. Meanwhile, the complexity of detecting the growth state of the microorganisms in the pore plate is reduced, and popularization and application are facilitated.

The invention discloses a disease diagnosis method and system based on multi-modal space-frequency domain adaptive fusion, and relates to the field of artificial intelligence and biomedical engineering.The method comprises the steps that multi-modal data are standardized, the unified and standardized multi-modal data are coded, and multi-modal initial feature representation is obtained; after projection and gating alignment and cross-modal interactive attention alignment are carried out on the initial feature representation of each modal, enhanced representations of each modal are obtained, and then the enhanced representations of each modal are fused into a shared feature representation; performing deep feature extraction on the enhanced representation of each mode to obtain deep features of each mode, and performing adaptive multi-domain feature enhancement processing to obtain multi-domain enhanced features of each mode; performing semantic alignment on the multi-domain enhanced features of each mode, and then performing fusion through a hierarchical attention mechanism to obtain fusion features; and the fusion features are input into a diagnosis network for prediction, a disease diagnosis result is obtained, and the intelligent diagnosis precision and robustness of papillary thyroid carcinoma are improved.

Disclosed are a method, a device, and an information processing program for determining, by using refractive index distribution data pertaining to an object to be observed, the region of a cell that has undergone programmed cell death in the object to be observed.

Disclosed is a computer-implemented method which encompasses registering a tracked imaging device such as a microscope having a known viewing direction and an atlas to a patient space so that a transformation can be established between the atlas space and the reference system for defining positions in images of an anatomical structure of the patient. Labels are associated with certain constituents of the images and are input into a learning algorithm such as a machine learning algorithm, for example a convolutional neural network, together with the medical images and an anatomical vector and for example also the atlas to train the learning algorithm for automatic segmentation of patient images generated with the tracked imaging device. The trained learning algorithm then allows for efficient segmentation and / or labelling of patient images without having to register the patient images to the atlas each time, thereby saving on computational effort.