ACM technique for recognition of region of interest using contour and colour features

In the present situation human health is a very important factor. With today’s growing technology, health conditions are deteriorating day by day. Malnutrition, lifestyle play a very important role. These are leading to many diseases such as respiratory infections, heart disease, diabetes, Cancer, Alzheimer’s, strokes and many more. Among these, few diseases are curable, due to the facilities available. Whereas few may be non-curable if care is not taken in the initial stages. Cancer poses the biggest threat among all life-threatening diseases. An efficient lesion segmentation method is introduced for the detection of Melanoma skin cancer disease at the preliminary stages using Adaptive Contour Model (ACM). High-quality segmentation is achieved based on contour features and sharp edge detection using ACM. The performance of the proposed Adaptive Contour Model (ACM) is tested upon PH2 and ISIC Challenge 2017 Dataset. The Performance matrices for the segmentation process are measured in terms of \(Jaccard\) $\mathit{Jaccard}$  index (JA), Dice coefficient (DI) and accuracy that are found to be 79.23, 87.26 and 94.63 considering ISIC dataset and 89.14, 93.98 and 96.95 which is quite high considering PH2 dataset. A method for detection of melanoma has been the critical need of the day. The proposed method shows that the performance of the Adaptive Contour Model (ACM) is more than 95%, which is better than other methods.