Contour Field based Elliptical Shape Prior for the Segment Anything Model
This work addresses the challenge of producing elliptical segmentation results efficiently in deep learning models, which is incremental for specific tasks in medical and natural image analysis.
The paper tackled the problem of integrating elliptical shape priors into the Segment Anything Model (SAM) to improve segmentation accuracy for medical and natural images, resulting in enhanced performance over the original SAM as demonstrated on specific datasets.
The elliptical shape prior information plays a vital role in improving the accuracy of image segmentation for specific tasks in medical and natural images. Existing deep learning-based segmentation methods, including the Segment Anything Model (SAM), often struggle to produce segmentation results with elliptical shapes efficiently. This paper proposes a new approach to integrate the prior of elliptical shapes into the deep learning-based SAM image segmentation techniques using variational methods. The proposed method establishes a parameterized elliptical contour field, which constrains the segmentation results to align with predefined elliptical contours. Utilizing the dual algorithm, the model seamlessly integrates image features with elliptical priors and spatial regularization priors, thereby greatly enhancing segmentation accuracy. By decomposing SAM into four mathematical sub-problems, we integrate the variational ellipse prior to design a new SAM network structure, ensuring that the segmentation output of SAM consists of elliptical regions. Experimental results on some specific image datasets demonstrate an improvement over the original SAM.