| Autor: |
Willis, A., Lee, C., Krogue, J., Watters, A., Vaidyanathan, M., Young‐Lin, N., Uddin, A., Tiyasirichokchai, T., Caron, S., Santi, A., Melnick, D., Martin, A., Hudson, K., Jansen, S., Singh, P., Arguelles, C., Etemadi, M., Prabhakara, S., Gomes, R.G. |
| Předmět: |
|
| Zdroj: |
Ultrasound in Obstetrics & Gynecology; Sep2024 Supplement 1, Vol. 64, p17-18, 2p |
| Abstrakt: |
This article discusses the use of artificial intelligence (AI) systems to interpret blind sweep ultrasound scans for estimating gestational age (GA) in new clinical settings. The study involved adapting a previously trained AI model to a different probe manufacturer and evaluating its performance on blind sweeps from 824 patients. Without fine-tuning, the model's mean absolute error (MAE) for GA estimation was comparable to standard clinical estimates. However, after fine-tuning on a small number of scans, the model achieved similar performance to the original setting. These findings suggest that AI-based ultrasound assessment can be successfully deployed in new sites and expand access to care in low-resource settings. [Extracted from the article] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Plný text