A highly densed deep neural architecture for classification of the multi-organs in fetal ultrasound scans

Artificial intelligence (AI) makes a substantial contribution to decision-making in many intricate application areas of the medical sciences. One such application is organ classification in maternal-fetal ultrasound scans using sophisticated AI methodology like deep neural networks for better analysis. In this paper, we present a novel and highly dense deep neural architecture specifically designed for the multi-organ classification of fetal ultrasound scans. Our proposed approach introduces a unique combination of densely connected layers, convolution layers, and skip connections, tailored to accurately identify and classify multiple fetal organs simultaneously. To the best of our knowledge, this is the first study to address the comprehensive classification of multiple organs in fetal ultrasound images using such a highly dense neural network. The architecture is designed to capture both local and global features, critical for distinguishing intricate organ structures in ultrasound images. The model also minimizes the gradient loss for faster convergence of the model parameters in the training phase. Through extensive evaluation of a curated dataset of fetal ultrasound scans, we demonstrate that our novel architecture achieves superior classification accuracy-96.85%, precision-97.12%, recall-96.66%, F1-score-96.88%, and AUC-ROC score-97.27%, outperforming state-of-the-art methods in the context of multi-organ classification. Thus, the proposed highly dense deep neural architecture presents a promising avenue for enhancing fetal ultrasound imaging, bringing potential benefits to prenatal care, and contributing to improved neonatal outcomes.