Chest radiography is a commonly utilized imaging technique for acquiring Chest X-Ray (CXR) images due to its cost-effectiveness and its role in diagnosing lung?related disorders. Nevertheless, interpreting CXR images can be challenging, and the process of separating the lung field from CXR images can be a valuable tool for assessing and diagnosing lung diseases. While various segmentation methods exist, this study primarily focuses on META’s latest Segment Anything Model (SAM). SAM is an Artificial Intelligence (AI) model designed to segment objects within an image. This research aims to harness SAM’s capabilities for segmenting CXR images. Additionally, we explore the potential of another novel model called Grounding DINO. Grounding DINO is a zero-shot object detection model that utilizes a Swin (Shifted Windows) transformer for extracting image features and BERT (Bidirectional Encoder Representations from Transformers) for extracting textual information. It is primarily employed to detect objects in an image based on a provided text prompt, creating bounding boxes around the objects when certain text and box thresholds are met. These bounding boxes are then used as prompts for SAM to generate segmentation masks. The proposed framework has been assessed on CXRs obtained from patients at Emory Hospital in Atlanta, Georgia, USA and further evaluated using NIH clinical center’s CXR image dataset.

Abstract — The Segment Anything Model (SAM) is a state-of-the-art deep learning architecture for image seg- mentation that allows users to segment arbitrary objects in images using points, or bounding boxes. SAM uses a novel two-stage approach that first encodes the input image into a high-dimensional embedding, and then generates object masks using the embedding and the input prompt. This ap- proach allows SAM to produce high-quality segmentation even for objects that were not seen during training, and to handle complex input prompts with multiple objects and attributes. We evaluate SAM on the open source Chest X- ray dataset known as Japanese Society of Radiological Technology (JSRT) dataset and another dataset obtained from Emory Hospital, Atlanta, Georgia,USA and show that it achieves state-of-the-art performance in terms of Stability Score and Jaccard Index including the perfor- mance across different demographic data such as age and gender. Overall, SAM provides a powerful tool for image segmentation, enabling efficient and accurate object detec- tion and segmentation for a wide range of applications. It also represents a significant advance in the field of image segmentation and opens up new opportunities for interactive and multi-modal image analysis.