Highlight the Advanced Capabilities and the Computational Efficiency of DeepLabV3+ in Medical Image Segmentation: An Ablation Study

In clinical practice, identifying the location and extent of tumors and lesions is crucial for disease diagnosis and treatment. Artificial intelligence, particularly deep neural networks, offers precise and automated segmentation, yet its application is often hindered by limited data and high computational demands. Transfer learning helps mitigate these challenges by significantly reducing computational costs, although applying these models can still be resource-intensive. This study aims to present a flexible and computationally efficient architecture that leverages transfer learning and delivers highly accurate results across various medical imaging problems. We evaluated three datasets with varying similarities to ImageNet: ISIC 2018 (skin lesions), CBIS-DDSM (breast masses), and the Shenzhen & Montgomery CXR Set (lung segmentation). An ablation study on ISIC 2018 tested various pre-trained backbones, architectures, and loss functions. The optimal configuration—DeepLabV3+ with a pre-trained ResNet50 backbone and Log-Cosh Dice loss—was validated on the remaining datasets, achieving state-of-the-art results. Our findings demonstrate that computationally simpler architectures can deliver robust performance without extensive resources, establishing DeepLabV3+ with the ResNet50 as a baseline for future studies. Finally, we emphasize that in the medical domain, enhancing data quality is more critical for improving segmentation accuracy than increasing model complexity.