real-time detection of capsule endoscopy using yolo: a comparative study with gpdnet

Capsule endoscopy (ce) technology is rapidly advancing due to its easy usability, long battery life, and exceptional image quality. the more resolution of ce images, the more time is needed to spend on the detection of a desired content in them. to address the issue, a new approach is presented in this paper using the popular yolo v5 neural network architecture to detect the location and label of lesions in two public ce contents. a gpd neural network based on alexnet is used as a rival classifier. the primary goal of this research is to reduce diagnostic time while maintaining accuracy. the results show a 6% increase in detection accuracy over the well-tailored rival. this is a significant achievement that could have a positive impact on the diagnosis and treatment of various medical domains. interestingly, yolo shows 58% more time-efficiency with an average prediction time of 5.39 milliseconds per frame. the scalability of yolo is also analysed over kvasir. the results indicate, while a workload is increased in 324 magnitudes, its accuracy is boosted more than 1% and it is only slower a 6.95 times graceful degradation, proving yolo's real-time applicability. implementations and supplementary data are available on github.

improving detection of capsule endoscopy using yolo

capsule endoscopy (ce) technology is rapidly advancing due to its easy usability, long battery life, and exceptional image quality. however, the increasing clarity of image sequences captured by ce requires more time and effort to detect desired content. to address this issue, a new approach is presented in this paper using the popular yolo v5 neural network architecture to detect the location and label of lesions in two public ce contents. a gpd neural network based on alexnet is used as a rival classifier. the primary goal of this research is to reduce diagnostic time while maintaining accuracy using yolo, and the results show a 6% increase in detection accuracy over the rival. additionally, yolo is 58% more time-efficient with an average prediction time of 5.39 milliseconds per frame. the scalability of yolo is also analyzed, and results indicate a 6.95 times graceful degradation over kvasir, proving yolo’s real-time applicability. higher resolution inputs lead to better results with yolo. implementations and supplementary data are available on github.