Dataset Information

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound.

ABSTRACT: Identifying and interpreting fetal standard scan planes during 2-D ultrasound mid-pregnancy examinations are highly complex tasks, which require years of training. Apart from guiding the probe to the correct location, it can be equally difficult for a non-expert to identify relevant structures within the image. Automatic image processing can provide tools to help experienced as well as inexperienced operators with these tasks. In this paper, we propose a novel method based on convolutional neural networks, which can automatically detect 13 fetal standard views in freehand 2-D ultrasound data as well as provide a localization of the fetal structures via a bounding box. An important contribution is that the network learns to localize the target anatomy using weak supervision based on image-level labels only. The network architecture is designed to operate in real-time while providing optimal output for the localization task. We present results for real-time annotation, retrospective frame retrieval from saved videos, and localization on a very large and challenging dataset consisting of images and video recordings of full clinical anomaly screenings. We found that the proposed method achieved an average F1-score of 0.798 in a realistic classification experiment modeling real-time detection, and obtained a 90.09% accuracy for retrospective frame retrieval. Moreover, an accuracy of 77.8% was achieved on the localization task.

SUBMITTER: Baumgartner CF

PROVIDER: S-EPMC6051487 | biostudies-other | 2017 Nov

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound.

Baumgartner Christian F CF Kamnitsas Konstantinos K Matthew Jacqueline J Fletcher Tara P TP Smith Sandra S Koch Lisa M LM Kainz Bernhard B Rueckert Daniel D

IEEE transactions on medical imaging 20170711 11

Identifying and interpreting fetal standard scan planes during 2-D ultrasound mid-pregnancy examinations are highly complex tasks, which require years of training. Apart from guiding the probe to the correct location, it can be equally difficult for a non-expert to identify relevant structures within the image. Automatic image processing can provide tools to help experienced as well as inexperienced operators with these tasks. In this paper, we propose a novel method based on convolutional neura ...[more]

PMID: 28708546

Similar Datasets

Project description:BackgroundThe benefit of fetal echocardiograms (FE) to detect severe congenital heart diseases (SCHD) in the setting of a normal second-trimester ultrasound is unclear. We aimed to assess whether the increase in SCHD detection rates when FE are performed for risk factors in the setting of a normal ultrasound was clinically significant to justify the resources needed.MethodsThis is a multicenter, population-based, retrospective cohort study, including all singleton pregnancies and offspring in Quebec (Canada) between 2007 and 2015. Administrative health care data were linked with FE clinical data to gather information on prenatal diagnosis of CHD, indications for FE, outcomes of pregnancy and offspring, postnatal diagnosis of CHD, cardiac interventions, and causes of death. The difference between the sensitivity to detect SCHD with and without FE for risk factors was calculated using generalized estimating equations with a noninferiority margin of 5 percentage points.ResultsA total of 688 247 singleton pregnancies were included, of which 30 263 had at least one FE. There were 1564 SCHD, including 1071 that were detected prenatally (68.5%). There were 12 210 FE performed for risk factors in the setting of a normal second-trimester ultrasound, which led to the detection of 49 additional cases of SCHD over 8 years. FE referrals for risk factors increased sensitivity by 3.1 percentage points (95% CI, 2.3-4.0; P<0.0001 for noninferiority).ConclusionsIn the setting of a normal second-trimester ultrasound, adding a FE for risk factors offered low incremental value to the detection rate of SCHD in singleton pregnancies. The current ratio of clinical gains versus the FE resources needed to screen for SCHD in singleton pregnancies with isolated risk factors does not seem favorable. Further studies should evaluate whether these resources could be better allocated to increase SCHD sensitivity at the ultrasound level, and to help decrease heterogeneity between regions, institutions and operators.

Project description:IntroductionCongenital anomalies are the most encountered cause of fetal death, infant mortality and morbidity. 7.9 million infants are born with congenital anomalies yearly. Early detection of congenital anomalies facilitates life-saving treatments and stops the progression of disabilities. Congenital anomalies can be diagnosed prenatally through morphology scans. A correct interpretation of the morphology scan allows a detailed discussion with the parents regarding the prognosis. The central feature of this project is the development of a specialised intelligent system that uses two-dimensional ultrasound movies obtained during the standard second trimester morphology scan to identify congenital anomalies in fetuses.Methods and analysisThe project focuses on three pillars: committee of deep learning and statistical learning algorithms, statistical analysis, and operational research through learning curves. The cross-sectional study is divided into a training phase where the system learns to detect congenital anomalies using fetal morphology ultrasound scan, and then it is tested on previously unseen scans. In the training phase, the intelligent system will learn to answer the following specific objectives: (a) the system will learn to guide the sonographer's probe for better acquisition; (b) the fetal planes will be automatically detected, measured and stored and (c) unusual findings will be signalled. During the testing phase, the system will automatically perform the above tasks on previously unseen videos.Pregnant patients in their second trimester admitted for their routine scan will be consecutively included in a 32-month study (4 May 2022-31 December 2024). The number of patients is 4000, enrolled by 10 doctors/sonographers. We will develop an intelligent system that uses multiple artificial intelligence algorithms that interact between themselves, in bulk or individual. For each anatomical part, there will be an algorithm in charge of detecting it, followed by another algorithm that will detect whether anomalies are present or not. The sonographers will validate the findings at each intermediate step.Ethics and disseminationAll protocols and the informed consent form comply with the Health Ministry and professional society ethics guidelines. The University of Craiova Ethics Committee has approved this study protocol as well as the Romanian Ministry of Research Innovation and Digitization that funded this research. The study will be implemented and reported in line with the STROBE (STrengthening the Reporting of OBservational studies in Epidemiology) statement.Trial registration numberThe study is registered under the name 'Pattern recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical Learning', project number 101PCE/2022, project code PN-III-P4-PCE-2021-0057.Trial registrationClinicalTrials.gov, unique identifying number NCT05738954, date of registration: 2 November 2023.

Dataset Information

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound.

Publications

SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets