Three-dimensional diagnostic ultrasound could be used for physiologic biometrics and positive individual identification, according to a study presented Monday at the AIUM meeting.
Three-dimensional diagnostic ultrasound could be used for physiologic biometrics and positive individual identification, according to a study presented Monday at the AIUM meeting.
Dr. Ganesh Narayanasami and colleagues from the University of Michigan's radiology department used a conventional 3D ultrasound scanner to collect anatomic and physiologic features of human fingers. After repeated scanning tests on several volunteers, the investigators found a number of anatomic and physiologic features that were unique to each individual.
They discovered that heart rate, body temperature, and blood pressure measured by B-mode and Doppler imaging showed a number of identifying characteristics not visible with conventional gray-scale scanning. Gray-scale, compound, and color-flow images from fingers were coregistered using special software.
Three-D color flow revealed unique spatial vascular characteristics as well as heart rate and peripheral flow indicators that were tested before and after the subjects participated in mild physical exercise.
This physiological information along with fingerprint images can provide reliable personal identification in hospitals, schools, and other public and private institutions, Narayanasami said. Ultrasound fingerprinting can be obtained from inexpensive fingerprint sensors that are already commercially available.
The Reading Room: Racial and Ethnic Minorities, Cancer Screenings, and COVID-19
November 3rd 2020In this podcast episode, Dr. Shalom Kalnicki, from Montefiore and Albert Einstein College of Medicine, discusses the disparities minority patients face with cancer screenings and what can be done to increase access during the pandemic.
Study: AI Boosts Ultrasound AUC for Predicting Thyroid Malignancy Risk by 34 Percent Over TI-RADS
February 17th 2025In a study involving assessment of over 1,000 thyroid nodules, researchers found the machine learning model led to substantial increases in sensitivity and specificity for estimating the risk of thyroid malignancy over traditional TI-RADS and guidelines from the American Thyroid Association.