Interpretable deep learning for diagnosis of fungal and acanthamoeba keratitis using in vivo confocal microscopy images.

Infectious keratitis refers to a group of corneal disorders in which corneal tissues suffer inflammation and damage caused by pathogenic infections. Among these disorders, fungal keratitis (FK) and acanthamoeba keratitis (AK) are particularly severe and can cause permanent blindness if not diagnosed early and accurately. In Vivo Confocal Microscopy (IVCM) allows for imaging of different corneal layers and provides an important tool for an early and accurate diagnosis. In this paper, we introduce the IVCM-Keratitis dataset, which comprises of a total of 4001 sample images of AK and FK, as well as non-specific keratitis (NSK) and healthy corneas classes. We use this dataset to develop multiple deep-learning models based on Convolutional Neural Networks (CNNs) to provide automated assistance in enhancing the diagnostic accuracy of confocal microscopy in infectious keratitis. Densenet161 had the best performance among these models, with an accuracy, precision, recall, and F1 score of 93.55%, 92.52%, 94.77%, and 96.93%, respectively. Our study highlights the potential of deep learning models to provide automated diagnostic assistance for infectious keratitis via confocal microscopy images, particularly in the early detection of AK and FK. The proposed model can provide valuable support to both experienced and inexperienced eye-care practitioners in confocal microscopy image analysis, by suggesting the most likely diagnosis. We further demonstrate that these models can highlight the areas of infection in the IVCM images and explain the reasons behind their diagnosis by utilizing saliency maps, a technique used in eXplainable Artificial Intelligence (XAI) to interpret these models.

A naturalistic study of brushing patterns using powered toothbrushes.

Dental caries and periodontal disease are very common chronic diseases closely linked to inadequate removal of dental plaque. Powered toothbrushes are viewed as more effective at removing plaque; however, the conflicting evidence and considerable unexplained heterogeneity in their clinical outcomes does not corroborate the relative merits of powered tooth brushing. To explain the heterogeneity of brushing patterns with powered toothbrushes, we conducted a observational study of tooth brushing practices of 12 participants in their naturalistic setting. Integrated brush sensors and a digital data collection platform allowed unobtrusive and accurate capture of habitual brushing patterns. Annotated brushing data from 10 sessions per participant was chosen for scrutiny of brushing patterns. Analysis of brushing patterns from the total 120 sessions revealed substantial between- and within-participant variability in brushing patterns and efficiency. Most participants (91.67%) brushed for less than the generally prescribed two minutes; individual participants were also inconsistent in brushing duration across sessions. The time devoted to brushing different dental regions was also quite unequal. Participants generally brushed their buccal tooth surfaces more than twice as long as the occlusal (2.18 times longer (95% CI 1.42, 3.35; p < 0.001)) and lingual surfaces (2.22 times longer (95% CI 1.62, 3.10; p < 0.001); the lingual surfaces of the maxillary molars were often neglected (p < 0.001). Participants also varied in the epochs of excessive brushing pressure and the regions to which they were applied. In general, the occlusal surfaces were more likely to be brushed with excessive pressure (95% CI 0.10, 0.98; p = 0.015). Our study reveals that users of powered toothbrushes vary substantially in their use of the toothbrushes and diverge from recommended brushing practices. The inconsistent brushing patterns, between and within individuals, can affect effective plaque removal. Our findings underscore the limited uptake of generic oral self-care recommendations and emphasize the need for personalized brushing recommendations that derive from the objective sensor data provided by powered toothbrushes.