IVCVJul 22, 2024

SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection

arXiv:2407.15728v216 citationsh-index: 16
AI Analysis

This addresses COVID-19 detection in medical imaging, but it is incremental as it builds on existing models like SAM and CLIP for a specific domain.

The paper tackles segmentation of 3D CT scans for COVID-19 detection by introducing SAM2CLIP2SAM, a vision-language model that combines SAM and CLIP to segment lungs, then uses RACNet for classification, showing improved performance on two annotated databases.

This paper presents a new approach for effective segmentation of images that can be integrated into any model and methodology; the paradigm that we choose is classification of medical images (3-D chest CT scans) for Covid-19 detection. Our approach includes a combination of vision-language models that segment the CT scans, which are then fed to a deep neural architecture, named RACNet, for Covid-19 detection. In particular, a novel framework, named SAM2CLIP2SAM, is introduced for segmentation that leverages the strengths of both Segment Anything Model (SAM) and Contrastive Language-Image Pre-Training (CLIP) to accurately segment the right and left lungs in CT scans, subsequently feeding these segmented outputs into RACNet for classification of COVID-19 and non-COVID-19 cases. At first, SAM produces multiple part-based segmentation masks for each slice in the CT scan; then CLIP selects only the masks that are associated with the regions of interest (ROIs), i.e., the right and left lungs; finally SAM is given these ROIs as prompts and generates the final segmentation mask for the lungs. Experiments are presented across two Covid-19 annotated databases which illustrate the improved performance obtained when our method has been used for segmentation of the CT scans.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes