Search

Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. Therefore, we assessed 'All Data are Ext' (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e. providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. Overall, the AI showed higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p<0.001), obtaining a higher sensitivity (0.921, 95% CI 0.900- 0.942 vs. 0.734, 95% CI 0.701-0.770; p<0.001) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p<0.001). As the algorithm exhibited a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists particularly in diagnosing challenging cases.

Background: Convolutional neural network (CNN)-based melanoma classifiers face several challenges that limit their usefulness in clinical practice. Objective: To investigate the impact of multiple real-world dermoscopic views of a single lesion of interest on a CNN-based melanoma classifier. Methods: This study evaluated 656 suspected melanoma lesions. Classifier performance was measured using area under the receiver operating characteristic curve (AUROC), expected calibration error (ECE) and maximum confidence change (MCC) for (I) a single-view scenario, (II) a multiview scenario using multiple artificially modified images per lesion and (III) a multiview scenario with multiple real-world images per lesion. Results: The multiview approach with real-world images significantly increased the AUROC from 0.905 (95% CI, 0.879-0.929) in the single-view approach to 0.930 (95% CI, 0.909-0.951). ECE and MCC also improved significantly from 0.131 (95% CI, 0.105-0.159) to 0.072 (95% CI: 0.052-0.093) and from 0.149 (95% CI, 0.125-0.171) to 0.115 (95% CI: 0.099-0.131), respectively. Comparing multiview real-world to artificially modified images showed comparable diagnostic accuracy and uncertainty estimation, but significantly worse robustness for the latter. Conclusion: Using multiple real-world images is an inexpensive method to positively impact the performance of a CNN-based melanoma classifier.

Although artificial intelligence (AI) systems have been shown to improve the accuracy of initial melanoma diagnosis, the lack of transparency in how these systems identify melanoma poses severe obstacles to user acceptance. Explainable artificial intelligence (XAI) methods can help to increase transparency, but most XAI methods are unable to produce precisely located domain-specific explanations, making the explanations difficult to interpret. Moreover, the impact of XAI methods on dermatologists has not yet been evaluated. Extending on two existing classifiers, we developed an XAI system that produces text and region based explanations that are easily interpretable by dermatologists alongside its differential diagnoses of melanomas and nevi. To evaluate this system, we conducted a three-part reader study to assess its impact on clinicians' diagnostic accuracy, confidence, and trust in the XAI-support. We showed that our XAI's explanations were highly aligned with clinicians' explanations and that both the clinicians' trust in the support system and their confidence in their diagnoses were significantly increased when using our XAI compared to using a conventional AI system. The clinicians' diagnostic accuracy was numerically, albeit not significantly, increased. This work demonstrates that clinicians are willing to adopt such an XAI system, motivating their future use in the clinic.

Homology generators in a relation offer individuals the ability to delay identification, by guiding the order via which the individuals reveal their attributes (see arXiv:1712.04130). This perspective applies as well to the identification of goal-attaining strategies in systems with errorful control, since the strategy complex of a fully controllable nondeterministic or stochastic graph is homotopic to a sphere. Specifically, such a graph contains for each state $v$ a maximal strategy $\sigma_v$ that converges to state $v$ from all other states in the graph and whose identity may be shrouded in the following sense: One may reveal certain actions of $\sigma_v$ in a particular order so that the full strategy becomes known only after at least $n-1$ of these actions have been revealed, with none of the actions revealed definitively inferable from those previously revealed. Here $n$ is the number of states in the graph. Moreover, the strategy contains at least $(n-1)!$ such informative action release sequences, each of length at least $n-1$. The earlier work described above sketched a proof that every maximal strategy in a pure nondeterministic or pure stochastic graph contains at least one informative action release sequence of length at least $n-1$. The primary purpose of the current report is to fill in the details of that sketch. To build intuition, the report first discusses several simpler examples. These examples suggest an underlying structure for hiding capabilities or bluffing capabilities, as well as for detecting such deceit., Comment: 76 pages, 40 figures, numerous examples

Information has intrinsic geometric and topological structure, arising from relative relationships beyond absolute values or types. For instance, the fact that two people share a meal describes a relationship independent of the meal's ingredients. Multiple such relationships give rise to relations and their lattices. Lattices have topology. That topology informs the ways in which information may be observed, hidden, inferred, and dissembled. Dowker's Theorem establishes a homotopy equivalence between two simplicial complexes derived from a relation. From a privacy perspective, one complex describes individuals with common attributes, the other describes attributes shared by individuals. The homotopy equivalence produces a lattice. An element in the lattice consists of two components, one being a set of individuals, the other being a set of attributes. The lattice operations join and meet each amount to set intersection in one component and set union followed by a potentially privacy-puncturing inference in the other component. Privacy loss appears as simplicial collapse of free faces. Such collapse is local, but the property of fully preserving both attribute and association privacy requires a global condition: a particular kind of spherical hole. By looking at the link of an identifiable individual in its encompassing Dowker complex, one can characterize that individual's attribute privacy via another sphere condition. Even when long-term attribute privacy is impossible, homology provides lower bounds on how an individual may defer identification, when that individual has control over how to reveal attributes. Intuitively, the idea is to first reveal information that could otherwise be inferred. This last result highlights privacy as a dynamic process. Privacy loss may be cast as gradient flow. Harmonic flow for privacy preservation may be fertile ground for future research., Comment: 154 pages, 76 figures, main narrative written for a general audience, detailed proofs in appendices

We present and explore a model of stateless and self-stabilizing distributed computation, inspired by real-world applications such as routing on today's Internet. Processors in our model do not have an internal state, but rather interact by repeatedly mapping incoming messages ("labels") to outgoing messages and output values. While seemingly too restrictive to be of interest, stateless computation encompasses both classical game-theoretic notions of strategic interaction and a broad range of practical applications (e.g., Internet protocols, circuits, diffusion of technologies in social networks). We embark on a holistic exploration of stateless computation. We tackle two important questions: (1) Under what conditions is self-stabilization, i.e., guaranteed "convergence" to a "legitimate" global configuration, achievable for stateless computation? and (2) What is the computational power of stateless computation? Our results for self-stabilization include a general necessary condition for self-stabilization and hardness results for verifying that a stateless protocol is self-stabilizing. Our main results for the power of stateless computation show that labels of logarithmic length in the number of processors yield substantial computational power even on ring topologies. We present a separation between unidirectional and bidirectional rings (L/poly vs. P/poly), reflecting the sequential nature of computation on a unidirectional ring, as opposed to the parallelism afforded by the bidirectional ring. We leave the reader with many exciting directions for future research.

On2broker provides brokering services to improve access to heterogeneous, distributed, and semistructured information sources as they are presented in the World Wide Web. It relies on the use of ontologies to make explicit the semantics of Web pages. This paper discusses the general architecture and main components (i.e., query engine, information agent, inference engine, and database manager) of On2broker and provides some application scenarios. The paper shows how semantic based access is provided to Web sources described with HTML (HyperText Markup Language), XML (eXtensible Markup Language), or RDF (Resource Description Framework). (Contains 15 references.) (Author/MES)