KEYWORDS: Object detection, Portability, Microscopes, Microscopy, Education and training, Medicine, Diseases and disorders, Detection and tracking algorithms, Cameras, 3D printing
Helminth infections affect around 1.5 billion people worldwide but have historically been neglected by major healthcare initiatives. Manual microscopic examination to identify parasite eggs in urine or faeces remains the gold-standard diagnostic, but the technique is time consuming and requires bright-field microscopes which can be expensive to transport and maintain. We present a low-cost device which uses deep learning to automate helminth diagnosis from Kato-Katz (KK) faecal smears. The device comprises a 3D-printed microscope, which connects wirelessly to an Android smartphone. Egg detection is accomplished with a ResNet-50 object detection algorithm, trained on a dataset of over 6,000 images of eggs from six common helminth species. The model is exported to TensorFlow Lite and hosted locally in the app, enabling edge computing and removing the need for external internet connection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.