A framework for detecting arsenic disease

Humans are exposed to arsenic (As) primarily from air, food and water. Anyone can develop arsenic toxicity as a result of arsenic exposure. Most of the reports of chronic as well as toxicity in human focus attention on skin manifestations because of its diagnostic specificity. A dermal manifestation such as hyperpigmentation is diagnostic of chronic arsenicosis. This paper focuses on designing and modelling a system that will collate Pigmented Skin Lesion (PSL), their analysis, corresponding observations and conclusions by medical experts using prototyping methodology. The system uses computational intelligence technique to analyse, process, and classify the image library data based on texture and morphological features of the images. A user in a remote location can use mobile data acquisition devices (such as smartphone) to generate images of PSL, supply such images as input to the proposed system, which in turns should intelligently be able to specify the arsenic poisoned hyperpigmentation status of the imaged PSL. The system has been evaluated with a set of images and found that the system can almost accurately detect arsenic.