Rutgers, the State University of New Jersey

Computed Anatomy Incorporated

Koios Medical, Inc.

T-netix, Inc.

Sonavista, Inc.

Other

Clearview Diagnostics, Inc.

Empire Technology Development LLC

Richard James Mammone

Christine I Podilchuk

Ajit Jairaj

William Hulbert

Lev Barinov

Manish Sharma

Xiaoyu Zhang

Martin Gersten

Joseph L Zelvin

Kevin Farrell

Joseph Wilder

Adam B Fineberg

William E Mayo

Kevin R Farrell

Ananth Sankar

Han-Seng Liou

Khaled Assaleh

Devang Naik

Mark C Croft

Zwi Kalman

Khaled T Assaleh

Brian Freeman

A system and method of computer-aided detection (CAD or CADe) of medical images that utilizes persistence between images of a sequence to identify regions of interest detected with low interference from artifacts to reduce false positives and improve probability of detection of true lesions, thereby providing improved performance over static CADe methods for automatic ROI lesion detection.

Method and system of computer-aided detection using multiple images from different views of a region of interest to improve detection accuracy

A system and method is disclosed to reduce variation of the clinical decision making process when an image reporting and data system (IRADS) for medical diagnosis is used. Image reporting and data systems provide guidelines for an operator to identify images as belonging to one of a number of categories and specific clinical actions are then recommended based upon such categories. Some clinical actions such as biopsies may be recommended by IRADS even when they are not necessary. The present inventive concept is configured to utilize a Computer-Assisted Diagnosis (CAD) system that is specifically programmed to minimize discrepancies between the recommended clinical actions of an individual or specific group of experts using the standard IRADS process and the optimum clinical actions based on correlation with biopsy proven data. The resulting CAD system reduces the number of unnecessary clinical actions such as biopsies based on the operator's error profile.

Method and means of CAD system personalization to reduce intraoperator and interoperator variation

A method and means to utilize machine learning to train a device to generate a confidence level indicator (CLI). The device is a CAD system that has been initially trained using initial machine learning to recommend classifications for image features presented to the device. Probabilistic classification is utilized to incorporate intermediate values given by a human operator to better indicate a level of confidence of the CAD system's recommendations as to what classes should be associated with certain image features.

Method and means of CAD system personalization to provide a confidence level indicator for CAD system recommendations

A device to detect an object in a medical image is described. An image analysis application, executed by the device, receives the medical image as an input. The medical image is next partitioned to sub-regions. Parts of the object are detected in a selection of the sub-regions using a deep-learning neural network (DNN) model. Bounding boxes for the selection are also determined. The bounding boxes are evaluated based on a confidence score detected as above a threshold level. The confidence score designates the parts as contained within the selection. Next, a region of interest (ROI) is determined as a group including the selection. Similar orientations associated with the bounding boxes are comparable to similar orientations of a positive training model of the DNN model. Furthermore, the selection is designated as the ROI within the medical image. The medical image is provided with the ROI to a user.

Neural network-based object detection in visual input

A device to enhance and present a medical image using a corrective mechanism is described. An image analysis application executed by the device captures a digital copy of the medical image displayed on a display device. A flawed photography effect associated with the digital copy is identified by processing the digital copy. Next, the digital copy is enhanced based on the flawed photography effect. Furthermore, the enhanced digital copy can be processed with an artificial intelligence mechanism to generate an annotation. The annotation is associated with a cancer identification. In addition, the enhanced digital copy and the annotation are displayed.

Device to enhance and present medical image using corrective mechanism

A mobile device to provide a medical image based distortion correction mechanism is described. An image analysis application, executed by the mobile device, captures a digital copy of the medical image with a camera component in response to a user action. Distortion(s) associated with the digital copy are identified by processing the digital copy with deep neural network (DNN) model(s). Next, a manual correction description is determined to correct the distortion(s) in relation to the camera component and the medical image. Furthermore, a notification to recapture the digital copy is provided to the user. The notification includes the manual correction description. Additionally, in response to another user action to correct the distortion(s) or a failure to detect the user execute manual correction(s) associated with the distortion(s) within a time period, the distortion(s) within the digital copy are corrected and the corrected digital copy is provided to the user.

Medical image based distortion correction mechanism

A device to correct an image blur within a medical image is described. An image analysis application executed by the device receives the medical image from a medical image provider. Next, the image blur is detected within the medical image by analyzing the medical image. The medical image is subsequently processed with a deep learning model to correct the image blur. In response to the processing, a de-blurred medical image is generated. The de-blurred medical image is provided for a presentation or a continued analysis.

Correcting image blur in medical image

A device to provide a heat map based medical image diagnostic mechanism is described. An image analysis application executed by the device receives a medical image from a medical image provider. A region of interest (ROI) is determined or provided by a user. A disease state score including a malignancy score is calculated for the ROI. Next, the ROI is partitioned into sub-regions. Impact values associated with the sub-regions are also determined. The impact values indicate the influence of a sub-region on the disease state score. Furthermore, annotations are determined based on pixel values associated with the sub-region. A heat map of the sub-regions is also generated based on the impact values. The heat map is labeled with the annotations. Next, the heat map is overlaid on the ROI. The medical image is provided with the heat map to the user.

Heat map based medical image diagnostic mechanism

Embodiments provided herein generally relate to improved ultrasound visualization. In some embodiments, interoperative ultrasound displays may be enhanced for more accurate identification of cancerous and non-cancerous tissues.

Ultrasound with augmented visualization

Methods and means of CAD system personalization to reduce intraoperator and interoperator variation

The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. An estimate of the enrollement channel and of the test channel is developed for inverse filtering of the enrollment or the test speech, respectively. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

Subword-based speaker verification using multiple-classifier fusion, with channel, fusion, model and threshold adaptation

The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

Growing community of inventors

Warren, NJ, United States of America

Richard James Mammone