Abstract
The goal of this study was to evaluate the maturity of current Deep Learning classification techniques for their application in a real maternal-fetal clinical environment. A large dataset of routinely acquired maternal-fetal screening ultrasound images (which will be made publicly available) was collected from two different hospitals by several operators and ultrasound machines. All images were manually labeled by an expert maternal fetal clinician. Images were divided into 6 classes: four of the most widely used fetal anatomical planes (Abdomen, Brain, Femur and Thorax), the mother’s cervix (widely used for prematurity screening) and a general category to include any other less common image plane. Fetal brain images were further categorized into the 3 most common fetal brain planes (Trans-thalamic, Trans-cerebellum, Trans-ventricular) to judge fine grain categorization performance. The final dataset is comprised of over 12,400 images from 1,792 patients, making it the largest ultrasound dataset to date. We then evaluated a wide variety of state-of-the-art deep Convolutional Neural Networks on this dataset and analyzed results in depth, comparing the computational models to research technicians, which are the ones currently performing the task daily. Results indicate for the first time that computational models have similar performance compared to humans when classifying common planes in human fetal examination. However, the dataset leaves the door open on future research to further improve results, especially on fine-grained plane categorization.
Highlights
The goal of this study was to evaluate the maturity of current Deep Learning classification techniques for their application in a real maternal-fetal clinical environment
The acquisition of fetal and maternal ultrasound images in most fetal medicine centers is done following international guidelines promoted by scientific committees[8,9]
A wide variety of Convolutional Neural Networks (CNNs) were benchmarked using a setting mimicking a real clinical scenario and their performance directly compared on the same data against research technicians who performs this task on a daily basis
Summary
The goal of this study was to evaluate the maturity of current Deep Learning classification techniques for their application in a real maternal-fetal clinical environment. We evaluated a wide variety of state-of-the-art deep Convolutional Neural Networks on this dataset and analyzed results in depth, comparing the computational models to research technicians, which are the ones currently performing the task daily. The acquisition of fetal and maternal ultrasound images in most fetal medicine centers is done following international guidelines promoted by scientific committees[8,9] This means that images are obtained following the same protocols in a repeatable way. In the last few years, CNNs have shown its usefulness in a wide set of medical applications, such as dermatology[11], radiology[12] and/or to classify or segment organs and lesions in images from computer tomographies and MRI13 These methods are known to excel “at automatically recognizing complex patterns in image data and provide a quantitative, rather than qualitative assessment”[12]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
