Daren Sawkey

Title: Daren Sawkey: Innovator in Medical Imaging Technology

Introduction

Daren Sawkey is a prominent inventor based in Palo Alto, CA, known for his contributions to medical imaging technology. With a total of 4 patents, he has made significant strides in the field, particularly in the area of machine learning applications for medical image evaluation.

Latest Patents

Daren's latest patents include innovative technologies such as "Automatic localized evaluation of contours with visual feedback." This patent describes a localized evaluation network that incorporates a discriminator acting as a classifier, which may be included within a generative adversarial network (GAN). The GAN may utilize a generative network like U-NET for creating segmentations. The localized evaluation network is trained on image pairs that include medical images of organs of interest and corresponding segmentation (mask) images. The network is designed to distinguish whether an image pair accurately represents the ground truth. The GAN examines the interior layers of the discriminator to evaluate how much each localized image region contributes to the final classification. Additionally, the patent discloses embodiments that include a visual attribute, such as a heat map, representing the contributions of localized regions of a contour to an overall confidence score. These localized regions can be highlighted and reported for quality assurance review.

Another notable patent is "Classification of organ of interest shapes for autosegmentation quality assurance." This invention involves receiving a second image that includes an overlay depicting organ-at-risk (OAR) segmentations. The overlay is generated by a first machine learning model based on a first image depicting the anatomical region of a current patient. A second machine learning model then classifies the second image as one of a set of class names and characterizes the extent to which the second image is similar to or dissimilar from images with the same class name in a set of third images. The characterization is based on outputs from the internal layers of the second machine learning model, and dimensionality reduction may be performed to present the outputs in a human-comprehensible form.

Career Highlights

Daren has worked with leading companies in the medical technology sector, including Varian Medical Systems, Inc. and Siemens Healthineers International AG. His experience in these organizations has allowed him to develop and refine his innovative ideas in medical imaging.

Collaborations

Throughout his career, Daren has collaborated with talented professionals such as Corey Zankowski and Michelle