This paper presents a study on polypoid lesion segmentation using the YOLO-V8 network in wireless video capsule endoscopy (WCE) images. The research addresses the challenge of early detection and removal of polyps, which are precursors to malignancy, in gastrointestinal (GI) tract disorders. WCE is a non-invasive imaging technique that captures images of the GI tract using swallowable camera devices. Due to the large volume of images generated, automated polyp segmentation is crucial for efficient diagnosis. The study evaluates computer-aided approaches for polyp detection using a dataset of labeled anomalies and findings. YOLO-V8, an improved deep learning model, is used for polyp segmentation and is found to perform better than existing methods, achieving high precision and recall. The study highlights the potential of automated detection systems in improving GI polyp identification. The YOLO-V8 model is evaluated across different iterations (n, s, m, l, x), with YOLO-V8 m showing exceptional performance in precision (98%) and recall (97.9%). The study also discusses the importance of early detection and prevention in GI tract disorders, particularly small bowel tumours (SBTs) and colorectal cancer (CRC). The KID dataset, a comprehensive repository of WCE images, is used for training and evaluation. The results demonstrate the effectiveness of YOLO-V8 in polypoid lesion segmentation, with high accuracy and efficiency. The study underscores the need for robust datasets and further research to enhance the performance of automated detection systems in GI imaging. The findings contribute to the development of computer-aided diagnosis tools for early cancer detection and prevention.This paper presents a study on polypoid lesion segmentation using the YOLO-V8 network in wireless video capsule endoscopy (WCE) images. The research addresses the challenge of early detection and removal of polyps, which are precursors to malignancy, in gastrointestinal (GI) tract disorders. WCE is a non-invasive imaging technique that captures images of the GI tract using swallowable camera devices. Due to the large volume of images generated, automated polyp segmentation is crucial for efficient diagnosis. The study evaluates computer-aided approaches for polyp detection using a dataset of labeled anomalies and findings. YOLO-V8, an improved deep learning model, is used for polyp segmentation and is found to perform better than existing methods, achieving high precision and recall. The study highlights the potential of automated detection systems in improving GI polyp identification. The YOLO-V8 model is evaluated across different iterations (n, s, m, l, x), with YOLO-V8 m showing exceptional performance in precision (98%) and recall (97.9%). The study also discusses the importance of early detection and prevention in GI tract disorders, particularly small bowel tumours (SBTs) and colorectal cancer (CRC). The KID dataset, a comprehensive repository of WCE images, is used for training and evaluation. The results demonstrate the effectiveness of YOLO-V8 in polypoid lesion segmentation, with high accuracy and efficiency. The study underscores the need for robust datasets and further research to enhance the performance of automated detection systems in GI imaging. The findings contribute to the development of computer-aided diagnosis tools for early cancer detection and prevention.