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.
Post-acute sequelae of SARS-CoV-2 (PASC) is an increasingly recognized yet incompletely understood public health concern. Several studies have examined various ways to phenotype PASC to better characterize this heterogeneous condition. However, many gaps in PASC phenotyping research exist, including a lack of the following: 1) standardized definitions for PASC based on symptomatology; 2) generalizable and reproducible phenotyping heuristics and meta-heuristics; and 3) phenotypes based on both COVID-19 severity and symptom duration. In this study, we defined computable phenotypes (or heuristics) and meta-heuristics for PASC phenotypes based on COVID-19 severity and symptom duration. We also developed a symptom profile for PASC based on a common data standard. We identified four phenotypes based on COVID-19 severity (mild vs. moderate/severe) and duration of PASC symptoms (subacute vs. chronic). The symptoms groups with the highest frequency among phenotypes were cardiovascular and neuropsychiatric with each phenotype characterized by a different set of symptoms.
Atherosclerotic lesions within carotid and cerebral vessels are likely to influence hemodynamics and manifest into vascular pathologies, including Alzheimers Disease and ischemic stroke. Hemodynamics are influenced by changes in luminal diameter of vessels and wall shear stress derived from turbulence, which directly relates to the surface topography of the lumen. In this study, we performed a quantitative assessment of surface metrology of carotid and cerebral arteries in relation to vessel size and location among individuals. We speculate intracranial vessels will follow suit of extracranial vessels, with increased surface roughness in larger-diameter vessels. Samples of the internal carotid, common carotid, and multiple branches of the Circle of Willis were collected at 18 different sites from 10 human whole body donors. The arterial surface metrology was analyzed using a Sensofar S Neox 3D optical profiler, from which ISO 25718-2 areal roughness parameters, texture direction, motifs analysis, and scale-sensitive fractal analyses were analyzed using SensoMap software. The most significant differences between individuals, though surface roughness appears also greater in the larger vessels. In comparison, the side (left vs. right) is almost immaterial. With further research in this field, the pathophysiology of intracranial atherosclerosis a the role of atherosclerosis in neurodegenerative disorders.
In this paper, we introduce a Variational Autoencoder (VAE) based training approach that can compress and decompress cancer pathology slides at a compression ratio of 1:512, which is better than the previously reported state of the art (SOTA) in the literature, while still maintaining accuracy in clinical validation tasks. The compression approach was tested on more common computer vision datasets such as CIFAR10, and we explore which image characteristics enable this compression ratio on cancer imaging data but not generic images. We generate and visualize embeddings from the compressed latent space and demonstrate how they are useful for clinical interpretation of data, and how in the future such latent embeddings can be used to accelerate search of clinical imaging data.
Power law distributions are widely observed in chemical physics, geophysics, biology, and beyond. The independent variable x of these distributions has an obligatory lower bound and in many cases also an upper bound. Estimating these bounds from sample data is notoriously difficult, with a recent method involving O(N^3) operations, where N denotes sample size. Here I develop an approach for estimating the lower and upper bounds that involves O(N) operations. The approach centers on calculating the mean values, x_min and x_max, of the smallest x and the largest x in N-point samples. A fit of x_min or x_max as a function of N yields the estimate for the lower or upper bound. Application to synthetic data demonstrates the accuracy and reliability of this approach.