20240054763. METHOD FOR INTERPRETING KIDNEY ULTRASOUND IMAGES WITH ARTIFICIAL INTELLIGENCE simplified abstract (Taichung Veterans General Hospital)
METHOD FOR INTERPRETING KIDNEY ULTRASOUND IMAGES WITH ARTIFICIAL INTELLIGENCE
Organization Name
Taichung Veterans General Hospital
Inventor(s)
Lin-Shien Fu of Taichung City (TW)
Yueh-Chuan Chang of Taichung City (TW)
METHOD FOR INTERPRETING KIDNEY ULTRASOUND IMAGES WITH ARTIFICIAL INTELLIGENCE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240054763 titled 'METHOD FOR INTERPRETING KIDNEY ULTRASOUND IMAGES WITH ARTIFICIAL INTELLIGENCE
Simplified Explanation
The abstract describes a method for interpreting kidney ultrasound images using artificial intelligence, allowing non-experts to detect abnormalities early for remote medical care.
- Deep-learning method used on abnormal and non-anomalous kidney ultrasound images
- Images classified by experienced nephrological experts
- Image pre-processing to obtain prediction modules
- Rules module establishes specific rules for combination and sequence of prediction modules
- Interpretation model predicts if kidney ultrasound image is abnormal based on combination of prediction modules and rules module
- Prediction modules determine probability of predefined abnormal pattern
- Rules module provides logic for determining prediction modules
Potential Applications
- Early detection of kidney abnormalities - Remote medical care based on AI interpretation of kidney ultrasound images
Problems Solved
- Allows non-experts to interpret kidney ultrasound images accurately - Enables early detection of kidney abnormalities for timely medical intervention
Benefits
- Increases accessibility to kidney health assessment - Facilitates remote monitoring and diagnosis - Improves efficiency in detecting kidney abnormalities
Original Abstract Submitted
a method for interpreting kidney ultrasound images with artificial intelligence includes: using a deep-learning method on abnormal and non-anomalous kidney ultrasound images obtained from classification by experienced nephrological experts and via image pre-processing to obtain prediction modules, and upon or after obtaining the prediction modules, obtaining a rules module establishing specific rules for combination and sequence among the prediction modules, and obtaining an interpretation model from a combination of the prediction modules and the rules module to predict whether a kidney ultrasound image is abnormal; wherein each prediction module is used to determine the probability of predefined abnormal pattern, and the rules module provides the logic for determining the prediction modules. accordingly, the method for interpreting kidney ultrasound images with artificial intelligence is able to allow non-kidney image interpretation experts to find kidney abnormality early and to use it as the basis for future remote medical care item.
