Multi-Pass Organ Segmentation for Small-Organ Boundary Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging techniques, such as MRI and CT scans, struggle to accurately detect and isolate smaller organs like the pancreas due to their deformability, blending with surrounding tissues, and limited appearance in scans, making it difficult for radiologists to reliably find organ boundaries.
Innovation Solution
A heuristic-based segmentation method using multiple scan passes, synthetic centroid masks, and iterative thresholding to isolate smaller organs, involving frame normalization, 3D correlation, and boundary testing to distinguish organs from neighboring structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If medical imaging scans are used to detect organs, then internal structure information is obtained, but detection accuracy deteriorates for small organs due to homogeneity of surrounding tissue
Solution Approach 1:
The patent applies segmentation by dividing the medical image into multiple regions based on intensity thresholds. It performs multiple segmentation passes with different thresholds to separate the organ of interest from surrounding tissues, progressively refining the boundary detection and improving measurement precision for small organs embedded in homogeneous tissue.
Solution Approach 2:
The patent performs preliminary actions by conducting frame normalization and generating synthetic centroid masks before the actual segmentation process. These preparatory steps establish reference frameworks and expected organ locations, enabling more accurate subsequent detection and reducing the difficulty of finding organ boundaries in complex medical images.
2Reliability
If manual organ identification is performed by radiologists, then organ assessment is possible, but time consumption increases
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform organ segmentation and boundary identification without requiring manual radiologist intervention for each step. The automated multi-pass segmentation process with synthetic centroid masks allows the system to independently assess organs, significantly reducing time loss while maintaining reliability through algorithmic consistency.
3Measurement precision
If multiple segmentation passes are performed, then organ boundary accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent systematically applies segmentation by dividing the complex multi-pass process into distinct, manageable stages: first pass with initial threshold, second pass with refined threshold, and final pass with synthetic centroid mask guidance. This structured segmentation approach improves organ boundary accuracy while controlling processing complexity through clear阶段性 divisions.
Solution Approach 2:
The patent reduces processing complexity by performing preliminary actions such as frame normalization and synthetic centroid mask generation before the multiple segmentation passes. These preliminary steps prepare the data in advance, simplifying the subsequent segmentation operations and making the overall complex process more manageable and systematic.
Data Source
AI summary
Discussed herein are devices, systems, and methods for organ mask generation. A device, system and method for organ mask generation including generating a synthetic centroid mask, identifying first and second intensity thresholds, in a first segmentation pass, setting (i) pixels of an image with intensities less than the first threshold to zero and (ii) pixels of the image corresponding to objects with centroids outside the synthetic centroid mask to zero, resulting an initial organ mask, in a second segmentation pass, setting pixels (i) with intensities less than the second threshold, the second threshold less than the first threshold to zero and (ii) setting pixels corresponding to objects with centroids outside the initial organ mask to zero, resulting in a second organ mask, and expanding and filling the second organ mask to generate an organ mask.