FetalDenseNet: multi-scale deep learning for enhanced early detection of fetal anatomical planes in prenatal ultrasound
The study shows that CNN-based models, particularly DenseNet169, significantly improve diagnostic accuracy in fetal ultrasound interpretation. This advancement reduces error rates and provides support for clinical decision-making in prenatal care.
Authors
- Tania Islam (ORCID: https://orcid.org/0000-0003-3056-7799)
- Samrat Kumar Dey (ORCID: https://orcid.org/0000-0002-7999-8576)
- Umme Raihan Siddiqi (ORCID: https://orcid.org/0000-0001-6550-4179)
- Md. Shabukta Haider
- Arpita Howlader (ORCID: https://orcid.org/0000-0001-5413-2277)
- Deblina Mazumder Setu
- Md. Mahbubur Rahman (ORCID: https://orcid.org/0000-0001-6203-3375)
- Tushar Kanti Saha (ORCID: https://orcid.org/0000-0001-5577-4917)
Institutions
- University of Missouri Health System (US)
- Patuakhali Science and Technology University (BD)
- University of Barishal (BD)
- Bangladesh Open University (BD)
- Dhaka University of Engineering & Technology (BD)
- Shaheed Suhrawardy Medical College (BD)
- University of Missouri (US)
Publication Details
- Journal
- Journal of Perinatal Medicine
- Published
- 2025-09-23
- DOI
- https://doi.org/10.1515/jpm-2025-0249
- Primary Topic
- Fetal and Pediatric Neurological Disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00