Boosting Medical Image Segmentation Performance with Adaptive Convolution Layer
This work addresses the challenge of handling diverse scales and configurations in medical images for clinical applications, representing an incremental improvement over existing methods.
The paper tackles the problem of limited adaptability in medical image segmentation due to fixed kernel sizes in CNNs by proposing an adaptive convolution layer that dynamically adjusts kernel size based on local context, resulting in superior segmentation accuracy, Dice, and IoU on benchmark datasets like SegPC2021 and ISIC2018.
Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditional CNNs have achieved remarkable success in this field. However, they often rely on fixed kernel sizes, which can limit their performance and adaptability in medical images where features exhibit diverse scales and configurations due to variability in equipment, target sizes, and expert interpretations. In this paper, we propose an adaptive layer placed ahead of leading deep-learning models such as UCTransNet, which dynamically adjusts the kernel size based on the local context of the input image. By adaptively capturing and fusing features at multiple scales, our approach enhances the network's ability to handle diverse anatomical structures and subtle image details, even for recently performing architectures that internally implement intra-scale modules, such as UCTransnet. Extensive experiments are conducted on benchmark medical image datasets to evaluate the effectiveness of our proposal. It consistently outperforms traditional \glspl{CNN} with fixed kernel sizes with a similar number of parameters, achieving superior segmentation Accuracy, Dice, and IoU in popular datasets such as SegPC2021 and ISIC2018. The model and data are published in the open-source repository, ensuring transparency and reproducibility of our promising results.