Search

SignificanceOral cancer is one of the most prevalent cancers, especially in middle- and low-income countries such as India. Automatic segmentation of oral cancer images can improve the diagnostic workflow, which is a significant task in oral cancer image analysis. Despite the remarkable success of deep-learning networks in medical segmentation, they rarely provide uncertainty quantification for their output.AimWe aim to estimate uncertainty in a deep-learning approach to semantic segmentation of oral cancer images and to improve the accuracy and reliability of predictions.ApproachThis work introduced a UNet-based Bayesian deep-learning (BDL) model to segment potentially malignant and malignant lesion areas in the oral cavity. The model can quantify uncertainty in predictions. We also developed an efficient model that increased the inference speed, which is almost six times smaller and two times faster (inference speed) than the original UNet. The dataset in this study was collected using our customized screening platform and was annotated by oral oncology specialists.ResultsThe proposed approach achieved good segmentation performance as well as good uncertainty estimation performance. In the experiments, we observed an improvement in pixel accuracy and mean intersection over union by removing uncertain pixels. This result reflects that the model provided less accurate predictions in uncertain areas that may need more attention and further inspection. The experiments also showed that with some performance compromises, the efficient model reduced computation time and model size, which expands the potential for implementation on portable devices used in resource-limited settings.ConclusionsOur study demonstrates the UNet-based BDL model not only can perform potentially malignant and malignant oral lesion segmentation, but also can provide informative pixel-level uncertainty estimation. With this extra uncertainty information, the accuracy and reliability of the model’s prediction can be improved.

In medical imaging, deep learning-based solutions have achieved state-of-the-art performance. However, reliability restricts the integration of deep learning into practical medical workflows since conventional deep learning frameworks cannot quantitatively assess model uncertainty. In this work, we propose to address this shortcoming by utilizing a Bayesian deep network capable of estimating uncertainty to assess oral cancer image classification reliability. We evaluate the model using a large intraoral cheek mucosa image dataset captured using our customized device from high-risk population to show that meaningful uncertainty information can be produced. In addition, our experiments show improved accuracy by uncertainty-informed referral. The accuracy of retained data reaches roughly 90% when referring either 10% of all cases or referring cases whose uncertainty value is greater than 0.3. The performance can be further improved by referring more patients. The experiments show the model is capable of identifying difficult cases needing further inspection.

SignificanceEarly detection of oral cancer is vital for high-risk patients, and machine learning-based automatic classification is ideal for disease screening. However, current datasets collected from high-risk populations are unbalanced and often have detrimental effects on the performance of classification.AimTo reduce the class bias caused by data imbalance.ApproachWe collected 3851 polarized white light cheek mucosa images using our customized oral cancer screening device. We use weight balancing, data augmentation, undersampling, focal loss, and ensemble methods to improve the neural network performance of oral cancer image classification with the imbalanced multi-class datasets captured from high-risk populations during oral cancer screening in low-resource settings.ResultsBy applying both data-level and algorithm-level approaches to the deep learning training process, the performance of the minority classes, which were difficult to distinguish at the beginning, has been improved. The accuracy of "premalignancy" class is also increased, which is ideal for screening applications.ConclusionsExperimental results show that the class bias induced by imbalanced oral cancer image datasets could be reduced using both data- and algorithm-level methods. Our study may provide an important basis for helping understand the influence of unbalanced datasets on oral cancer deep learning classifiers and how to mitigate.

Global use of energy-inefficient mechanical vapor-compression air conditioning (AC) is increasing dramatically for home cooling. Direct evaporative coolers (EC) offer substantial energy savings, and may provide a sustainable alternative to AC for homes in hot, dry climates. One drawback of ECs is the potential for infiltration of outdoor air pollution into homes. Prior studies on this topic are limited by small sample sizes and a lack of comparison homes. In this study, we used aerosol photometers to sample indoor and outdoor fine particulate matter (PM2.5) from 16 homes with AC and 14 homes with EC in Utah County, Utah (USA) between July 2022 and August 2023. We observed a significantly larger infiltration factor (Fin) of outdoor PM2.5 in EC vs. AC homes (0.39 vs. 0.12, p = 0.026) during summer. Fin significantly increased during a wildfire smoke event that occurred during the study. During the wildfire event, EC homes offered little to no protection from outdoor PM2.5 (Fin = 0.96, 95% confidence interval (CI) 0.85, 1.07), while AC homes offered significant protection (Fin = 0.23, 95% CI 0.15, 0.32). We recommend additional research focused on cooling pad design for the dual benefits of cooling efficiency and particle filtration. [ABSTRACT FROM AUTHOR]

The article features Commander Rick Husband of Texas and how he became a member of the American Astronaut Corps. Also cited are the tragic accident involving the Space Shuttle Columbia that led to the deaths of Husband, Willie McCool, David Brown, Laurel Clark, Ilan Ramon, Mike Anderson, and Kalpana Chawla, and how members of the astronaut corps are selected.

Two-mirror telescopes possess an agreeable tradeoff between performance and complexity that suits the needs of many scientific tasks, and recent developments in manufacturing technology have enabled unobscured two-mirror designs with freeform surfaces. We illustrate how structural aberration coefficients reveal the fundamental aberration characteristics of such systems and provide a summary table of general solutions that prescribe freeform surface shapes and tilts. Two unobscured design forms with remarkable aberration cancellation, inspired by well-known on-axis anastigmatic solutions, are presented. [ABSTRACT FROM AUTHOR]

Freeform imaging systems are a subject of current interest. To aid in the design of such systems, we introduce structural aberration coefficients for plane symmetric imaging with XY-polynomial freeform surfaces that may also be tilted. Further, we extend the coefficients to systems with an arbitrary number of components and specifically provide analytical equations for two-mirror systems. Distinguishing between system configuration and structural parameters enhances clarity, which we highlight by deriving new conditions for minimum root-mean-square (RMS) spot size and minimum RMS wavefront error in aplanatic two-mirror telescopes. [ABSTRACT FROM AUTHOR]