15 March 2018 in IEEE Transactions on Multimedia
We investigate the design of an entire mobile imaging system for early detection of melanoma. Different from previous work, we focus on smartphone-captured visible light images. Our design addresses two major challenges. First, images acquired using a smartphone under loosely-controlled environmental conditions may be subject to various distortions, and this makes melanoma detection more difficult. Second, processing performed on a smartphone is subject to stringent computation and memory constraints. In our work, we propose a detection system that is optimized to run entirely on the resourceconstrained smartphone. Our system intends to localize the skin lesion by combining a lightweight method for skin detection with a hierarchical segmentation approach using two fast segmentation methods. Moreover, we study an extensive set of image features and propose new numerical features to characterize a skin lesion. Furthermore, we propose an improved feature selection algorithm to determine a small set of discriminative features used by the final lightweight system. In addition, we study the human-computer interface (HCI) design to understand the usability and acceptance issues of the proposed system. Our extensive evaluation on an image dataset provided by National Skin Center - Singapore (117 benign nevi and 67 malignant melanoma) confirms the effectiveness of the proposed system for melanoma detection: 89.09% sensitivity at specificity $\ge$ 90%. We demonstrate that a hierarchical segmentation approach using Otsu's and Minimum Spanning Tree (MST) method is robust and computationally-efficient. Our proposed color triangle and border fitting features can capture important information for melanoma detection. Furthermore, our proposed feature selection can identify a small discriminative feature set for the mobile platform. Our work is significant as we investigate the design of an entire system: lesion localization, feature computation, feature selection, classification and HCI design.