Semiquantitative Determination of Thiocyanate in Saliva Through Colorimetric Assays: Design of CNN Architecture via Input-Aware NAS

• Published in: IEEE sensors journal 2023-12, Vol.23 (23), p.29869-29876
• Main Authors: Taccioli, Tommaso, Ragusa, Edoardo, Pomili, Tania, Gastaldo, Paolo, Pompa, Pier Paolo
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Assaying; Biomarkers; Cameras; Color; Colorimetric test; Colorimetry; Convolutional neural networks; convolutional neural networks (CNNs); Image color analysis; Lighting; neural architecture search (NAS); Neural networks; point-of-care (POC); Reflectivity; Saliva; Sensor phenomena and characterization; Sensors; smart sensor; Smartphones; Thiocyanates
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2023.3325545

This article presents a novel method enabling point-of-care (POC) testing of thiocyanate concentration in saliva. Thiocyanate is an important biological marker; its levels are linked with diseases such as cancer and neurodegeneration. Hence, monitoring this marker frequently can positively impact users' lives. In the proposed setup, the goal is a semiquantitative reading of thiocyanate concentration from colorimetric assays in solution; the user-friendly, yet accurate readout procedure relies on a smartphone camera and is designed to be robust against moderate changes in indoor lighting conditions. The readout procedure exploits the capabilities of convolutional neural networks (CNNs) to fully profit from a setup involving a custom color chart and the assay vial. Thus, a data-driven strategy is adopted to deal with color distortions caused both by lighting conditions and by postprocessing operations embedded in the smartphone camera. A neural architecture search (NAS) procedure explicitly tuned for the problem at hand drove the design of the custom CNN architecture. The method has been tested using a collection of real-world data and compared with existing approaches. The results presented in this article show an increase in accuracy up to about 14% with respect to state-of-the-art methods.