Affordable artificial intelligence-based digital pathology for neglected tropical diseases: A proof-of-concept for the detection of soil-transmitted helminths and Schistosoma mansoni eggs in Kato-Katz stool thick smears

BackgroundWith the World Health Organization's (WHO) publication of the 2021-2030 neglected tropical diseases (NTDs) roadmap, the current gap in global diagnostics became painfully apparent. Improving existing diagnostic standards with state-of-the-art technology and artificial intelligence has the potential to close this gap. Methodology/Principal findingsWe prototyped an artificial intelligence-based digital pathology (AI-DP) device to explore automated scanning and detection of helminth eggs in stool prepared with the Kato-Katz (KK) technique, the current diagnostic standard for diagnosing soil-transmitted helminths (STHs; Ascaris lumbricoides, Trichuris trichiura and hookworms) and Schistosoma mansoni (SCH) infections. First, we embedded a prototype whole slide imaging scanner into field studies in Cambodia, Ethiopia, Kenya and Tanzania. With the scanner, over 300 KK stool thick smears were scanned, resulting in total of 7,780 field-of-view (FOV) images containing 16,990 annotated helminth eggs (Ascaris: 8,600; Trichuris: 4,083; hookworms: 3,623; SCH: 684). Around 90% of the annotated eggs were used to train a deep learning-based object detection model. From an unseen test set of 752 FOV images containing 1,671 manually verified STH and SCH eggs (the remaining 10% of annotated eggs), our trained object detection model extracted and classified helminth eggs from co-infected FOV images in KK stool thick smears, achieving a weighted average precision (+/- standard deviation) of 94.9% +/- 0.8% and a weighted average recall of 96.1% +/- 2.1% across all four helminth egg species. Conclusions/SignificanceWe present a proof-of-concept for an AI-DP device for automated scanning and detection of helminth eggs in KK stool thick smears. We identified obstacles that need to be addressed before the diagnostic performance can be evaluated against the target product profiles for both STH and SCH. Given that these obstacles are primarily associated with the required hardware and scanning methodology, opposed to the feasibility of AI-based results, we are hopeful that this research can support the 2030 NTDs road map and eventually other poverty-related diseases for which microscopy is the diagnostic standard. Author summaryRecently, the World Health Organization (WHO) published its 2021-2030 road map for neglected tropical diseases (NTDs). While diagnostics are clearly pivotal to steer the NTD endemic countries towards the ambitious targets set, the current gap in the global diagnostic armamentarium for NTDs once more becomes painfully apparent. As most NTD programs mainly rely on microscopic examination of slides, automation of slide scanning coupled with artificial intelligence (AI) has the potential to close this diagnostic gap by 2030. Therefore, we developed a device to automate scanning of stool smears and deployed it in four endemic countries to build an image data base for both intestinal and blood-dwelling worms. After the images were annotated, we used 90% to train and 10% to validate an AI model. As the AI model was able to reliably recognise worm eggs, we provided a proof-of-concept for automated scanning and detection of worm eggs in stool smears. We identified important obstacles for both the slide scanning device and the application of AI, but we are hopeful that this research can support the 2030 NTDs roadmap and eventually other NTDs for which microscopic examination is the diagnostic standard.