Basic Science and Instrumentation Scientific Session 2
Automated Field of Interest Determination Algorithm: An Optimization for Quantitative Ultrasound Analyses of Cervical Tissues in Spontaneous Preterm Birth Risk Assessment
Sunday, April 7, 2024
3:07pm – 3:19pm
Location: 410
Authors: Jingyi Zuo, Virginia Polytechnic Institute and State University Douglas Simpson, University of Illinois Urbana-Champaign William O'Brien, University of Illinois Urbana Champaign Barbara McFarlin, University of Illinois at Chicago Aiguo Han, Virginia Tech ,
Ultrasound imaging has long been used as a qualitative diagnostic approach. Quantitative ultrasound technique, however, complements conventional B-mode ultrasound imaging by quantifying tissue physiological and pathological status. Recent clinical studies have shown that QUS is promising in detecting early cervical microstructure changes during pregnancy, and it does not use ionizing radiation, making it a safer option for pregnant women and developing fetuses.
However, several time-consuming manual processes are used to define the field of interest (FOI) for QUS. This off-line process hinders QUS from clinical translation because it distracts clinicians from their work and patients. There is a critical need to automate the FOI determination process.
Our algorithm addresses the automatic FOI determination for cervical ultrasound images to replace human annotation in QUS analysis for predicting sPTB risk. It also offers a promising solution to overcome the time-consuming and variability of sonographer acquisitions and facilitates the clinical transition of QUS.