Automatic evaluation of fetal head biometry from ultrasound images using machine learning

Kim, Hwa Pyung; Lee, Sung Min; Kwon, Ja Young; Park, Yejin; Kim, Kang Cheol

doi:10.1088/1361-6579/ab21ac

Cited by 49 publications

(43 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In machines from several manufacturers, automatic image recognition is already being used to perform measurement of the fetal BPD, head circumference (HC), abdominal circumference, and femur length. As example, with automatic evaluation, after deep learning, a success rate of 91.43% and 100% for HC and BPD estimations were obtained, respectively, with an accuracy of 87.14% for the plane acceptance check [106].…”

Section: Artificial Intelligencementioning

confidence: 99%

“…The inspiration is the human brain, hence the designation artificial neuronal networks and machine learning, where the computer automatically recognizes patterns, based on entry of enormous quantities information bits, such as "ideal" ultrasound images of the fetal anatomy. The computer can then perform automatic measurements, for example fetal biometry [106]. In machines from several manufacturers, automatic image recognition is already being used to perform measurement of the fetal BPD, head circumference (HC), abdominal circumference, and femur length.…”

Section: Artificial Intelligencementioning

confidence: 99%

See 1 more Smart Citation

Obstetric ultrasound: where are we and where are we going?

Abramowicz

2021

Ultrasonography

View full text Add to dashboard Cite

Ultrasonography. 2020 Aug 25. Epub ahead of print Diagnostic ultrasound (DUS) is, arguably, the most common technique used in obstetrical practice. From A mode, first described by Ian Donald for gynecology in the late 1950s, to B mode in the 1970s, real-time and gray-scale in the early 1980s, Doppler a little later, sophisticated color Doppler in the 1990s and three dimensional/four-dimensional ultrasound in the 2000s, DUS has not ceased to be closely associated with the practice of obstetrics. The latest innovation is the use of artificial intelligence which will, undoubtedly, take an increasing role in all aspects of our lives, including medicine and, specifically, obstetric ultrasound. In addition, in the future, new visualization methods may be developed, training methods expanded, and workflow and ergonomics improved.

show abstract

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Obstetric ultrasound: where are we and where are we going?

Abramowicz

2021

Ultrasonography

View full text Add to dashboard Cite

show abstract

“…An accurate estimation of fetal weight and GA is essential to detect any abnormal fetal growth pattern, such as small or large for GA, IUGR, or cardiac abnormalities. Kim et al [23] recently published a DL model to automatically calculate the HC together with the biparietal diameter from 2-D US images. A different approach was used by Li et al [24], who first used RF to localize the fetal head and then ellipse fitting to estimate the HC from 2-D US images.…”

Section: For Image Quantification and Feature Extractionmentioning

confidence: 99%

Machine Learning in Fetal Cardiology: What to Expect

et al. 2020

View full text Add to dashboard Cite

In fetal cardiology, imaging (especially echocardiography) has demonstrated to help in the diagnosis and monitoring of fetuses with a compromised cardiovascular system potentially associated with several fetal conditions. Different ultrasound approaches are currently used to evaluate fetal cardiac structure and function, including conventional 2-D imaging and M-mode and tissue Doppler imaging among others. However, assessment of the fetal heart is still challenging mainly due to involuntary movements of the fetus, the small size of the heart, and the lack of expertise in fetal echocardiography of some sonographers. Therefore, the use of new technologies to improve the primary acquired images, to help extract measurements, or to aid in the diagnosis of cardiac abnormalities is of great importance for optimal assessment of the fetal heart. Machine leaning (ML) is a computer science discipline focused on teaching a computer to perform tasks with specific goals without explicitly programming the rules on how to perform this task. In this re-view we provide a brief overview on the potential of ML techniques to improve the evaluation of fetal cardiac function by optimizing image acquisition and quantification/segmentation, as well as aid in improving the prenatal diagnoses of fetal cardiac remodeling and abnormalities.

show abstract

“…Namun, klasifikasi ini membutuhkan prior knowledge yang baik untuk merancang sistem. Setelahnya, penelitian yang dilakukan Kim et al [5] dilakukan dengan menggunakan CNN. Dalam penelitian tersebut, cara paling akurat untuk mendeteksi batas kepala oleh U-Net adalah mengklasifikasikan setiap piksel menjadi empat kelas yang berbeda: jaringan ibu memiliki pola arah horizontal, batas kepala atas memiliki pola busur cekung, batas kepala bawah memiliki pola busur cembung, dan yang tersisa.…”

Section: Pendahuluanunclassified

Deteksi Otomatis Bidang Kepala Janin dari Citra Ultrasonografi 2 Dimensi

Aji¹,

Sardjono²,

Fatoni³

2020

JTITS

View full text Add to dashboard Cite

Modalitas pencitraan primer untuk untuk pemeriksaan anatomi dan fisiologi janin adalah alat ultrasonografi (USG) medis 2 dimensi mengingat harganya yang murah, ketersediaan yang melimpah, kemampuan realtime, dan tidak adanya bahaya radiasi. Head Circumference (HC) merupakan parameter pengukuran biometri janin yang dianalisa untuk mengetahui perkembangan janin secara kuantitatif dengan menggunakan mesin USG. Pada praktik klinis, karena rasio signal-to-noise yang rendah, klinisi seringkali mengalami kesulitan untuk mengenali bidang janin dengan tepat. Lebih dari itu, klinisi kesulitan untuk membuat elips yang paling mendekati hanya dengan tiga titik parameter minor dan mayor yang disediakan mesin USG. Proses deteksi dan pengukuran HC secara manual oleh klinisi membutuhkan waktu yang cukup lama dan akurasinya sangat bergantung dengan pengalaman dan kemampuan klinisi. Penelitian mengenai deteksi dan pengukuran otomatis HC sedang menjadi bidang penelitian yang cukup aktif. Dalam penelitian ini diajukan sebuah sistem deteksi otomatis untuk HC. Metode Convolutional Neural Network (CNN) diajukan untuk melakukan klasifikasi bidang elips janin dari jaringan ibu maupun jaringan janin lainnya. CNN dipekerjakan untuk pixel-wise classification citra ke dalam kelas bidang janin, maternal tissue, ataupun background. Pada penelitian ini, dari 13 citra uji, didapatkan rata rata akurasi segmentasi semantik sebesar 0.76.

show abstract

Automatic evaluation of fetal head biometry from ultrasound images using machine learning

Cited by 49 publications

References 27 publications

Obstetric ultrasound: where are we and where are we going?

Obstetric ultrasound: where are we and where are we going?

Machine Learning in Fetal Cardiology: What to Expect

Deteksi Otomatis Bidang Kepala Janin dari Citra Ultrasonografi 2 Dimensi

Contact Info

Product

Resources

About