A Novel IoMT System for Pathological Diagnosis Based on Intelligent Mobile Scanner and Whole Slide Image Stitching Method

Digital pathology digitizes traditional pathological sections into whole slide images (WSIs), which greatly reduces the workload of pathologists and improves the efficiency of pathological diagnosis. However, conventional pathological scanners are usually bulky and expensive, limiting their popularity in remote and underdeveloped areas, and restricting the development and application of digital pathology in these areas. This paper proposes an efficient and robust Internet of Medical Things (IoMT) system for pathological diagnosis. For data acquisition, we developed an automatic portable pathological section scanner based on mobile Internet, Landing-Smart, which integrates four main components including a smartphone, a glass slide carrier, an electric controller and an optical imaging unit. Through the customized scan app, the smartphone uses its built-in camera to continually capture enlarged images of the field of view (FoV) in the section and uploads the images to the cloud server in real time via mobile internet, where the image processing and stitching method is implemented to generate the WSI of the pathological section. To validate the performance of the proposed system and Landing-Smart, we collect 209 cervical cytology smears and scan them into WSIs using conventional scanners and Landing-Smart, respectively. The double-blinded assessment results have illustrated that the WSIs obtained via Landing-Smart can be comparable to those obtained via general digital pathology scanners.