Abstract: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object.

Abstract: An image processing system is provided. The image processing system includes a display, a processor, and a memory. The memory stores processor-executable code that when executed by the processor causes receiving an image of a region of interest of a patient with an enteric tube or line disposed within the region of interest, detecting the medical tube or line within the image, generating a combined image by superimposing graphical markers on the image that indicate placement or misplacement of the enteric tube or line, and displaying the combined image on a display. In further aspects, a classification of the enteric tube or line (e.g., correctly placed tube present, malpositioned tube present, and so forth) may be determined and communicated to one or more clinicians. Additionally, the outputs of the image processing system may also be provided to facilitate triage of patients, helping prioritize which tube placements require further attention and in what order.

Abstract: In various embodiments, a system can: access a failure image on which a first model has inaccurately performed an inferencing task; train, on a set of dummy images, a second model to learn a visual variety of the failure image, based on a loss function having a first term and a second term, the first term quantifying visual content dissimilarities between the set of dummy images and outputs predicted during training by the second model, and the second term quantifying, at a plurality of different image scales, visual variety dissimilarities between the failure image and the outputs predicted during training by the second model; and execute the second model on each of a set of training images on which the first model was trained, thereby yielding a set of first converted training images that exhibit the visual variety of the failure image.

Abstract: Systems/techniques that facilitate multi-layer image registration are provided. In various embodiments, a system can access a first image and a second image. In various aspects, the system can generate, via execution of a machine learning model on the first image and the second image, a plurality of registration fields and a plurality of weight matrices that respectively correspond to the plurality of registration fields. In various instances, the system can register the first image with the second image based on the plurality of registration fields and the plurality of weight matrices.

Abstract: Techniques are described for multi-task neural network model design using task crystallization are described. In one example a task crystallization method comprises adding one or more task-specific channels to a backbone neural network adapted to perform a primary inferencing task to generate a multi-task neural network model, wherein the adding comprises adding task-specific elements to different layers of the backbone neural network for each channel of the one or more task-specific channels. The method further comprises training, by the system, the one or more task-specific channels to perform one or more additional inferencing tasks that are respectively different from one another and the primary inferencing task, comprising separately tuning and crystallizing the task-specific elements of each channel of the one or more task-specific channels.

Abstract: Systems/techniques that facilitate multi-layer image registration are provided. In various embodiments, a system can access a first image and a second image. In various aspects, the system can generate, via execution of a machine learning model on the first image and the second image, a plurality of registration fields and a plurality of weight matrices that respectively correspond to the plurality of registration fields. In various instances, the system can register the first image with the second image based on the plurality of registration fields and the plurality of weight matrices.

Abstract: Systems/techniques that facilitate improved deep learning image processing are provided. In various embodiments, a system can access a medical image, wherein pixels or voxels of the medical image can be allocated among a plurality of regions. In various aspects, the system can generate, via execution of a deep learning neural network on the medical image, a set of region-wise parameter maps, wherein a region-wise parameter map can consist of one predicted parameter per region of the medical image. In various instances, the system can generate a transformed version of the medical image by feeding the set of region-wise parameter maps to an analytical transformation function. In various cases, the system can render the transformed version of the medical image on an electronic display. In various aspects, the plurality of regions can be irregular or tissue-based.

Abstract: Systems/techniques that facilitate deep learning image analysis with increased modularity and reduced footprint are provided. In various embodiments, a system can access medical imaging data. In various aspects, the system can perform, via execution of a deep learning neural network, a plurality of inferencing tasks on the medical imaging data. In various instances, the deep learning neural network can comprise a common backbone in parallel with a plurality of task-specific backbones. In various cases, the plurality of task-specific backbones can respectively correspond to the plurality of inferencing tasks.

Abstract: The invention relates to a method for a computer device, for detecting an optimal candidate compound based on a plurality of samples comprising a cell line and one or more biomarkers, and a plate map configuration, wherein the plate map configuration is providing locations of samples comprising cell lines exposed to one or more biomarkers and different concentrations of a candidate compound forming at least one concentration gradient, the candidate compound being comprised in a plurality of candidate compounds, said method comprising generating (310) phenotypic profiles of each concentration gradient of each of the plurality of candidate compounds at a plurality of successive points in time to form a plurality of compound profiles, wherein generating phenotypic profiles comprises the steps obtaining (312) image data depicting each sample comprised in the concentration gradient, generating (314) a class-label and a class for each cell of the samples based on the image data, detecting (320) the optimal candidat

Abstract: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object.

Abstract: Systems/techniques that facilitate multi-layer image registration are provided. In various embodiments, a system can access a first image and a second image. In various aspects, the system can generate, via execution of a machine learning model on the first image and the second image, a plurality of registration fields and a plurality of weight matrices that respectively correspond to the plurality of registration fields. In various instances, the system can register the first image with the second image based on the plurality of registration fields and the plurality of weight matrices.

Abstract: The invention relates to a method for a computer device, for detecting an optimal candidate compound based on a plurality of samples comprising a cell line and one or more biomarkers, and a plate map configuration, wherein the plate map configuration is providing locations of samples comprising cell lines exposed to one or more biomarkers and different concentrations of a candidate compound forming at least one concentration gradient, the candidate compound being comprised in a plurality of candidate compounds, said method comprising generating (310) phenotypic profiles of each concentration gradient of each of the plurality of candidate compounds at a plurality of successive points in time to form a plurality of compound profiles, wherein generating phenotypic profiles comprises the steps obtaining (312) image data depicting each sample comprised in the concentration gradient, generating (314) a class-label and a class for each cell of the samples based on the image data, detecting (320) the optimal candidat

Abstract: Systems and techniques that facilitate freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run.

Abstract: Systems and techniques for facilitating image analysis using deviation from normal data are presented. In one example, a system generates atlas map data indicative of an atlas map that includes a first portion of patient image data from a plurality of reference patients and a second portion of the patient image data from a plurality of target patients. The first portion of the patient image data is matched to a corresponding age group for a set of patient identities associated with the first portion of the patient image data. The system also generates deviation map data that represents an amount of deviation for the second portion of the patient image data compared to the first portion of the patient image data. Furthermore, the system trains a neural network based on the deviation map data to determine one or more clinical conditions.

Abstract: Systems and techniques for facilitating a deep convolutional neural network with self-transfer learning are presented. In one example, a system includes a machine learning component, a medical imaging diagnosis component and a visualization component. The machine learning component generates learned medical imaging output regarding an anatomical region based on a convolutional neural network that receives medical imaging data. The machine learning component also performs a plurality of sequential downsampling and upsampling of the medical imaging data associated with convolutional layers of the convolutional neural network. The medical imaging diagnosis component determines a classification and an associated localization for a portion of the anatomical region based on the learned medical imaging output associated with the convolutional neural network.

Abstract: Systems and techniques for facilitating image analysis using deviation from normal data are presented. In one example, a system generates atlas map data indicative of an atlas map that includes a first portion of patient image data from a plurality of reference patients and a second portion of the patient image data from a plurality of target patients. The first portion of the patient image data is matched to a corresponding age group for a set of patient identities associated with the first portion of the patient image data. The system also generates deviation map data that represents an amount of deviation for the second portion of the patient image data compared to the first portion of the patient image data. Furthermore, the system trains a neural network based on the deviation map data to determine one or more clinical conditions.

Abstract: Systems and techniques that facilitate freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run.

Abstract: Systems and techniques for facilitating a deep convolutional neural network with self-transfer learning are presented. In one example, a system includes a machine learning component, a medical imaging diagnosis component and a visualization component. The machine learning component generates learned medical imaging output regarding an anatomical region based on a convolutional neural network that receives medical imaging data. The machine learning component also performs a plurality of sequential downsampling and upsampling of the medical imaging data associated with convolutional layers of the convolutional neural network. The medical imaging diagnosis component determines a classification and an associated localization for a portion of the anatomical region based on the learned medical imaging output associated with the convolutional neural network.

Abstract: The invention relates to a method for a computer device, for detecting an optimal candidate compound based on a plurality of samples comprising a cell line and one or more biomarkers, and a plate map configuration, wherein the plate map configuration is providing locations of samples comprising cell lines exposed to one or more biomarkers and different concentrations of a candidate compound forming at least one concentration gradient, the candidate compound being comprised in a plurality of candidate compounds, said method comprising generating (310) phenotypic profiles of each concentration gradient of each of the plurality of candidate compounds at a plurality of successive points in time to form a plurality of compound profiles, wherein generating phenotypic profiles comprises the steps obtaining (312) image data depicting each sample comprised in the concentration gradient, generating (314) a class-label and a class for each cell of the samples based on the image data, detecting (320) the optimal candidat

Abstract: Systems and techniques for facilitating a deep learning architecture for automated image feature extraction are presented. In one example, a system includes a machine learning component. The machine learning component generates learned imaging output regarding imaging data based on a convolutional neural network that receives the imaging data. The machine learning component also performs a plurality of sequential and/or parallel downsampling and upsampling of the imaging data associated with convolutional layers of the convolutional neural network.