Abstract
Objective: Large scale retrospective analysis of fetal ultrasound (US) data is important in the understanding of the cumulative impact of antenatal factors on offspring’s health outcomes. Although the benefits are evident, there is a paucity of research into such large scale studies as it requires tedious and expensive effort in manual processing of large scale data repositories. This study presents an automated framework to facilitate retrospective analysis of large scale US data repositories. Method: Our framework consists of four modules: (1) an image classifier to distinguish the Brightness (B) -mode images; (2) a fetal image structure identifier to select US images containing user-defined fetal structures of interest (fSOI); (3) a biometry measurement algorithm to measure the fSOIs in the images and, (4) a visual evaluation module to allow clinicians to validate the outcomes. Results: We demonstrated our framework using thalamus as the fSOI from a hospital repository of more than 80,000 patients, consisting of 3,816,967 antenatal US files (DICOM objects). Our framework classified 1,869,105 B-mode images and from which 38,786 thalamus images were identified. We selected a random subset of 1290 US files with 558 B-mode (containing 19 thalamus images and the rest being other US data) and evaluated our framework performance. With the evaluation set, B-mode image classification resulted in accuracy, precision, and recall (APR) of 98.67%, 99.75% and 98.57% respectively. For fSOI identification, APR was 93.12%, 97.76% and 80.78% respectively. Conclusion: We introduced a completely automated approach designed to analyze a large scale data repository to enable retrospective clinical research.
Highlights
Ultrasound (US) screening is the global standard of care for the detection of developmental fetal anomalies during pregnancy [1]
As the images could depict different organs and each organ could have multiple views on different planes, we developed a hierarchical classification framework with a feature extractor and a two stage classifier to effectively categorize the fetal images based on organs and the views of an organ
The framework produced accurate classification results for the TC plane retrieval with mean accuracy, precision and recall of 96.45%, 98.95% and 91.45%, which is promising as the experimental analysis used routinely acquired images instead of using cleaned images acquired for research
Summary
Ultrasound (US) screening is the global standard of care for the detection of developmental fetal anomalies during pregnancy [1]. Much more information is embedded in the routinely acquired US images than just the characteristics of the standard set of anatomical structures, and this additional information are currently unused This information can potentially be used to determine the influence of antenatal factors on fetal development [5], e.g., thalamic size as measured on the US images may be associated with maternal methadone usage and may influence neuro-developmental outcomes [6]. This approach requires the understanding the relationship between environmental factors and health outcomes with the fetal growth and anatomical parameters encoded within the US image. These parameters derived from these US images when linked with maternal characteristics (e.g., smoking status, malnutrition, lifestyle, etc.) can help to identify risk factors that contribute
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE journal of translational engineering in health and medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
