An Algorithm for the Estimation of Hemoglobin Level from Digital Images of Palpebral Conjunctiva Based in Digital Image Processing and Artificial Intelligence

Anemia is a common problem that affects a significant part of the world’s population, especially in impoverished countries. This work aims to improve the accessibility of remote diagnostic tools for underserved populations. Our proposal involves implementing algorithms to estimate hemoglobin levels using images of the eyelid conjunctiva and a calibration label captured with a mid-range cell phone. We propose three algorithms: one for calibration label segmentation, another for palpebral conjunctiva segmentation, and the last one for estimating hemoglobin levels based on the segmented images from the previous algorithms. Experiments were performed using a data set of children’s eyelid images and calibration stickers. An L1 norm error of 0.72 g/dL was achieved using the SLIC-GAT model to estimate the hemoglobin level. In conclusion, the integration of these segmentation and regression methods improved the estimation accuracy compared to current approaches, considering that the source of the images was a mid-range commercial camera. The proposed method has the potential for mass screening in low-income rural populations as it is non-invasive, and its simplicity makes it feasible for community health workers with basic training to perform the test. Therefore, this tool could contribute significantly to efforts aimed at combating childhood anemia.