General Electric Company

Fei Zhao

Rakesh Mullick

Paulo Ricardo Mendonca

Vivek Prabhakar Vaidya

Vidya Pundalik Kamath

Soma Biswas

Xiaoxing Li

Saad Ahmed Sirohey

Robert August Kaucic

Rahul Bhotika

Bipul Das

Roshni Bhagalia

Pavan Kumar Veerabhadra Annangi

Kunlin Cao

Ziyue Xu

A method is provided for detecting lesions in ultrasound images. The method includes acquiring ultrasound information, determining discriminative descriptors that describe the texture of a candidate lesion region, and classifying each of the discriminative descriptors as one of a top boundary pixel, a lesion interior pixel, a lower boundary pixel, or a normal tissue pixel. The method also includes determining a pattern of transitions between the classified discriminative descriptors, and classifying the candidate lesion region as a lesion or normal tissue based on the pattern of transitions between the classified discriminative descriptors.

Method and system for lesion detection in ultrasound images

A method is provided for detecting lesions in ultrasound images. The method includes acquiring an ultrasound image, generating a Fisher-tippett (FT) distribution-based edge feature map from the acquired ultrasound image, generating gradient concentration (GC) scores for pixels of the acquired ultrasound image using the FT distribution-based edge feature map, and identifying a candidate lesion region within the acquired ultrasound image based on the GC scores.

A computer-implemented method of post-processing medical image data is provided. The method includes receiving tracked image data representative of multiple blood vessels, generating a binary tree structure for the multiple blood vessels based on a parent-child relationship between branches of the multiple blood vessels, generating a likelihood model for determining a validity of the branches of the multiple blood vessels, and generating a likelihood score for each branch based on the respective branch's compatibility with the likelihood model. The method also includes generating a reconstructed tree for the multiple blood vessels. Compatible branches are included in the reconstructed tree, while invalid branches are not included in the reconstructed tree.

Methods for generating a reconstructed tree structure from medical image data

A method of automatic defect recognition includes receiving a initial set of inspection image data of a scanned object from a scanning machine; applying a first image analysis algorithm to this set of inspection image data; then removing from the set of inspection image data any defect-free image regions, so as to retain a set of analyzed inspection image data; applying an additional image analysis algorithm(s) to the set of analyzed inspection image data, wherein the additional algorithm(s) has a higher computational cost than the first image analysis algorithm; and based on the applying of the additional image analysis algorithm(s), removing from the first set of inspection image data a second set of defect-free image regions, thereby retaining a set of twice-analyzed inspection image data.

Sequential approach for automatic defect recognition

The present disclosure relates to the use of probabilistic models to classify elements of a medical image into different tissue types. The models may be based upon geometric abstractions of the different tissue types being classified. In addition, the present disclosure teaches the derivation and modification of models for tissue classification based upon the neighboring region of the voxels undergoing classification.

Tissue classification in medical images

Growing community of inventors

Schenectady, NY, United States of America

Fei Zhao