Abstract: An image processing device includes: a processor; and a memory encoded with instructions executed by the processor, including: imaging pluripotent stem cells with time in a culture process and acquiring a plurality of images, extracting a colony region of the cells from the image, extracting a high luminance region on the basis of a group of pixels with larger luminance values than a standard value from among pixels constituting the image, extracting an extraction target region with relatively high contrast in the colony region on the basis of the colony and high luminance regions, and outputting the extraction target region as an extraction result, wherein as a relationship among the colony, high luminance, and extraction target regions, the colony region is formed, the high luminance region is then formed therein, and the extraction target region is then formed in the high luminance region in the culture process of the cells.

Abstract: Systems and methods for denoising a magnetic resonance (MR) image utilize an unsupervised deep convolutional neural network (U-DCNN). Magnetic resonance (MR) image data of an area of interest of a subject can be acquired, which can include noisy input images that comprise noise data and noise free image data. For each of the noisy input images, iterations can be run of a converging sequence in an unsupervised deep convolutional neural network. In each iteration, parameter settings are updated; the parameter settings are used in calculating a series of image feature sets with the U-DCNN. The image feature sets predict an output image. The converging sequence of the U-DCNN is terminated before the feature sets predict a respective output image that replicates all of the noise data from the noisy input image. Based on a selected feature set, a denoised MR image of the area of interest of the subject can be output.

Abstract: Disclosed is a fluorescence image analyzing apparatus including a light source that emits light to a sample including a plurality of cells labeled with a fluorescent dye at a target site, an imaging unit that captures a fluorescence image of each of the cells that emit fluorescence by being irradiated with the light, a fluorescence image of the cell, and a processing unit that processes the fluorescence image captured by the imaging unit to acquire a bright spot pattern of fluorescence in the fluorescence image. The processing unit selects a reference pattern corresponding to a measurement item of the sample from a plurality of reference patterns corresponding to a plurality of measurement items and generates information used for determination of the sample based on the bright spot pattern of fluorescence in the fluorescence image and the selected reference pattern.

Abstract: A device includes: a distribution information acquiring part configured to acquire, based on an image in which a plurality of cells that are cultivated in a predetermined area are imaged, distribution information relating to a distribution in the predetermined area of the plurality of cells; and a determination part configured to determine a cultivated state of the plurality of cells based on the distribution information acquired by the distribution information acquiring part.

Abstract: Provided is a weakly supervised pathological image tissue segmentation method based on an online noise suppression strategy, including: acquiring a hematoxylin-eosin (H&E) stained graph, processing the H&E stained graph to obtain a data set, dividing the data set, training a classification network based on a divided data set, and generating a pseudo-label; suppressing a noise existing in the pseudo-label based on the online noise suppression strategy, and training a semantic segmentation network through the pseudo-label after noise suppression and a training set corresponding to the pseudo-label to obtain a prediction result of the semantic segmentation network after the training, and taking the prediction result as a final segmentation result.

Abstract: Embodiments include accessing an image of a region of tissue demonstrating cancerous pathology; detecting a plurality of cells represented in the image; segmenting a cellular nucleus of a first member of the plurality of cells and a cellular nucleus of at least one second, different member of the plurality of cells; extracting a set of nuclear morphology features from the plurality of cells; constructing a feature driven local cell graph (FeDeG) based on the set of nuclear morphology features and a spatial relationship between the cellular nuclei using a mean-shift clustering approach; computing a set of FeDeG features based on the FeDeG; providing the FeDeG features to a machine learning classifier; receiving, from the machine learning classifier, a classification of the region of tissue as a long-term or a short-term survivor, based, at least in part, on the set of FeDeG features; and displaying the classification.

Abstract: Detecting cells depicted in an image using RNA segmentation can include obtaining a FISH image of a tissue that depicts multiple cells, obtaining a nuclear stained image of the tissue, and generating a mask that includes multiple areas that each have a position with respect to the tissue by enhancing structures depicted in the FISH image. Edges depicted in the enhanced FISH image are detected to use for the mask, and positions are determined for a first plurality of regions that fit potential nuclei depicted in the nuclear stained image. A second plurality of regions are selected from the first plurality by determining, using the mask, which regions from the first plurality overlap with the position of an area from multiple areas in the mask. Unique nuclei in the tissue are labelled using the second plurality of regions that each indicate a potential nuclei in the tissue.

Abstract: Techniques for acquiring focused images of a microscope slide are disclosed. During a calibration phase, a “base” focal plane is determined using non-synthetic and/or synthetic auto-focus techniques. Furthermore, offset planes are determined for color channels (or filter bands) and used to generate an auto-focus model. During subsequent scans, the auto-focus model can be used to quickly estimate the focal plane of interest for each color channel (or filter band) rather than re-employing the non-synthetic and/or synthetic auto-focus techniques.

Abstract: A telepresence device may relay video, audio, and/or measurement data to a user operating a control device. A user interface may permit the user to quickly view and/or understand temporally and/or spatially disparate information. The telepresence device may pre-gather looped video of spatially disparate areas in an environment. A temporal control mechanism may start video playback at a desired point hi a current or historical video segment. Notations may be associated with time spans in a video and recalled by capturing an image similar to a frame in the time span of the video. An area of interest may be selected and video containing the area of interest may be automatically found. Situational data may be recorded and used to recall video segments of interest. The telepresence device may synchronize video playback and movement. A series of videos may be recorded at predetermined time intervals to capture visually trending information.

Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.

Abstract: The present disclosure is directed to multiplex assays, kits and methods, including automated methods, for identifying PD-L1 positive immune cells, PD-L1 positive tumor cells, and PD-L1 negative immune cells within a tissue sample using two dyes selected from diaminobenzidine (DAB), 4-(dimethylamino) azobenzene-4?-sulfonamide (DABSYL), tetramethylrhodamine (DISCOVERY Purple), N,N?-biscarboxypentyl-5,5?-disulfonato-indo-dicarbocyanine (Cy5), and Rhodamine 110 (Rhodamine).

Abstract: A method of generating an image of a sample is provided. The method comprises providing a plurality of photon detectors, scanning the sample with an excitation beam over a predetermined time period, the detectors receiving photons emitted by the sample due to the excitation during the time period. A plurality of intensity images associated with each of the detectors are generated, each being proportional to the mean number of photons detected per unit time. A plurality of correlation images associated with each combination of two of the detectors are generated, each of the correlation images being proportional to the variance of the distribution of detected photons per unit time. The image of the sample is generated using joint sparse recovery from the plurality of intensity and correlation images, wherein the intensity and correlation images have common support.

Abstract: A method for detecting cytopathic effect (CPE) in a well sample includes generating a well image depicting a well containing cells and a medium (and possibly viruses), and pre-processing the well image at least by partitioning the well image into sub-images each corresponding to a different portion of the well. The method also includes, for each of some or all of the sub-images, determining, by analyzing the sub-image using a convolutional neural network, a respective score indicative of a likelihood that any cells in the portion of the well corresponding to the sub-image exhibit CPE. The method further includes determining a CPE status of the cells contained in the well based on the respective scores for the sub-images, and generating output data indicating the CPE status.

Abstract: A method and device for detecting circulating abnormal cells. The method for detecting the circulating abnormal cells comprises: respectively segmenting and labelling, by using an image processing algorithm and a morphological algorithm, cell nuclei included in dark field microscope images of a plurality of probe channels (101); inputting the dark field microscope images, in which cell nuclei are labelled, of the plurality of probe channels into a pre-built circulating abnormal cell detection model to acquire the number of staining signals included in each labelled cell nucleus in the dark field microscope image of each probe channel (102); and for each labelled cell nucleus, on the basis of the number of the staining signals included in the labelled cell nucleus in the acquired dark field microscope image of each probe channel, determining whether the labelled cell nucleus belongs to a circulating abnormal cell (103).

Abstract: Methods, systems, and computer readable media for 3D printing from images, e.g., medical images or images obtained using any appropriate volumetric imaging technology. In some examples, a method includes receiving, from a medical imaging device, a multi-dimensional image of a structure. The method includes, for each two dimensional (2D) slice of the multi-dimensional image, converting, row-by-row for each row of the 2D slice, voxels of the 2D slice into 3D printing instructions for the 2D slice. The method includes 3D printing, by controlling a 3D printing extruder, a physical model based on the structure by 3D printing, slice by slice, each 2D slice using the 3D printing instructions.

Abstract: This invention relates to a hyperspectral imaging system for denoising and/or color unmixing multiple overlapping spectra in a low signal-to-noise regime with a fast analysis time. This system may carry out Hyper-Spectral Phasors (HySP) calculations to effectively analyze hyper-spectral time-lapse data. For example, this system may carry out Hyper-Spectral Phasors (HySP) calculations to effectively analyze five-dimensional (5D) hyper-spectral time-lapse data. Advantages of this imaging system may include: (a) fast computational speed, (b) the ease of phasor analysis, and (c) a denoising algorithm to obtain the minimally-acceptable signal-to-noise ratio (SNR). An unmixed color image of a target may be generated. These images may be used in diagnosis of a health condition, which may enhance a patient's clinical outcome and evolution of the patient's health.

Abstract: A method for creating training data for an artificial intelligence system to classify hyperspectral data. The method including receiving a hyperspectral image from a data source, wherein the hyperspectral image includes a first pixel group associated with a first classification, forming from the hyperspectral image a first augmented image using a first augmentation algorithm and a second augmented image using a second augmentation algorithm, selecting a first group of sample pixels from the hyperspectral image, the first augmented image and the second augmented image, wherein each pixel of the selected first group of sample pixels is having an association with the first classification or with a second classification and providing the selected first group of sample pixels and the associated classifications of each pixel for an artificial training system to be used as a training data.

Abstract: A method for identifying candidate target cells within a biological fluid specimen includes a digital image of the biological fluid specimen with the digital image having a plurality of color channels, identifying first connected regions of pixels of a minimum first intensity in a first channel, identifying second connected regions of pixels of a minimum second intensity in a second channel, and determining first connected regions and second connected regions that spatially overlap. For a pair of a first connected region and a second connected region that spatially overlap, whether the second connected region overlaps the first connected region by a threshold amount is determined, and if the second connected region overlaps the first connected region by the threshold amount then the portion of the image corresponding to the overlap is continued to be treated as a candidate for classification.

Abstract: A method for identifying and enumerating candidate target cells within a biological fluid specimen is described. The method includes obtaining a biological fluid specimen, preparing the biological fluid specimen by staining cell features in the biological fluid specimen, capturing a digital image having a plurality of color channels of the biological fluid specimen, and applying image analysis to the digital image. A computer program product for identifying candidate target cells within a biological fluid specimen is also described. The computer program comprises instructions to cause a processor to carry out the image analysis.

Abstract: An image capturing module receives a predetermined number of a first set of frames by calibration of the image capturing device. An image processing module calculates focal values of each of the predetermined number of the first set of frames using a focal value calculation technique, identifies a predefined threshold of the focal value among each of the focal values calculated, determines a reference frame among each of the predetermined number of the first set of frames. An image comparison module compares focal value of one or more live frames with the focal value of reference frame, selects an optimal live frame from the one or more live frames when the focal value of the one or more live frames is greater than predefined percentage of the focal value of the reference frame. A notification module notifies an achievement of an optimal focal value range corresponding to the optimal live frame to an operator through one or more notification means.

Abstract: A computer device segments a first sample region to obtain a candidate image region set that includes a plurality of candidate image regions, For each of the candidate image regions, the device obtains a first relationship degree corresponding to each candidate image region and obtains a second relationship degree corresponding to the candidate image region. The device obtains a relationship degree change value based on the first relationship degree and the second relationship degree. The device selects, from the plurality of candidate image regions, a first candidate image region as a target image region in accordance with a determination that the first candidate image region satisfies a condition in the relationship degree change value. The device performs model training based on the target image region to obtain a target detection model.

Abstract: A quantitative phase image generating method for a microscope, includes: irradiating an object with illumination light; disposing a focal point of an objective lens at each of a plurality of positions that are mutually separated by gaps ?z along an optical axis of the objective lens, and detecting light from the object; generating sets of light intensity distribution data corresponding to each of the plurality of positions based upon the detected light; and generating a quantitative phase image based upon the light intensity distribution data; wherein the gap ?z is set based upon setting information of the microscope.

Abstract: An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of non-overlapping image tiles. Bags of tiles are created through sampling of the image tiles. For each H&E stain image, the system generates a feature vector from a bag of tiles sampled from the partitioned image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. With the trained models, the analytics system predicts a hormone receptor status by applying a prediction model to the feature vector for a test H&E stain image.

Abstract: A cell image analysis method may include: obtaining, for each of cell images, a value of a feature parameter to be used in determination of a type of a cell, by analyzing the cell images; and displaying the value of the feature parameter in association with the each of the cell images.

Abstract: A system and method for image-guided microscopic illumination are provided. A processing module controls an imaging assembly such that a camera acquires an image or images of a sample in multiple fields of view, and the image or images are automatically transmitted to a processing module and processed by the first processing module automatically in real-time based on a predefined criterion so as to determine coordinate information of an interested region in each field of view. The processing module also controls an illuminating assembly to illuminate the interested region of the sample according to the received coordinate information regarding to the interested region, with the illumination patterns changing among the fields of view.

Abstract: Systems and methods for predicting images with enhanced spatial resolution using a neural network are provided herein. According to an aspect of the invention, a method includes accessing an input image of a biological sample, wherein the input image includes a first spatial resolution and a plurality of spectral images, and wherein each spectral image of the plurality of spectral images includes data from a different wavelength band at a different spectral channel; applying a trained artificial neural network to the input image; generating an output image at a second spatial resolution, wherein the second spatial resolution is higher than the first spatial resolution, and wherein the output image includes a fewer number of spectral channels than the plurality of spectral images included in the input image; and outputting the output image.

Abstract: Embodiments of the present systems and methods may provide imaging techniques for multidirectional imaging, light conditioning, illumination sequences, or machine learning to create algorithms created from training by other advanced imaging techniques. In an embodiment, a method for generating an image may comprise obtaining an image of an object produced by a camera and generating, from the obtained image produced by a conventional camera, using an artificial intelligence model and imaging process, an output image including additional information similar to additional information present in an image of the object produced by an advanced imaging system.

Abstract: A hyperspectral imaging spectrophotometer and system, with calibration, data collection, and image processing methods designed to match human visual perception and color matching of complex colored objects.

Abstract: Methods are provided to project depth-spanning stacks of limited depth-of-field images of a sample into a single image of the sample that can provide in-focus image information about three-dimensional contents of the image. These methods include applying filters to the stacks of images in order to identify pixels within each image that have been captured in focus. These in-focus pixels are then combined to provide the single image of the sample. Filtering of such image stacks can also allow for the determination of depth maps or other geometric information about contents of the sample. Such depth information can also be used to inform segmentation of images of the sample, e.g., by further dividing identified regions that correspond to the contents of the sample at multiple different depths.

Abstract: A system and method for developing applications (Apps) for automated assessment and analysis of processed biological samples. Such samples are obtained, combined with nutrient media and incubated. The incubated samples are imaged and the image information is classified according to predetermined criteria. The classified image information is then evaluated according to Apps derived from classified historical image information in a data base. The classified historical image information is compared with the classified image information to provide guidance on further processing of the biological sample through Apps tailored to process provide sample process guidance tailored to the classifications assigned to the image information.

Abstract: A visual analysis method for cable element identification includes steps of constructing and labeling a picture data set, preparing a training data set and training a model, to train the preset identification and analysis model, such that the preset identification and analysis model can have accuracy of identification of cable elements; then, cable element information existing in a target image screen is identified by the completely trained preset identification and analysis model, so as to label a target picture; in the analysis method, the produced and manufactured cable elements can be shot, and then, shot pictures are identified and analyzed by using the preset identification and analysis model, such that a structural quality condition of each cable element is rapidly and comprehensively determined, possible structural defects of each cable element can be conveniently and accurately known, and the cable elements with unqualified quality can be screened out in time.

Abstract: The present disclosure provides a rapid three-dimensional imaging system based on a multi-angle 4Pi microscope. The system includes: an illumination module, configured to obtain a parallel light of which a size covering a projection surface of a spatial light modulator; a wavefront modulation module, configured to place the LCOS device on a Fourier plane of an illumination end; a two-dimensional scanning module, configured to control a light beam to realize a two-dimensional scanning on an object plane; an illumination interference module, configured to generate point spread function PSFs of a 4Pi through an illumination interference to irradiate a fluorescent sample; an imaging module, configured to acquire interference images of two fluorescent signals; and a controller, configured to control the wavefront modulation module to adjust a polarization direction of the light to generate PSFs of the 4Pi with different inclination angles.

Abstract: A method of using a machine learning model to output a task-specific prediction may include receiving a digitized cytology image of a cytology sample and applying a machine learning model to isolate cells of the digitized cytology image. The machine learning model may include identifying a plurality of sub-portions of the digitized cytology image, identifying, for each sub-portion of the plurality of sub-portions, either background or cell, and determining cell sub-images of the digitized cytology image. Each cell sub-image may comprise a cell of the digitized cytology image, based on the identifying either background or cell. The method may further comprise determining a plurality of features based on the cell sub-images, each of the cell sub-images being associated with at least one of the plurality of features, determining an aggregated feature based on the plurality of features, and training a machine learning model to predict a target task based on the aggregated feature.

Abstract: A Computer Aided Diagnosis, CADx, system (200) is described that comprises: at least one input (210, 212, 214) configured to provide at least one input medical image; and a CADx processing engine (220) configured to receive and process the at least one input medical image and produce at least one CADx score. A CADx score mapping circuit is operably coupled to the CADx processing engine (220) and configured to: map the at least one CADx score to a risk adjusted virtual score; and generate an output (235) of at least the risk adjusted virtual score associated with the processed at least one input medical image. The at least one CADx score and the risk adjusted virtual score correspond to an equivalent risk of condition or disease associated with a patient.

Abstract: A method for video object detection includes detecting an object in a first video frame, and selecting a first interest point and a second interest point of the object. The first interest point is in a first region of interest located at a first corner of a box surrounding the object. The second interest point is in a second region of interest located at a second corner of the box. The second corner is diagonally opposite the first corner. A first optical flow of the first interest point and a second optical flow of the second interest point are determined. A location of the object in a second video frame is estimated by determining, in the second video frame, a location of the first interest point based on the first optical flow and a location of the second interest point based on the second optical flow.

Abstract: A generalizable and interpretable deep learning model for predicting biomarker status and biomarker metrics from histopathology slide images is provided.

Abstract: Embodiments discussed herein facilitate building and/or employing model(s) for determining tumor prognoses based on a combination of radiomic features and pathomic features. One example embodiment can perform actions comprising: providing, to a first machine learning model, at least one of: one or more intra-tumoral radiomic features associated with a tumor or one or more peri-tumoral radiomic features associated with a peri-tumoral region around the tumor; receiving a first predicted prognosis associated with the tumor from the first machine learning model; providing, to a second machine learning model, one or more pathomic features associated with the tumor; receiving a second predicted prognosis associated with the tumor from the second machine learning model; and generating a combined prognosis associated with the tumor based on the first predicted prognosis and the second predicted prognosis.

Abstract: A mask structure optimization device includes a classification target image size acquisition unit that is configured to acquire a size of a classification target image which is an image including a classification target, a mask size setting unit that is configured to set a size of a mask applied to the classification target image, a brightness detection unit that is configured to detect a brightness of each pixel within the classification target image at a position on an opposite side of the mask from the classification target image, a sum total brightness calculation unit that is configured to calculate the sum total brightness of the each pixel within the classification target image detected by the brightness detection unit, an initial value setting unit that is configured to set an initial value for a mask pattern of the mask, and a movement unit that is configured to relatively move the mask with respect to the classification target image.

Abstract: A surgical specimen imaging system includes a micro-X-ray computed tomography (CT) unit for CT imaging of the specimen and a structured light imaging (SLI) unit for optical imaging at multiple wavelengths, multiple phase offsets, and multiple structured-light pattern periods including unstructured light. The system's image processing unit receives CT and optical images and is configured by firmware in memory to co-register the images and process the optical images to determine texture at multiple subimages of the optical images, determined textures forming a texture map. The texture map is processed by a machine-learning-based classifier to determine a tissue type map of the specimen, and the tissue type map is processed with the CT images to give a 3D tissue-type map. In embodiments, the firmware extracts optical properties including scattering and absorption at multiple wavelengths and the classifier also uses these properties in generating the tissue type map.

Abstract: Various implementations disclosed herein include devices, systems, and methods that complete content for a missing part of an image of an environment. For example, an example process may include obtaining an image including defined content and missing parts for which content is undefined, determining a spatial image transformation for the image based on the defined content and the missing parts of the image, altering the image by applying the spatial image transformation, and completing the altered image.

Abstract: A storage assembly for storing a plurality of specimens includes a frame, a plurality of modular storage units for perfusion and/or incubation of one or more specimens removably coupled to the frame, a sample transfer apparatus configured to retrieve a specimen holder from a chosen modular storage unit of the plurality of modular storage units, and a control unit communicatively coupled to the sample transfer apparatus. The control unit is configured to cause the sample transfer apparatus to retrieve a specimen from a modular storage unit of the plurality of modular storage units and deliver the specimen to a delivery position.

Abstract: The invention is notably directed to a computer-implemented method for normalizing medical images, e.g., whole slide images. This method includes steps performed for each image of a first subset of images of a dataset. Actual quantities are estimated for each image, including actual stain vectors and, possibly, robust maximum stain concentrations (typically hematoxylin and eosin stain vectors and concentrations). The actual quantities estimated are assessed by comparing them to reference data based on reference quantities estimated for one or more images of a second subset of images of the dataset, where the second subset of images differ from the first subset of images. The reference quantities include reference stain vectors. For each image, either the actual quantities or the reference quantities for the dataset are selected as effective quantities, based on an outcome of the previous assessment of the actual quantities. Each image is then normalized.

Abstract: Disclosed herein are systems, methods and computer-program products to create synthetic immunohistochemistry (IHC) stained digital slides generated using artificial neural networks (ANNs). In some implementations, the created digital slides can be used as a ground truth to evaluate a method of analyzing IHC stained tissues.

Abstract: The present application provides a convolution calculation method, a convolution calculation apparatus, a terminal device, and a computer readable storage medium. The method includes: inputting an image to be processed into a deep learning model, and obtaining a to-be-blocked convolution group and a target size of a block from all convolution layers of the deep learning model; blocking all input channel data of a first to-be-blocked convolution layer in said convolution group according to the target size, a size of each block being the target size; obtaining an output result of said convolution group according to all blocks of all input channel data of said first convolution layer; inputting the output result of said convolution group to a specified network of the deep learning model. Sizes of blocks of the to-be-blocked convolution layer and bandwidth consumption can be adjusted to adapt to frequently updating and upgrading the deep learning model.

Abstract: Provided is a novel cell sheet evaluation method. A cell sheet evaluation method includes: a step of analyzing, based on an observed image of a cell sheet, a characteristic indicating shape uniformity of cells constituting the cell sheet; and a step of evaluating a binding state between cells in the cell sheet based on the analysis result.

Abstract: An automated method and system for determining the risk of developing a cancer in a subject, the method comprising preparing a tissue sample obtained from the subject for visually identifying at least one biological marker associated with the cancer, digitally scanning the prepared tissue sample, analyzing the scanned image of the tissue sample to identify regions of interest, quantifying at least one parameter associated with the marker, and executing an algorithm using the quantified parameter to calculate a risk score, wherein the risk score is representative of the risk of the individual developing the cancer.

Abstract: Embodiments include controlling a processor to perform operations, the operations comprising accessing a digitized image of a region of tissue (ROT) demonstrating cancerous pathology; extracting a set of radiomic features from the digitized image, where the set of radiomic features are positively correlated with programmed death-ligand 1 (PD-L1) expression; providing the set of radiomic features to a machine learning classifier; receiving, from the machine learning classifier, a probability that the region of tissue will experience cancer recurrence, where the machine learning classifier computes the probability based, at least in part, on the set of radiomic features; generating a classification of the region of tissue as likely to experience recurrence or non-recurrence based, at least in part, on the probability; and displaying the classification and at least one of the probability, the set of radiomic features, or the digitized image.

Abstract: An ensemble learning prediction method includes: establishing a plurality of base predictors based on a plurality of training data; initializing a plurality of sample weights of a plurality of sample data and initializing a processing set; in each iteration round, based on the sample data and the sample weights, establishing a plurality of predictor weighting functions of the predictors in the processing set and predicting each of the sample data by each of the predictors in the processing set for identifying a prediction result; evaluating the predictor weighting functions, and selecting a respective target predictor weighting function from the predictor weighting functions established in each iteration round and selecting a target predictor from the predictors in the processing set to update the processing set and to update the sample weights of the sample data.

Abstract: There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.

Abstract: A method and apparatus of a device that classifies a mesothelioma image is described. In an exemplary embodiment, the device segments the mesothelioma image into a region of interest that includes information useful for classification, and a background region, by applying a first convolutional neural network. In addition, the device tiles the region of interest into a set of tiles. For each tile, the device extracts a feature vector of that tile by applying a second convolutional neural network, where the features of the feature vectors represent local descriptors of the tile. Furthermore, the device processes the extracted feature vectors of the set of tiles to classify the image.