Method for probabilistic boosting tree-based lesion segmentation in e.g. ultrasound image data for diagnosis of liver tumors, involves minimizing error to select base classifiers to compute total classifiers in probabilistic boosting tree

Simple SummaryContent extracted from patent full text and abstract with AI.

This patent describes a method for automatically segmenting lesions, such as liver tumors, in medical image data (e.g., ultrasound or CT scans). The method uses a probabilistic boosting tree (PBT) machine learning algorithm, which is specially trained to identify and outline abnormal regions in the images by minimizing errors and optimizing the classifiers used during training.

Use CasesContent extracted from patent full text and abstract with AI.

• Automated detection of liver tumors in ultrasound or CT scans for diagnostic purposes
• Computer-aided diagnosis tools in hospitals and clinics
• Automated lesion detection for other organs or diseases in medical imaging
• Pre-processing step for radiologists to highlight suspicious areas
• Screening large volumes of medical images efficiently in clinical trials or research studies

BenefitsContent extracted from patent full text and abstract with AI.

• Faster and more accurate detection of lesions compared to manual analysis
• Reduced risk of human error in medical image interpretation
• Improved diagnostic confidence for clinicians
• Potential for real-time or high-throughput analysis of medical imaging data
• Adaptability to different types of medical images and lesion types

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The method involves applying a probabilistic boosting tree (PBT)-based lesion recognition on image points of an image data set to be evaluated using total classifiers and a base classifiers (B) determined by training. Positively recognized lesions are marked and/or output. An error during allocating the image points by the total classifiers as lesions and cost factors for a number of computations is minimized for selecting the base classifiers for computing the total classifiers in the PBT during AdaBoost training. An independent claim is also included for a processing unit i.e. computed tomography (CT) system.