Tomosynthesis Stack Navigation With Automatic ROI Focusing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tomosynthesis systems require significant time for reviewers to navigate through multiple images to locate the best focus of an object or region of interest, due to limited angle acquisition leading to varying focus across slices, deterring full utilization of detailed image benefits.
Innovation Solution
A computer-controlled workstation that automatically identifies and displays images with the best focus of a selected object or region of interest, and optionally presents a series of near-focus images, using focus measure computation based on sharpness, contrast, or high-frequency component ratios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If reviewers manually navigate through multiple tomosynthesis image slices to locate the best focus of an object or region of interest, then they can identify the optimal image for evaluation, but the review time increases significantly
Solution Approach 1:
The system performs preliminary computation of focus measures for all image slices before the reviewer needs to evaluate them. By pre-calculating focus metrics (such as sharpness, contrast, or high-frequency component ratios) for each slice containing the object or region of interest, the system prepares the information in advance, allowing the reviewer to immediately access the best-focused image without manual navigation through all slices.
Solution Approach 2:
The patent replaces the manual mechanical navigation process (reviewer scrolling through slices) with an automated computational system. The computer-controlled workstation automatically computes focus measures, identifies the slice with the best focus, and displays it to the reviewer, substituting human manual search with algorithmic automation that processes images much faster than manual review.
2Reliability
If reviewers navigate through the entire tomosynthesis stack to locate best focus images, then they can ensure accurate evaluation, but the complexity of the review process increases
Solution Approach 1:
The system extracts only the essential information needed for evaluation—the slice containing the best focus of the object or region of interest—from the complete tomosynthesis stack. By computing focus measures for all slices and identifying the optimal one, the system extracts and presents only the most relevant image, eliminating the need for reviewers to examine unnecessary slices while maintaining evaluation accuracy.
Solution Approach 2:
The computer-controlled workstation acts as an intermediary between the tomosynthesis image stack and the reviewer. It automatically computes focus measures, compares all slices, identifies the best-focused image, and presents it to the reviewer, thereby simplifying the complex task of manual slice-by-slice evaluation while ensuring accurate identification of the optimal image for assessment.
Data Source
AI summary
A system and method for reviewing a tomosynthesis image data set comprising volumetric image data of a breast, the method comprising, in one embodiment, causing an image or a series of images from the data set to be displayed on a display monitor and selecting or indicating through a user interface an object or region of interest in a presently displayed image of the data set, thereby causing an image from the data set having a best focus measure of the user selected or indicated object or region of interest to be automatically displayed on the display monitor.