This inventor holds 1 USPTO granted patent. Top assignees: Centre Hospitalier Sud Francilien, Université D'evry-Val-D'essonne. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
1 out of 1 
1 out of 30 Years Active: 2026
Title: Jonathan Kobold and Medical Image Segmentation
Introduction
Jonathan Kobold is an inventor associated with Weilheim, Germany. His work includes a patent application for an automated method to segment a thrombus and a related lesion in three-dimensional brain images.
Latest Patents
Kobold is associated with 1 patent: “Automatic Method for Segmentation of a Thrombus and a Lesion in a Three-Dimensional Brain Image.” The method uses two supervised recurrent artificial neural networks: one predicts lesions, and the other predicts thrombi. Their predictions are combined across images derived from a three-dimensional brain scan to produce segmentations. For the lesion, the method selects the widest segmentation when multiple candidates are available.
Career Highlights
Kobold’s listed organizational affiliations include Université d’Évry-Val-d’Essonne and Centre Hospitalier Sud Francilien. The patent reflects an application of machine learning to medical image analysis, with the aim of identifying a thrombus and the lesion it causes.
Collaborations
Kobold’s listed coworkers include Cosmin Alecu and Vincent Vigneron.
Conclusion
Jonathan Kobold’s patent work focuses on using recurrent neural networks to support the segmentation of thrombi and related lesions in three-dimensional brain images.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile