Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12593966-B2
Publication Date
2026-04-07
Expiration Date
Abstract
Systems, devices, and methods for providing an endoluminal transhepatic access to a patient pancreaticobiliary system in an endoscopic procedure are disclosed. An example of a transhepatic access procedure comprises navigating a steerable elongate instrument through a body cavity or channel and exiting to a access site of liver, puncturing the liver from the access site, extending the steerable elongate instrument through the liver and into the pancreaticobiliary system and performing an operation therein. Following the operation, the steerable elongate instrument can be retreated, and the access site of liver can be closed with a closure means. Apparatus and methods of training a machine-learning model and using said model to identify patient candidacy for retrograde access based on images of patient anatomy are also disclosed.
Core Innovation
The invention provides an endoscopic system for transhepatic access to a pancreaticobiliary system of a patient using a steerable elongate instrument. Patient information including an image of a duodenal papilla is received by a controller circuit, and the received image is applied to a trained machine-learning model.
At least one of a geometric feature or a morphological feature is extracted from the image of the duodenal papilla. The trained machine-learning model uses the determination and the extracted feature or features to determine a pancreaticobiliary access approach between retrograde access via the duodenal papilla and transhepatic access to the pancreaticobiliary system.
The trained machine-learning model predicts one or more anatomical complication outcomes for the determined access approach. The system provides a display configured to provide a treatment plan that includes cannulation and navigation parameters for the steerable elongate instrument and the predicted one or more anatomical complication outcomes based on the determined pancreaticobiliary access approach.
Claims Coverage
Independent claim clm-00001 is directed to an endoscopic system that performs ML-based access-approach determination and complication prediction from a duodenal papilla image, and then displays a treatment plan including cannulation and navigation parameters. The independent claim includes 4 main inventive feature groupings: ML-based approach determination using geometric or morphological features, ML-based prediction of anatomical complication outcomes, and user-facing treatment plan display with cannulation and navigation parameters.
Machine-learning access-approach determination from a duodenal papilla image
A controller circuit configured to receive patient information including an image of a duodenal papilla, apply the received image of the duodenal papilla to a trained machine-learning model to determine a pancreaticobiliary access approach between retrograde access via the duodenal papilla and transhepatic access to the pancreaticobiliary system.
Geometric or morphological feature extraction for the access decision
The controller circuit extracts at least one of a geometric feature or a morphological feature from the image of the duodenal papilla for use with the trained machine-learning model.
Anatomical complication outcome prediction for the determined approach
Predict, using the trained machine-learning model and the extracted geometric feature or morphological feature, one or more anatomical complication outcomes for the determined pancreaticobiliary access approach.
Display of a treatment plan with cannulation and navigation parameters and predicted outcomes
A display configured to provide a treatment plan including cannulation and navigation parameters for the steerable elongate instrument and the predicted one or more anatomical complication outcomes, based on the determination of the pancreaticobiliary access approach.
The independent claim centers on using a trained machine-learning model fed with a duodenal papilla image and extracted geometric or morphological features to determine between retrograde and transhepatic pancreaticobiliary access, predict anatomical complication outcomes for the chosen approach, and display a treatment plan with cannulation and navigation parameters together with the predicted outcomes.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?