ResNet-34 with Lightweight Decoder for Accurate and Efficient Segmentation of Fetal Brain MRI

2026-05-31

AI Summary

Fetal brain MRI segmentation remains highly challenging due to fetal motion, low tissue contrast, and anatomical variations across gestational ages. To address these issues, this work proposes a lightweight yet effective segmentation architecture that combines a ResNet-34 encoder with a compact MLP-based decoder. The model incorporates adaptive feature refinement to enhance boundary preservation and replaces transposed convolutions with bilinear upsampling, achieving a favorable trade-off between accuracy, parameter efficiency, and inference speed. Evaluated on the FeTA 2021 dataset, the proposed method attains a Dice coefficient of 90.33%, an IoU of 86.93%, and an overall accuracy of 97.37%, significantly outperforming baseline models such as U-Net and DeepLabV3. These results demonstrate its strong potential for real-time clinical deployment.

Abstract

Accurate segmentation of fetal brain tissues in Magnetic Resonance Imaging (MRI) is critical for early diagnosis of congenital abnormalities and improving prenatal care. However, the task remains difficult because of fetal motion, low tissue contrast, and major anatomical variability throughout gestational ages, particularly in segmenting complex structures such as white matter, gray matter, lateral ventricles, deep gray matter, extra-cerebrospinal fluid, cerebellum, and brainstem. As a solution to these difficulties, this research introduces a novel deep learning model that combines a ResNet-34 encoder with a lightweight decoder leveraging multi-layer perceptron (MLP) modules for adaptive feature refinement. This design specifically enhances the model's ability to preserve anatomical boundaries and mitigate segmentation errors caused by motion artifacts and intensity inhomogeneities. Computational efficiency is achieved by reducing parameter count, employing bilinear upsampling instead of transposed convolutions, and optimizing the decoder for speed without sacrificing accuracy. Trained and validated on the FeTA 2021 dataset using 5-fold cross-validation, the proposed model outperforms baseline architectures such as UNet, UNet++, DeepLabV3, and DeepLabV3+, achieving an average Accuracy of 97.37% with a mean Dice Similarity Coefficient (DSC) of 90.33%, mean Intersection over Union (IoU) of 86.93%, and Precision of 90.83%. Additionally, its fast inference time and reduced computational load make it well-suited for integration into real-time clinical workflows.

Problem

• fetal brain MRI
• image segmentation
• anatomical variability
• motion artifacts
• low tissue contrast

Innovation

• Lightweight Decoder
• ResNet-34
• MLP-based Feature Refinement
• Fetal Brain MRI Segmentation
• Efficient Deep Learning