Atilla Kiraly

Title: Atilla Kiraly: Innovator in Cancer Detection Technology

Introduction

Atilla Kiraly is a prominent inventor based in Mountain View, CA (US). He has made significant contributions to the field of medical technology, particularly in cancer detection. His innovative approach utilizes advanced deep learning techniques to enhance the accuracy of cancer diagnosis.

Latest Patents

Atilla Kiraly holds a patent for a groundbreaking method and system aimed at improving cancer detection using deep learning. This patent describes a method to generate a probabilistic prediction of the presence or absence of cancer in both longitudinal and current image datasets, as well as multimodal image datasets. The system employs an ensemble of deep learning models, including a global model in the form of a 3D convolutional neural network (CNN). This model extracts features indicative of cancer presence on a global scale. Additionally, the system incorporates a two-stage prediction model that identifies cancer detection candidates and assigns a cancer probability to each candidate. The overall prediction of cancer probability is derived from the probabilities assigned by the second stage model.

Career Highlights

Atilla Kiraly is currently employed at Google Inc., where he continues to work on innovative solutions in the field of artificial intelligence and healthcare. His expertise in deep learning and image analysis has positioned him as a key player in the development of advanced medical technologies.

Collaborations

Atilla has collaborated with talented coworkers such as Shravya Shetty and Sujeeth Bharadwaj. Their combined efforts contribute to the advancement of technology in cancer detection and other areas of research.

Conclusion

Atilla Kiraly's work exemplifies the intersection of technology and healthcare, showcasing how innovations in deep learning can lead to significant improvements in cancer detection. His contributions are paving the way for more accurate and efficient diagnostic methods in the medical field.