Abstract: Systems or techniques for facilitating learnable visual prompt engineering are provided. In various embodiments, a system can access a medical image and a pre-trained machine learning model that is configured to perform a diagnostic or prognostic inferencing task. In various aspects, the system can apply a pre-processing transformation to one or more pixels or voxels of the medical image, thereby yielding a transformed version of the medical image, wherein the pre-processing transformation can convert an input pixel or voxel intensity value to an output pixel or voxel intensity value via one or more parameters that are iteratively learned. In various instances, the system can perform the diagnostic or prognostic inferencing task, by executing the pre-trained machine learning model on the transformed version of the medical image.

Abstract: An iterative framework for learning multimodal mappings tailored to medical image inferencing tasks is provided. In an example, a computer-implemented method can comprise receiving multimodal annotation data for medical images, the multimodal annotation data comprising non-image annotation data and image annotation data, and employing one or more machine learning (ML) processes to learn bi-directional mappings between non-image features included in the non-image annotation data and image features associated with the medical images and the image annotation data. The method further comprises generating, as a result of the one or more ML processes, a model configured to: infer one or more of the non-image features associated with new medical images given the new medical images, and/or infer one or more of the image features associated with the new medical images given the new medical images and non-image input corresponding to at least some of the non-image annotation data.

Abstract: Systems or techniques that facilitate ensembled querying of example images via deep learning embeddings are provided. In various embodiments, a system can access a medical image associated with a medical patient. In various aspects, the system can generate an ensembled heat map indicating where in the medical image an anatomical structure is likely to be located, by executing an embedder neural network on the medical image and on a plurality of example medical images associated with other medical patients. In various instances, respective instantiations of the anatomical structure can be flagged in the plurality of example medical images by user-provided clicks.

Abstract: Methods and Systems are provided for performing early onset diagnostics for clogged injectors using fuel trims collected from the Engine Management System and evaluated in different operating modes of the engine. Example implementations use fuel trims that can estimate the contrast in combustion ratio ? across different operating modes defined on the engine speed and calculated engine load plane. Features are extracted, then classified using machine learning to output a diagnosis according to different levels of fuel injector clogging.

Abstract: Systems/techniques that facilitate generation of model suitability coefficients are provided. In various embodiments, a system can access a model trained on a training dataset, and the system can compute a coefficient indicating whether the model is suitable for deployment on a target dataset, based on analyzing activation maps associated with the model. In some cases, the system can: train a generative adversarial network (GAN) to learn a distribution of training activation maps produced by the model; generate a set of target activation maps of the model, by feeding samples from the target dataset to the model; cause a generator of the GAN to generate synthetic training activation maps from the learned distribution of training activation maps; iteratively perturb inputs of the generator until distances between the synthetic training activation maps and the target activation maps are minimized; and aggregate the minimized distances to form the coefficient.

Abstract: Systems/techniques that facilitate improved uncertainty estimation via object-specific and object-agnostic segmentation disagreement are provided. In various embodiments, a system can access an image depicting an object. In various aspects, the system can localize, via execution of an object-specific segmentation model on the image, a first inferred boundary of the object. In various instances, the system can generate an uncertainty score for the first inferred boundary, based on a second inferred boundary of the object generated via execution of an object-agnostic segmentation model on the image.

Abstract: Techniques are described for refining or updating medical image inferencing models post deployment using synthetic images generated from non-image data feedback. In an example, a system can comprise a memory that stores computer-executable components and a processor that executes the computer-executable components stored in the memory. The computer-executable components can comprise an image generation component that generates synthetic medical images based on feedback information associated with performance of a medical image inferencing model received in association with application of the medical image inferencing model to medical images in a deployment environment, wherein the feedback information excludes image data. The computer-executable components can further comprise a refinement component that updates the medical image inferencing model using the synthetic images and a model updating process.

Abstract: Methods and systems are provided for generating respiratory support recommendations. In one embodiment, a method includes extracting imaging features from patient imaging information for a patient, extracting non-imaging features from patient clinical data of the patient, entering the imaging features and the non-imaging features to a joint model trained to output respiratory support recommendations as a function of the imaging features and the non-imaging features, and displaying one or more respiratory support recommendations output by the joint model.

Abstract: Various systems and methods are provided for training and using a diagnostic model including artificial intelligence (AI) models. The diagnostic model including the AI models may be trained by receiving training data including a majority class of samples corresponding to medical data of patients that do not have the medical condition and a minority class of samples corresponding to medical data of patients that do have the medical condition, determining sub-groups of the majority class of samples based on features of the majority class of samples, generating sub-group training datasets that each include respective samples of the sub-groups of the majority class of samples and samples of the minority class of samples, and training the AI models of the diagnostic model using the sub-group training datasets. The diagnostic model including the AI models may be used to determine whether a patient has a medical condition.

Abstract: Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N4), where N is the size of the measurement data, to O(M4), where M is the size of an individual decimated measurement data array, wherein M<N.

Abstract: Systems/techniques that facilitate improved distillation of deep ensembles are provided. In various embodiments, a system can access a deep learning ensemble configured to perform an inferencing task. In various aspects, the system can iteratively distill the deep learning ensemble into a smaller deep learning ensemble configured to perform the inferencing task, wherein a current distillation iteration can involve training a new neural network of the smaller deep learning ensemble via a loss function that is based on one or more neural networks of the smaller deep learning ensemble which were trained during one or more previous distillation iterations.

Abstract: Systems and methods are provided for quantifying uncertainty of segmentation mask predictions made by machine learning models, where the uncertainty may be used to streamline an anatomical measurement workflow by automatically identifying less certain caliper placements. In one example, the current disclosure teaches receiving an image including a region of interest, determining a segmentation mask for the region of interest using a trained machine learning model, placing a caliper at a position within the image based on the segmentation mask, determining an uncertainty of the position of the caliper, and responding to the uncertainty of the position of the caliper being greater than a pre-determined threshold by displaying a visual indication of the position of the caliper via a display device and prompting a user to confirm or edit the position of the caliper.

Abstract: The disclosure relates generally to a patient monitoring device and, more particularly, to improved system and method to detect a false alarm in a patient monitoring device. The disclosure specifically relates to a system and a method to detect a false alarm in a patient monitoring device. The system may include a patient monitoring device configured to receive a patient monitoring data from a patient. The system may enable the processing of the patient monitoring data by a processing device to determine a false alarm generated by the patient monitoring device. The system may further provide a user-interface, which may be configured to filter a true alarm from a false alarm generated by the patient monitoring device.

Abstract: A method for controlling a physical process includes receiving an input dataset corresponding to the physical process. The method further includes determining a data model based on the input dataset. The data model includes a plurality of latent space variables of a machine learning model. The method also includes receiving a plurality of reference models corresponding to a plurality of classes. Each of the plurality of reference models includes a corresponding plurality of latent space variables. The method includes comparing the data model with each of the plurality of reference models to generate a plurality of distance metric values. The method further includes selecting a reference model among the plurality of reference models based on the plurality of distance metric values. The method also includes controlling the physical process based on the selected reference model.

Abstract: Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N4), where N is the size of the measurement data, to O(M4), where M is the size of an individual decimated measurement data array, wherein M<N.

Abstract: Methods and systems are provided for predicting cardiac arrhythmias based on multi-modal patient monitoring data via deep learning. In an example, a method may include predicting an imminent onset of a cardiac arrhythmia in a patient, before the cardiac arrhythmia occurs, by analyzing patient monitoring data via a multi-arm deep learning model, outputting an arrhythmia event in response to the prediction, and outputting a report indicating features of the patient monitoring data contributing to the prediction. In this way, the multi-arm deep learning model may predict cardiac arrhythmias before their onset.

Abstract: Methods and systems are provided for reconstructing images from measurement data using one or more deep neural networks according to a decimation strategy. In one embodiment, a method for reconstructing an image using measurement data comprises, receiving measurement data acquired by an imaging device, selecting a decimation strategy, producing a reconstructed image from the measurement data using the decimation strategy and one or more deep neural networks, and displaying the reconstructed image via a display device. By decimating measurement data to form one or more decimated measurement data arrays, a computational complexity of mapping the measurement data to image data may be reduced from O(N4), where N is the size of the measurement data, to O(M4), where M is the size of an individual decimated measurement data array, wherein M<N.

Abstract: Methods and systems are provided for determining a phase shift and noise insensitive similarity metric for electrocardiogram (ECG) beats in a Holter monitor recording. In one embodiment, a method includes selecting a first beat and a second beat recorded via one or more Holter monitors, determining a dynamic time warping (DTW) distance between the first beat and the second beat, setting a similarity label for the first beat and the second beat based on the DTW distance, and storing the first beat, the second beat, and the similarity label, in a location of non-transitory memory as an ECG training data triad, and training a machine learning model with the ECG training data triad.

Abstract: A system is presented. The system includes an acquisition subsystem configured to obtain images corresponding to a target domain. Moreover, the system includes a processing subsystem in operative association with the acquisition subsystem and including a memory augmented domain adaptation platform configured to compute one or more features of an input image corresponding to a target domain, identify a set of support images based on the features of the input image, where the set of support images corresponds to the target domain, augment an input to a machine-learnt model with a set of features, a set of masks, or both corresponding to the set of support images to adapt the machine-learnt model to the target domain, and generate an output based at least on the set of features, the set of masks, or both. Additionally, the system includes an interface unit configured to present the output for analysis.

Abstract: Systems and methods are provided for quantifying uncertainty of segmentation mask predictions made by machine learning models, where the uncertainty may be used to streamline an anatomical measurement workflow by automatically identifying less certain caliper placements. In one example, the current disclosure teaches receiving an image including a region of interest, determining a segmentation mask for the region of interest using a trained machine learning model, placing a caliper at a position within the image based on the segmentation mask, determining an uncertainty of the position of the caliper, and responding to the uncertainty of the position of the caliper being greater than a pre-determined threshold by displaying a visual indication of the position of the caliper via a display device and prompting a user to confirm or edit the position of the caliper.