Medical Image Processing Apparatus for Autopsy Imaging Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In medical image processing for ascertaining the cause of death through Autopsy Imaging (Ai), the large number of slice images from whole-body CT or MRI scans overwhelms radiologists, and existing CAD systems take too long to analyze, making it difficult to distinguish between death-causing abnormalities and post-mortem changes or resuscitation-related issues.
Innovation Solution
A medical image processing apparatus that includes an image acquiring unit, an abnormal area detecting unit, and an outputting unit, which uses region-specific algorithms to analyze images, exclude abnormalities caused by resuscitation or post-mortem changes, and prioritize display based on influence levels and exclusion levels to efficiently identify the cause of death.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If whole-body CT or MRI scans are performed to obtain comprehensive images for cause of death determination, then the coverage and completeness of examination is improved, but the number of slice images becomes enormous making it difficult for radiologists to analyze all images
Solution Approach 1:
The patent divides the enormous number of slice images into multiple groups based on anatomical regions or imaging sequences. The image grouping unit organizes images into manageable groups, allowing radiologists to systematically review images region by region rather than being overwhelmed by the complete set of thousands of slices.
Solution Approach 2:
The abnormal area detecting unit automatically extracts and highlights regions containing abnormalities from the large number of slice images. This extraction function isolates only the relevant images that contain pathological findings, filtering out normal images and presenting only the critical ones to radiologists for further evaluation.
2Measurement precision
If CAD systems analyze all whole-body images to detect abnormal areas, then the detection completeness is improved, but the processing time becomes excessively long (three or four days)
Solution Approach 1:
The system performs preliminary automatic detection of abnormal areas using CAD algorithms before radiologist review. The abnormal area detecting unit pre-identifies potential abnormalities and prepares a list of suspicious regions, so that radiologists can focus their expert analysis only on these pre-screened areas rather than examining every image from scratch.
Solution Approach 2:
The system applies CAD analysis selectively to identify only those images containing abnormalities, rather than requiring comprehensive manual review of all images. The abnormal area detecting unit performs detection on a subset of images that are most likely to contain pathology, reducing the overall processing burden while maintaining detection effectiveness.
3Reliability
If radiologists review all slice images to ensure no abnormality is missed, then the diagnostic accuracy is improved, but the time required for cause of death determination becomes unacceptably long
Solution Approach 1:
The system provides feedback to radiologists by presenting abnormal areas detected by CAD in a structured format, highlighting the location and characteristics of detected abnormalities. This feedback mechanism allows radiologists to efficiently verify or correct automated findings without having to manually search through all images, maintaining diagnostic accuracy while improving workflow efficiency.
4Loss of information
If the system displays all detected abnormal areas, then the completeness of information presentation is improved, but the ability to quickly identify critical abnormalities is reduced due to information overload
Solution Approach 1:
The output unit presents abnormal area information with varying levels of detail or emphasis based on the characteristics of each abnormality. Critical abnormalities may be highlighted or presented with more prominent formatting, while less significant findings are presented with standard formatting. This differential presentation helps radiologists quickly identify the most important abnormalities while still providing access to complete information.
Data Source
AI summary
According to one embodiment, a medical image processing apparatus includes an image acquiring unit, a detection algorithm storage, an abnormal area detecting unit and an outputting unit. The image acquiring unit acquires image data of a corpse. The detection algorithm storage stores an abnormal area detection algorithm. The abnormal area detecting unit uses the abnormal area detection algorithm to the image data of the corpse and analyzes the image data to detect an abnormal area. The outputting unit outputs information of the abnormal area detected by the abnormal area detecting unit.