Capsule Image Review Using CADe-Centered Detection Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional endoscopic and capsule endoscope systems face limitations such as invasiveness, discomfort, and inefficiency in diagnosing GI tract abnormalities, with conventional capsule cameras failing to provide a comprehensive view of hidden areas and requiring extensive manual review of large image datasets.
Innovation Solution
A method and system for processing capsule camera images using computer-assisted detection (CADe) to highlight detection areas, applying lateral circle shifts to center these areas, and adjusting playback speed and display formats to enhance diagnostic efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If conventional capsule cameras are used to capture GI tract images, then the system is less invasive and more comfortable for patients, but the diagnostic review time is excessively long and manual examination is inefficient
Solution Approach 1:
The system performs preliminary computer-assisted detection (CADe) on capsule images to automatically identify and flag potential abnormalities before human review. This preliminary processing reduces the volume of images requiring manual examination by highlighting only those containing detected abnormalities, thereby maintaining patient comfort while significantly improving diagnostic efficiency
Solution Approach 2:
The patent introduces an intermediary CADe system that acts as a mediator between the capsule camera and the human diagnostician. This intermediary automatically processes images, detects abnormalities, and presents only relevant findings to the physician, eliminating the need for manual review of all captured images and thus resolving the contradiction between patient comfort and diagnostic efficiency
2Device complexity
If capsule cameras provide forward-looking field of view, then the device complexity is reduced, but hidden areas around ridges and irregularities cannot be observed
Solution Approach 1:
The patent employs asymmetric camera positioning and orientation within the capsule, with cameras strategically angled to capture side views and panoramic perspectives of the GI tract. This asymmetric configuration enables visualization of hidden areas around ridges and irregularities that would be invisible to conventional forward-looking cameras, while maintaining reasonable device complexity through targeted rather than omnidirectional coverage
3Device complexity
If detection areas are not highlighted in CADe frames, then the display complexity is reduced, but diagnostic accuracy and abnormality identification speed decrease
Solution Approach 1:
The system applies color-based highlighting to detection areas in CADe frames, using distinct colors or color intensities to mark regions containing detected abnormalities. This visual enhancement dramatically improves abnormality identification speed and diagnostic accuracy by drawing the physician's attention directly to relevant areas, while adding minimal complexity to the display system through software-based graphical overlays
4Productivity
If playback speed is increased to reduce review time, then diagnostic efficiency improves, but viewer fatigue increases and diagnostic quality may deteriorate
Solution Approach 1:
The system implements variable playback speed with periodic pauses at frames containing detected abnormalities. During normal navigation, images are displayed at higher speed to maintain efficiency, but the system automatically slows down or pauses when abnormality markers are encountered, allowing the physician to thoroughly examine suspicious areas without fatigue from continuously high-speed playback, thus maintaining both diagnostic speed and quality
Data Source
AI summary
Systems and methods are provided for processing images captured by a capsule camera system. According to one method, a frame sequence comprises panoramic picture representative of a GI scene covering substantially a lateral 360-degree Field-of-View is received. CADe (computer-assisted detection) is applied to detect one or more target abnormalities in the frame sequence, where said applying the computer-assisted detection (CADe) results in one or more CADe frames and each CADe frame contains at least one detection area containing a detected abnormality or a false positive. Circle shift is applied laterally to a target CADe frame to shift a detection area to a lateral center or close to the lateral center of the target CADe frame. The CADe frames comprising the target CADe frame are provided with the detection area shifted to the lateral center or close to the lateral center of the target CADe frame.