ABSTRACT
The Segment Anything Model (SAM) is a foundational model that has demonstrated impressive results in the field of natural image segmentation. However, its performance remains suboptimal for medical image segmentation, particularly when delineating lesions with irregular shapes and low contrast. This can be attributed to the significant domain gap between medical images and natural images on which SAM was originally trained. In this paper, we propose an adaptation of SAM specifically tailored for lesion segmentation termed LeSAM. LeSAM first learns medical-specific domain knowledge through an efficient adaptation module and integrates it with the general knowledge obtained from the pre-trained SAM. Subsequently, we leverage this merged knowledge to generate lesion masks using a modified mask decoder implemented as a lightweight U-shaped network design. This modification enables better delineation of lesion boundaries while facilitating ease of training. We conduct comprehensive experiments on various lesion segmentation tasks involving different image modalities such as CT scans, MRI scans, ultrasound images, dermoscopic images, and endoscopic images. Our proposed method achieves superior performance compared to previous state-of-the-art methods in 8 out of 12 lesion segmentation tasks while achieving competitive performance in the remaining 4 datasets. Additionally, ablation studies are conducted to validate the effectiveness of our proposed adaptation modules and modified decoder.
Subject(s)
Algorithms , Image Interpretation, Computer-Assisted , Humans , Image Interpretation, Computer-Assisted/methodsABSTRACT
Low-dose computed tomography (LDCT) imaging faces great challenges. Although supervised learning has revealed great potential, it requires sufficient and high-quality references for network training. Therefore, existing deep learning methods have been sparingly applied in clinical practice. To this end, this paper presents a novel Unsharp Structure Guided Filtering (USGF) method, which can reconstruct high-quality CT images directly from low-dose projections without clean references. Specifically, we first employ low-pass filters to estimate the structure priors from the input LDCT images. Then, inspired by classical structure transfer techniques, deep convolutional networks are adopted to implement our imaging method which combines guided filtering and structure transfer. Finally, the structure priors serve as the guidance images to alleviate over-smoothing, as they can transfer specific structural characteristics to the generated images. Furthermore, we incorporate traditional FBP algorithms into self-supervised training to enable the transformation of projection domain data to the image domain. Extensive comparisons and analyses on three datasets demonstrate that the proposed USGF has achieved superior performance in terms of noise suppression and edge preservation, and could have a significant impact on LDCT imaging in the future.
Subject(s)
Image Processing, Computer-Assisted , Tomography, X-Ray Computed , Image Processing, Computer-Assisted/methods , Tomography, X-Ray Computed/methods , Algorithms , Signal-To-Noise RatioABSTRACT
Speckle is a major quality degrading factor in optical coherence tomography (OCT) images. In this work we propose a new deep learning network for speckle reduction in retinal OCT images, termed DeSpecNet. Unlike traditional algorithms, the model can learn from training data instead of manually selecting parameters such as noise level. The proposed deep convolutional neural network (CNN) applies strategies including residual learning, shortcut connection, batch normalization and leaky rectified linear units to achieve good despeckling performance. Application of the proposed method to the OCT images shows great improvement in both visual quality and quantitative indices. The proposed method provides good generalization ability for different types of retinal OCT images. It outperforms state-of-the-art methods in suppressing speckles and revealing subtle features while preserving edges.