Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179344,
        author = {Pavan Vadiraj Puranik and Arati Nayak and Varsha jadhav and Madan Joshi and Prajwal Hiremath and Pavan kalburgi},
        title = {Early Screening Of Fetal Abnormalities Using Ultrasound Images and Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {6050-6053},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179344},
        abstract = {Ultrasound imaging plays a vital role in prenatal screening and the early detection of fetal abnormalities. However, accurately interpreting ultrasound images can be complex, especially when early diagnosis is crucial. Our project introduces a deep learning-based system for fetal abnormality prediction using ultrasound images, aimed at assisting healthcare professionals in making prompt and reliable decisions. By employing the Google Net architecture, the system automatically classifies fetal ultrasound images as normal or abnormal. The integration of Grad-CAM visualization enhances interpretability, while the system's user-friendly web interface allows for efficient image upload and result visualization. This approach improves diagnostic accuracy, reduces interpretation time, and supports healthcare professionals in providing better prenatal care.},
        keywords = {Fetal Abnormality Detection, Ultrasound Imaging, Deep Learning, Google Net, Grad-CAM.},
        month = {May},
        }