Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.01201 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910820574691328 |
|---|---|
| author | Venturini, Lorenzo Budd, Samuel Farruggia, Alfonso Wright, Robert Matthew, Jacqueline Day, Thomas G. Kainz, Bernhard Razavi, Reza Hajnal, Jo V. |
| author_facet | Venturini, Lorenzo Budd, Samuel Farruggia, Alfonso Wright, Robert Matthew, Jacqueline Day, Thomas G. Kainz, Bernhard Razavi, Reza Hajnal, Jo V. |
| contents | The current approach to fetal anomaly screening is based on biometric measurements derived from individually selected ultrasound images. In this paper, we introduce a paradigm shift that attains human-level performance in biometric measurement by aggregating automatically extracted biometrics from every frame across an entire scan, with no need for operator intervention. We use a convolutional neural network to classify each frame of an ultrasound video recording. We then measure fetal biometrics in every frame where appropriate anatomy is visible. We use a Bayesian method to estimate the true value of each biometric from a large number of measurements and probabilistically reject outliers. We performed a retrospective experiment on 1457 recordings (comprising 48 million frames) of 20-week ultrasound scans, estimated fetal biometrics in those scans and compared our estimates to the measurements sonographers took during the scan. Our method achieves human-level performance in estimating fetal biometrics and estimates well-calibrated credible intervals in which the true biometric value is expected to lie. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01201 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Whole-examination AI estimation of fetal biometrics from 20-week ultrasound scans Venturini, Lorenzo Budd, Samuel Farruggia, Alfonso Wright, Robert Matthew, Jacqueline Day, Thomas G. Kainz, Bernhard Razavi, Reza Hajnal, Jo V. Computer Vision and Pattern Recognition Machine Learning I.4.7; J.3 The current approach to fetal anomaly screening is based on biometric measurements derived from individually selected ultrasound images. In this paper, we introduce a paradigm shift that attains human-level performance in biometric measurement by aggregating automatically extracted biometrics from every frame across an entire scan, with no need for operator intervention. We use a convolutional neural network to classify each frame of an ultrasound video recording. We then measure fetal biometrics in every frame where appropriate anatomy is visible. We use a Bayesian method to estimate the true value of each biometric from a large number of measurements and probabilistically reject outliers. We performed a retrospective experiment on 1457 recordings (comprising 48 million frames) of 20-week ultrasound scans, estimated fetal biometrics in those scans and compared our estimates to the measurements sonographers took during the scan. Our method achieves human-level performance in estimating fetal biometrics and estimates well-calibrated credible intervals in which the true biometric value is expected to lie. |
| title | Whole-examination AI estimation of fetal biometrics from 20-week ultrasound scans |
| topic | Computer Vision and Pattern Recognition Machine Learning I.4.7; J.3 |
| url | https://arxiv.org/abs/2401.01201 |