Deep Learning-Based Detection of Fetal Brain Anomalies in Ultrasound Images: A Novel Approach

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 8

Year of Publication : 2025

Authors : Sneha Rahul Mhatre, Jagdish W. Bakal

10.14445/23488379/IJEEE-V12I8P102

How to Cite?

Sneha Rahul Mhatre, Jagdish W. Bakal, "Deep Learning-Based Detection of Fetal Brain Anomalies in Ultrasound Images: A Novel Approach," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 8, pp. 11-19, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I8P102

Abstract:

Early detection of fetal brain anomalies is critical for ensuring appropriate medical care. This paper presents an improved deep learning approach integrating image super-resolution with advanced classification techniques. Unlike prior work, we introduce a custom fine-tuned deep learning pipeline that enhances low-resolution ultrasound images before classification. The novel proposed architecture incorporates a modified Enhanced SRGAN for super-resolution and an optimized CNN classifier integrating VGG16, ResNet, and DenseNet features. A dataset of 4,000 grayscale ultrasound images (512×512 pixels) was collected and categorized into four classes: normal, cerebellum anomalies, thalamic anomalies, and ventricular anomalies. To address class imbalance (1039 normal vs. 2961 abnormal), oversampling, augmentation, and class-weighted loss functions were applied. Unlike previous studies, we provide a comprehensive performance analysis using accuracy (92.94%), precision, recall, F1-score, and confusion matrices, demonstrating the impact of super-resolution on classification accuracy. This research significantly improves fetal brain anomaly detection and establishes a robust deep learning pipeline for clinical applications.

Keywords:

Fetal brain ultrasound images, CNN, VGG16, ResNet, DenseNet, Image super resolution.

References:

[1] Samhita Shivaprasad, Sharisha Shanbhog and Jeevan Medikonda, “Detecting Fetal Brain Abnormalities Using Deep Learning Technique,” 2023 International Conference on Recent Advances in Information Technology for Sustainable Development (ICRAIS), Manipal, India, pp. 234-238, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Farzan Vahedifard et al., “Automatic Ventriculomegaly Detection in Fetal Brain MRI: A Step-by-Step Deep Learning Model for Novel 2D-3D Linear Measurements,” Diagnostics, vol. 13, no. 14, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ruowei Qu et al., “Deep Learning-Based Methodology for Recognition of Fetal Brain Standard Scan Planes in 2D Ultrasound Images,” IEEE Access, vol. 8, pp. 44443-44451, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Kavita Shinde, and Anuradha Thakare, “Deep Hybrid Learning Method for Classification of Fetal Brain Abnormalities,” 2021 International Conference on Artificial Intelligence and Machine Vision (AIMV), Gandhinagar, India, pp. 1-6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Tejal Singh, Srinivas Rao Kudavelly, and K. Venkata Suryanarayana, “Deep Learning Based Fetal Face Detection and Visualization in Prenatal Ultrasound,” 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France, pp. 1760-1763, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] D. Kavitha, and C.R. Lakshmi, “Prenatal Detection of Ventricular Septal Defects by VGG-16 Model Using Ultrasound Images,” 2023 3rd International Conference on Mobile Networks and Wireless Communications (ICMNWC), Tumkur, India, pp. 1-6, 2023.
[CrossRef] [Publisher Link]
[7] H. Sharma et al., “Spatio-Temporal Partitioning and Description of Full-Length Routine Fetal Anomaly Ultrasound Scans,” 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, pp. 987-990, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Pan Zeng et al., “Intelligent Recognition of the Ultrasound Standard Plane of the Fetal Cranial Brain with the FCB-Net,” 2022 IEEE 16th International Conference on Anti-counterfeiting, Security, and Identification (ASID), Xiamen, China, pp. 168-172, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Omneya Attallah, Heba Gadelkarim, and Maha A. Sharkas, “Detecting and Classifying Fetal Brain Abnormalities Using Machine Learning Techniques,” 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA, pp. 1371-1376, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] L. Zhao et al., “Automated 3D Fetal Brain Segmentation Using an Optimized Deep Learning Approach,” American Journal of Neuroradiology, vol. 43, no. 3, pp. 448-454, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Yutaro Iwamoto et al., “Unsupervised MRI Super Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 7, no. 2, pp. 426-435, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Alper Güngör et al., “TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging,” IEEE Transactions on Medical Imaging, vol. 41, no. 12, pp. 3562-3574, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Ziyan Lin, and Zihao Chen, “Magnitude-Image Based Data-Consistent Deep Learning Method for MRI Super Resolution,” 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS), Shenzhen, China, pp. 302-305, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yao Sui et al., “Scan-Specific Generative Neural Network for MRI Super-Resolution Reconstruction,” IEEE Transactions on Medical Imaging, vol. 41, no. 6, pp. 1383-1399, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Can Zhao et al., “SMORE: A Self-Supervised Anti-Aliasing and Super-Resolution Algorithm for MRI Using Deep Learning,” IEEE Transactions on Medical Imaging, vol. 40, no. 3, pp. 805-817, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Parisa Ghaderi Daneshmand, Alireza Mehridehnavi, and Hossein Rabbani, “Reconstruction of Optical Coherence Tomography Images Using Mixed Low Rank Approximation and Second Order Tensor Based Total Variation Method,” IEEE Transactions on Medical Imaging, vol. 40, no. 3, pp. 865-878, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Haopeng Zhang, Pengrui Wang, and Zhiguo Jiang, “Nonpairwise-Trained Cycle Convolutional Neural Network for Single Remote Sensing Image Super-Resolution,” IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 5, pp. 4250-4261, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Zhen Chen et al., “Super-Resolution Enhanced Medical Image Diagnosis with Sample Affinity Interaction,” IEEE Transactions on Medical Imaging, vol. 40, no. 5, pp. 1377-1389, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Faming Fang, Juncheng Li, and Tieyong Zeng, “Soft-Edge Assisted Network for Single Image Super-Resolution,” IEEE Transactions on Image Processing, vol. 29, pp. 4656-4668, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Wei Wei et al., “Deep Recursive Network for Hyperspectral Image Super-Resolution,” IEEE Transactions on Computational Imaging, vol. 6, pp. 1233-1244, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Zhi-Wei Pan, and Hui-Liang Shen, “Multispectral Image Super-Resolution via RGB Image Fusion and Radiometric Calibration,” IEEE Transactions on Image Processing, vol. 28, no. 4, pp. 1783-1797, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Mahesh P. Potadar, Raghunath S. Holambe, and Rajan H. Chile, “Design and Development of a Deep Learning Model for Brain Abnormality Detection using MRI,” Computer Methods in Biomechanics and Biomedical Engineering, vol. 12, no. 1, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Sajad Einy et al., “Local and Deep Features based Convolutional Neural Network Frameworks for Brain MRI Anomaly Detection,” Complexity, vol. 2022, no. 1, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Cosmin I. Bercea et al., “Federated Disentangled Representation Learning for Unsupervised Brain Anomaly Detection,” Nature Machine Intelligence, vol. 4, no. 8, pp. 685-695, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Jordi Malé et al., “Unsupervised Deep Learning Architectures for Anomaly Detection in Brain MRI Scans,” Frontiers in Artificial Intelligence and Applications, pp. 90-93, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[26] S. Saranya, and V. Keerthiga, “Detection and Diagnosis of Fetal Ultrasound Images using Deep Learning Classification Methods,” 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, pp. 1050-1058, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Sina Walluscheck et al., “Unsupervised Learning of Healthy Anatomy for Anomaly Detection in Brain CT Scans,” Medical Imaging 2023: Computer-Aided Diagnosis, San Diego, California, United States, vol. 12465, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Ahmed Mateen Buttar et al., “Enhanced Neurological Anomaly Detection in MRI Images using Deep Convolutional Neural Networks,” Frontiers in Medicine, vol. 11, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Hari Mohan Rai, and Kalyan Chatterjee, “Detection of Brain Abnormality by a Novel Lu-Net Deep Neural CNN Model from MR Images,” vol. 2, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Jaime Simarro Viana et al., “Unsupervised 3D Brain Anomaly Detection,” Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 133-142, 2020.
[CrossRef] [Google Scholar] [Publisher Link]