Kidney stone classification with a lightweight model

In this paper, we describe the use of deep learning-based model for classifying kidney stone images in order to overcome the lack of medical infrastructures within the hospitals in the development countries like Madagascar. Moreover, the use of mobile phones such as smartphone is very popularized in these countries. This situation leads us to perform a lightweight deep learning-based model inspired from the architecture of SSDLiteX. The Balancing technical was used to achieve higher performance. Our system provides 100% of accuracy, validation accuracy and F1-score. The result shows that this model surpass all lightweight models recorded to the state of the art about kidney stone classification. According to its nature, the proposed approach could run on the low resource environment like Smartphone. Thus, it is reliable and answer the need of the specialist within the hospitals in the development country.