A study on the use of Edge TPUs for eye fundus image segmentation

• DOI: 10.1016/j.engappai.2021.104384
• Publication Date: 2021-07-27T16:54:35Z
• Authors: Javier Civit-Masot; Francisco Luna-Pe...; José María Rodríg...; Manuel Domínguez-...; Arturo Morgado-Es...; Antón Civit
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Single-board computer; Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Computer Science - Computer Vision and Pattern Recognition; Deep learning; Glaucoma; 02 engineering and technology; Medical image segmentation; Electrical Engineering and Systems Science - Image and Video Processing; Edge TPU; U-Net; Machine Learning (cs.LG); 03 medical and health sciences; Deep Learning; 0302 clinical medicine; FOS: Electrical engineering, electronic engineering, information engineering; 0202 electrical engineering, electronic engineering, information engineering

Preprint of paper published in Engineering Applications of Artificial Intelligence<br/>Medical image segmentation can be implemented using Deep Learning methods with fast and efficient segmentation networks. Single-board computers (SBCs) are difficult to use to train deep networks due to their memory and processing limitations. Specific hardware such as Google's Edge TPU makes them suitable for real time predictions using complex pre-trained networks. In this work, we study the performance of two SBCs, with and without hardware acceleration for fundus image segmentation, though the conclusions of this study can be applied to the segmentation by deep neural networks of other types of medical images. To test the benefits of hardware acceleration, we use networks and datasets from a previous published work and generalize them by testing with a dataset with ultrasound thyroid images. We measure prediction times in both SBCs and compare them with a cloud based TPU system. The results show the feasibility of Machine Learning accelerated SBCs for optic disc and cup segmentation obtaining times below 25 milliseconds per image using Edge TPUs.<br/>