Verily Life Sciences LLC

Google Inc.

Kira Whitehouse

Jin Zhang

Peter Wubbels

Tyler Rhodes

Rohan Ganeshananthan

Sam Kavusi

Eliezer Glik

Sunny Virmani

Introduced here are approaches to assessing whether digital features (or simply 'features') detected in digital images by detection models are representative of artifacts that can obscure actual pathologies. A diagnostic platform may characterize each digital feature detected in a digital image based on its likelihood of being an artifact. For instance, a digital feature could be characterized as being representative of an artifact caused by improper illumination, an artifact caused by a physical element that is adhered to the lens through which light is collected by an imaging device, or a pathological feature indicative of a disease.

Distinguishing artifacts from pathological features in digital images

Machine learning models used in medical diagnosis should be validated after being deployed in order to reduce the number of misdiagnoses. Validation processes presented here assess a performance of the machine learning model post-deployment. In post-deployment validation, the validation process monitoring can include: (1) monitoring to ensure a model performs as well as a reference member such as another machine learning model, and (2) monitoring to detect anomalies in data. This post-deployment validation helps identify low-performing models that are already deployed, so that relevant parties can quickly take action to improve either the machine learning model or the input data.

Validating a machine learning model after deployment

Machine learning models used in medical diagnosis should be validated before being deployed in order to reduce the number of misdiagnoses. Validation processes presented here assess a performance of the machine learning model pre-deployment. In one or more examples, prior to the deployment of the machine learning model, the validation process assesses (1) whether a model achieves high enough performance to be deployed, and (2) that the process by which the performance metrics were computed was both sanitary and comprehensive. This pre-deployment validation helps prevent low-performing models from being deployed.

Validating a machine learning model prior to deployment

Growing community of inventors

Portola Valley, CA, United States of America

Kira Whitehouse