Emily H Frisch, Anant Jain, Mike Jin, Erik P Duhaime, Amol Malshe, Steve Corey, Robert Allen, Nicole M Duggan, Chanel E Fischetti
{"title":"Artificial Intelligence to Determine Fetal Sex.","authors":"Emily H Frisch, Anant Jain, Mike Jin, Erik P Duhaime, Amol Malshe, Steve Corey, Robert Allen, Nicole M Duggan, Chanel E Fischetti","doi":"10.1055/a-2265-9177","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong> This proof-of-concept study assessed how confidently an artificial intelligence (AI) model can determine the sex of a fetus from an ultrasound image.</p><p><strong>Study design: </strong> Analysis was performed using 19,212 ultrasound image slices from a high-volume fetal sex determination practice. This dataset was split into a training set (11,769) and test set (7,443). A computer vision model was trained using a transfer learning approach with EfficientNetB4 architecture as base. The performance of the computer vision model was evaluated on the hold out test set. Accuracy, Cohen's Kappa and Multiclass Receiver Operating Characteristic area under the curve (AUC) were used to evaluate the performance of the model.</p><p><strong>Results: </strong> The AI model achieved an Accuracy of 88.27% on the holdout test set and a Cohen's Kappa score 0.843. The ROC AUC score for Male was calculated to be 0.896, for Female a score of 0.897, for Unable to Assess a score of 0.916, and for Text Added a score of 0.981 was achieved.</p><p><strong>Conclusion: </strong> This novel AI model proved to have a high rate of fetal sex capture that could be of significant use in areas where ultrasound expertise is not readily available.</p><p><strong>Key points: </strong>· This is the first proof-of-concept AI model to determine fetal sex.. · This study adds to the growing research in ultrasound AI.. · Our findings demonstrate AI integration into obstetric care..</p>","PeriodicalId":7584,"journal":{"name":"American journal of perinatology","volume":" ","pages":"1836-1840"},"PeriodicalIF":1.5000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of perinatology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1055/a-2265-9177","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/9 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"OBSTETRICS & GYNECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: This proof-of-concept study assessed how confidently an artificial intelligence (AI) model can determine the sex of a fetus from an ultrasound image.
Study design: Analysis was performed using 19,212 ultrasound image slices from a high-volume fetal sex determination practice. This dataset was split into a training set (11,769) and test set (7,443). A computer vision model was trained using a transfer learning approach with EfficientNetB4 architecture as base. The performance of the computer vision model was evaluated on the hold out test set. Accuracy, Cohen's Kappa and Multiclass Receiver Operating Characteristic area under the curve (AUC) were used to evaluate the performance of the model.
Results: The AI model achieved an Accuracy of 88.27% on the holdout test set and a Cohen's Kappa score 0.843. The ROC AUC score for Male was calculated to be 0.896, for Female a score of 0.897, for Unable to Assess a score of 0.916, and for Text Added a score of 0.981 was achieved.
Conclusion: This novel AI model proved to have a high rate of fetal sex capture that could be of significant use in areas where ultrasound expertise is not readily available.
Key points: · This is the first proof-of-concept AI model to determine fetal sex.. · This study adds to the growing research in ultrasound AI.. · Our findings demonstrate AI integration into obstetric care..
期刊介绍:
The American Journal of Perinatology is an international, peer-reviewed, and indexed journal publishing 14 issues a year dealing with original research and topical reviews. It is the definitive forum for specialists in obstetrics, neonatology, perinatology, and maternal/fetal medicine, with emphasis on bridging the different fields.
The focus is primarily on clinical and translational research, clinical and technical advances in diagnosis, monitoring, and treatment as well as evidence-based reviews. Topics of interest include epidemiology, diagnosis, prevention, and management of maternal, fetal, and neonatal diseases. Manuscripts on new technology, NICU set-ups, and nursing topics are published to provide a broad survey of important issues in this field.
All articles undergo rigorous peer review, with web-based submission, expedited turn-around, and availability of electronic publication.
The American Journal of Perinatology is accompanied by AJP Reports - an Open Access journal for case reports in neonatology and maternal/fetal medicine.