Inter-observer variability in fetal biometric measurements

Kilani, Rami; Aleyadeh, Wesam; Atieleh, Luay Abu; Suleimat, Abdul Mane Al; Khadra, Maysa; Hawamdeh, Hassan M

doi:10.1016/j.tjog.2017.12.006

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the training of the seven Mask-R-CNN models, we adopted an image-centric training procedure 12 . Images were resized such that their scale (shorter edge) is 800 pixels 27 .…”

Section: Methodsmentioning

confidence: 99%

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Slimani,

Hounka,

Mahmoudi

et al. 2023

Nat Commun

View full text Add to dashboard Cite

Fetal biometry and amniotic fluid volume assessments are two essential yet repetitive tasks in fetal ultrasound screening scans, aiding in the detection of potentially life-threatening conditions. However, these assessment methods can occasionally yield unreliable results. Advances in deep learning have opened up new avenues for automated measurements in fetal ultrasound, demonstrating human-level performance in various fetal ultrasound tasks. Nevertheless, the majority of these studies are retrospective in silico studies, with a limited number including African patients in their datasets. In this study we developed and prospectively assessed the performance of deep learning models for end-to-end automation of fetal biometry and amniotic fluid volume measurements. These models were trained using a newly constructed database of 172,293 de-identified Moroccan fetal ultrasound images, supplemented with publicly available datasets. the models were then tested on prospectively acquired video clips from 172 pregnant people forming a consecutive series gathered at four healthcare centers in Morocco. Our results demonstrate that the 95% limits of agreement between the models and practitioners for the studied measurements were narrower than the reported intra- and inter-observer variability among expert human sonographers for all the parameters under study. This means that these models could be deployed in clinical conditions, to alleviate time-consuming, repetitive tasks, and make fetal ultrasound more accessible in limited-resource environments.

show abstract

“…In the training of the seven Mask-R-CNN models, we adopted an image-centric training procedure 12 . Images were resized such that their scale (shorter edge) is 800 pixels 27 .…”

Section: Methodsmentioning

confidence: 99%

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Slimani,

Hounka,

Mahmoudi

et al. 2023

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Ultrasound is nowadays the cornerstone of obstetrics. Measurements taken during an ultrasound scan are essential for pregnancy management and optimal delivery 1 . Every measurement is subject to error.…”

Section: Introductionmentioning

confidence: 99%

Expected‐value bias in mid‐trimester preterm birth screening

Aiartzaguena

Campo

Melchor

et al. 2022

Ultrasound in Obstet & Gyne

View full text Add to dashboard Cite

What are the novel findings of this work?This work demonstrates the presence of expected-value bias when measuring cervical length (CL) in mid-trimester preterm birth screening. Blinding has demonstrated to be an effective strategy to improve the performance of CL screening in clinical practice. What are the clinical implications of this work?When the final risk depends on only one ultrasound measurement, the operator might be more biased than when the final risk is determined based on multiple factors. This study emphasizes the importance of auditing ultrasound measurements as part of quality control in clinical practice and proposes blinding as an effective strategy to decrease observer bias in CL measurement.

show abstract

“…FB coupled with AFV assessments are time-consuming, repetitive, and error-prone tasks, and several studies have stressed the need for quality audits to ensure measurements reproducibility and lower inter and intra-observer variability [11][12][13] .…”

Section: Introductionmentioning

confidence: 99%

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Slimani¹,

Hounka

Mahmoudi

et al. 2022

Preprint

View full text Add to dashboard Cite

Fetal biometry (FB) and amniotic fluid volume (AFV) assessments are two crucial yet repetitive tasks of fetal ultrasound screening scans that help detect potential life-threatening conditions, however, they suffer from reproducibility and reliability issues. Advances in deep learning have led to new applications in measurement automation in fetal ultrasound, showcasing human-level performances in several fetal ultrasound tasks. However, most of the studies performed are retrospective “in silico” studies and few include African patients in their dataset. Here we develop and prospectively assess the performance of deep learning models for an end-to-end FB and AFV automation from a newly constructed database of 172 293 de-identified Moroccan fetal ultrasound images in addition to publicly available datasets. They were tested on prospectively acquired video clips from 172 patients forming a consecutive series gathered at four healthcare centers in Morocco. Our results show the 95% limits of agreement between the models and practitioners for the studied measurements were narrower than reported intra and inter-observer variability for human expert sonographers for all the studied parameters. This means that these models could be deployed in clinical conditions, to alleviate time-consuming, repetitive tasks, and to make fetal US more accessible in limited resources environments.

show abstract

Inter-observer variability in fetal biometric measurements

Cited by 4 publications

References 12 publications

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Expected‐value bias in mid‐trimester preterm birth screening

Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning

Contact Info

Product

Resources

About