Company Filing History:
Years Active: 2024-2025
Title: Stojan Trajanovski: Innovator in Machine Learning and Image Processing
Introduction
Stojan Trajanovski is a notable inventor based in London, GB. He has made significant contributions to the fields of machine learning and image processing, holding a total of 3 patents. His work focuses on enhancing the explainability of machine learning models and improving the identification of lesions in medical imaging.
Latest Patents
One of his latest patents is titled "Explaining a model output of a trained model." This invention relates to a computer-implemented method for generating explainability information that clarifies the output of a trained model. The method employs aspect recognition models to identify characteristics in input instances, applying a saliency method to obtain a masked source representation relevant to the model output. The characteristics indicated by the aspect recognition models are then output as explainability information.
Another significant patent is "Identifying boundaries of lesions within image data." This invention provides a method and system for identifying lesion boundaries in image data using a machine learning algorithm. The algorithm generates probability and uncertainty data for each image data point, indicating the likelihood of being part of a lesion. The uncertainty data is then processed to accurately identify or correct the boundaries of the lesions.
Career Highlights
Stojan Trajanovski is currently employed at Koninklijke Philips Corporation N.V., where he continues to innovate in the field of technology. His work has been instrumental in advancing the capabilities of machine learning applications in healthcare and beyond.
Collaborations
He has collaborated with notable colleagues, including Bart Jacob Bakker and Dimitrios Mavroeidis, contributing to a dynamic and innovative work environment.
Conclusion
Stojan Trajanovski is a prominent figure in the realm of machine learning and image processing, with a focus on enhancing model explainability and medical imaging accuracy. His contributions are paving the way for future advancements in these critical fields.