ABSTRACT
Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.
ABSTRACT
Automatic visual inspection allows for the identification of surface defects in manufactured parts. Nevertheless, when defects are on a sub-millimeter scale, detection and recognition are a challenge. This is particularly true when the defect generates topological deformations that are not shown with strong contrast in the 2D image. In this paper, we present a method for recognizing surface defects in 3D point clouds. Firstly, we propose a novel 3D local descriptor called the Model Point Feature Histogram (MPFH) for defect detection. Our descriptor is inspired from earlier descriptors such as the Point Feature Histogram (PFH). To construct the MPFH descriptor, the models that best fit the local surface and their normal vectors are estimated. For each surface model, its contribution weight to the formation of the surface region is calculated and from the relative difference between models of the same region a histogram is generated representing the underlying surface changes. Secondly, through a classification stage, the points on the surface are labeled according to five types of primitives and the defect is detected. Thirdly, the connected components of primitives are projected to a plane, forming a 2D image. Finally, 2D geometrical features are extracted and by a support vector machine, the defects are recognized. The database used is composed of 3D simulated surfaces and 3D reconstructions of defects in welding, artificial teeth, indentations in materials, ceramics and 3D models of defects. The quantitative and qualitative results showed that the proposed method of description is robust to noise and the scale factor, and it is sufficiently discriminative for detecting some surface defects. The performance evaluation of the proposed method was performed for a classification task of the 3D point cloud in primitives, reporting an accuracy of 95%, which is higher than for other state-of-art descriptors. The rate of recognition of defects was close to 94%.
ABSTRACT
Our daily interaction with the world is plagued of situations in which we develop expertise through self-motivated repetition of the same task. In many of these interactions, and especially when dealing with computer and machine interfaces, we must deal with sequences of decisions and actions. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion and a specific sequence of choices must be performed in order to produce the expected outcome. But, as we become experts in the use of such interfaces, is it possible to identify specific search and learning strategies? And if so, can we use this information to predict future actions? In addition to better understanding the cognitive processes underlying sequential decision making, this could allow building adaptive interfaces that can facilitate interaction at different moments of the learning curve. Here we tackle the question of modeling sequential decision-making behavior in a simple human-computer interface that instantiates a 4-level binary decision tree (BDT) task. We record behavioral data from voluntary participants while they attempt to solve the task. Using a Hidden Markov Model-based approach that capitalizes on the hierarchical structure of behavior, we then model their performance during the interaction. Our results show that partitioning the problem space into a small set of hierarchically related stereotyped strategies can potentially capture a host of individual decision making policies. This allows us to follow how participants learn and develop expertise in the use of the interface. Moreover, using a Mixture of Experts based on these stereotyped strategies, the model is able to predict the behavior of participants that master the task.