Ge Precision Healthcare LLC

General Electric Company

Hewlett-packard Development Company, L.p.

Hariharan Ravishankar

Rahul Venkataramani

Dattesh Dayanand Shanbhag

Prasad Sudhakar

Vivek Prabhakar Vaidya

Sahika Genc

Erik Normann Steen

Sheshadri Thiruvenkadam

Arathi Sreekumari

Pavan Annangi

Sai Hareesh Anamandra

Suresh Emmanuel Joel

Tore Bjaastad

Ravindra Mohan Manjeshwar

Rakesh Mullick

Svein Arne Aase

Sandeep Suryanarayana Kaushik

Abhijit Vishwas Patil

Gokul Swamy

Sohan Rashmi Ranjan

Sitaram Ramachandrula

Radhika Madhavan

Prasad Sudhakara Murthy

Rohan Keshav Patil

Rohit Pardasani

Floribertus Pm Heukensfeldt Jansen

Pavan Kumar V Annangi

Michel Souheil Tohme

Aditya Saha

Renjith S Nair

Bharath Ram Sundar

Annangi P Pavan Kumar

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.

Model suitability coefficients based on generative adversarial networks and activation maps

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.

Systems and methods for respiratory support recommendations

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(N), where N is the size of the measurement data, to O(M), where M is the size of an individual decimated measurement data array, wherein M<N.

System and methods for reconstructing medical images using deep neural networks and recursive decimation of measurement data

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.

System and methods for quantifying uncertainty of segmentation masks produced by machine learning models

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.

System and method for class specific deep learning

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(N), where N is the size of the measurement data, to O(M), where M is the size of an individual decimated measurement data array, wherein M&#x3c;N.

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.

System and method for memory augmented domain adaptation

The subject matter discussed herein relates to systems and methods for generating a clinical outcome based on creating a task-specific model associated with processing raw image(s). In one such example, input raw data is acquired using an imaging system, a selection input corresponding to a clinical task is received, and a task-specific model corresponding to the clinical task is retrieved. Using the task-specific model, the raw data is mapped onto an application specific manifold. Based on the mapping of the raw data onto the application specific manifold the clinical outcome is generated, and subsequently providing the clinical outcome for review.

Systems and methods for predicting outcomes using raw data

Methods and systems are provided for automatically determining a phase shift and noise insensitive similarity metric for electrocardiogram (ECG) beats in a Holter monitor recording. In one embodiment, a deep neural network may be trained to map an ECG beat to a phase shift insensitive and noise insensitive feature space embedding using a training data triad, wherein the training data triad may be produced by a method comprising: 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.

System and methods for electrocardiogram beat similarity analysis using deep neural networks

The present approach relates to a system capable of life-long learning in a deep learning context. The system includes a deep learning network configured to process an input dataset and perform one or more tasks from among a first set of tasks. As an example, the deep learning network may be part of an imaging system, such as a medical imaging system, or may be used in industrial applications. The system further includes a learning unit communicatively coupled to the deep learning networkand configured to modify the deep learning network so as to enable it to perform one or more tasks in a second task list without losing the ability to perform the tasks from the first list.

System and method for using a deep learning network over time

Methods and systems are provided for improving image quality of ultrasound images by automatically determining one or more image quality parameters via a plurality of separate image quality models. In one example, a method for an ultrasound system includes determining a plurality of image quality parameters of an ultrasound image acquired with the ultrasound system, each image quality parameter determined based on output from a separate image quality model, and outputting feedback to a user of the ultrasound system based on the plurality of image quality parameters.

System and methods for ultrasound image quality determination

Methods and systems are provided for sequentially selecting scan parameter values for ultrasound imaging. In one example, a method includes selecting a first parameter value for the a first scan parameter based on an image quality of each ultrasound image of a first plurality of ultrasound images of an anatomical region, each ultrasound image of the first plurality of ultrasound images having a different parameter value for the first scan parameter, selecting a second parameter value for a second scan parameter based on an image quality of each ultrasound image of a second plurality of ultrasound images of the anatomical region, each ultrasound image of the second plurality of ultrasound images having a different parameter value for the second scan parameter, and applying the first parameter value for the first scan parameter and the second parameter value for the second scan parameter to one or more additional ultrasound images.

System and methods for sequential scan parameter selection

The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.

Growing community of inventors

Bengaluru, India

Hariharan Ravishankar