While convolutional neural networks (CNNs) have successfully been applied for skin lesion classification, previous studies have generally considered only a single clinical/macroscopic image and output a binary decision. In this work, we have presented a method which combines multiple imaging modalities together with patient metadata to improve the performance of automated skin lesion diagnosis. We evaluated our method on a binary classification task for comparison with previous studies as well as a five class classification task representative of a real-world clinical scenario. We showed that our multimodal classifier outperforms a baseline classifier that only uses a single macroscopic image in both binary melanoma detection (AUC 0.866 vs 0.784) and in multiclass classification (mAP 0.729 vs 0.598). In addition, we have quantitatively showed the automated diagnosis of skin lesions using dermatoscopic images obtains a higher performance when compared to using macroscopic images. We performed experiments on a new data set of 2917 cases where each case contains a dermatoscopic image, macroscopic image and patient metadata.
Dedicated to the memory of Robert A. Liebler, a friend and mentor, and a passionate advocate for studying the action of finite nonabelian groups on combinatorial designs.Difference sets have been studied for more than 80 years. Techniques from algebraic number theory, group theory, finite geometry, and digital communications engineering have been used to establish constructive and nonexistence results. We provide a new theoretical approach which dramatically expands the class of 2-groups known to contain a difference set, by refining the concept of covering extended building sets introduced by Davis and Jedwab in 1997. We then describe how product constructions and other methods can be used to construct difference sets in some of the remaining 2-groups. In particular, we determine that all groups of order 256 not excluded by the two classical nonexistence criteria contain a difference set, in agreement with previous findings for groups of order 4, 16, and 64. We provide suggestions for how the existence question for difference sets in 2-groups of all orders might be resolved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.