Company Filing History:
Years Active: 2025
Title: Innovations in Tumor Detection: The Contributions of Kyle Gerard
Introduction
Kyle Gerard is an innovative inventor based in Princeton, NJ (US). She has made significant contributions to the field of medical technology, particularly in the detection and classification of tumor cells. Her work focuses on utilizing machine learning to enhance the accuracy and efficiency of cancer detection.
Latest Patents
Kyle Gerard holds a patent for a groundbreaking invention titled "Multi-scale tumor cell detection and classification." This patent involves methods and systems for training a machine learning model. The process includes generating pairs of training pixel patches from a dataset of training images. Each pair consists of a first patch representing a part of a respective training image and a second patch, centered at the same location as the first, representing a larger part of the training image. The second patch is resized to match the size of the first patch. A detection model is trained using the first pixel patches to detect and locate cells in the images. Additionally, a classification model is trained to classify cells as cancerous based on cell location information generated by the detection model. A segmentation model is also trained using the second pixel patches to locate and classify cancerous arrangements of cells in the images. Kyle has 1 patent to her name.
Career Highlights
Kyle Gerard is currently employed at NEC Corporation, where she continues to develop innovative solutions in the field of medical imaging and machine learning. Her work has the potential to significantly impact cancer diagnosis and treatment.
Collaborations
Kyle collaborates with Eric Cosatto, who is also involved in advancing technologies related to medical imaging and machine learning.
Conclusion
Kyle Gerard's contributions to tumor cell detection and classification exemplify the intersection of technology and healthcare. Her innovative approach has the potential to improve cancer detection methods significantly.